diff --git a/_typos.toml b/_typos.toml
index d3031fb6f45..57eb6970da2 100644
--- a/_typos.toml
+++ b/_typos.toml
@@ -37,9 +37,6 @@ Moible = "Moible"
 Operaton = "Operaton"
 Optimizaing = "Optimizaing"
 Optimzier = "Optimzier"
-REGISTE = "REGISTE"
-Reivew = "Reivew"
-Reuqest = "Reuqest"
 Setment = "Setment"
 Similarily = "Similarily"
 Simle = "Simle"
@@ -99,6 +96,7 @@ fundemental = "fundemental"
 funtion = "funtion"
 ilter = "ilter"
 inferface = "inferface"
+infor = "infor"
 instert = "instert"
 instrinsics = "instrinsics"
 interchangable = "interchangable"
@@ -135,15 +133,6 @@ overrided = "overrided"
 overwrited = "overwrited"
 porcess = "porcess"
 processer = "processer"
-recevied = "recevied"
-recomment = "recomment"
-registerd = "registerd"
-registring = "registring"
-reivew = "reivew"
-relase = "relase"
-requirments = "requirments"
-resut = "resut"
-resuts = "resuts"
 sacle = "sacle"
 samle = "samle"
 satifies = "satifies"
diff --git a/docs/api/gen_alias_api.py b/docs/api/gen_alias_api.py
index 0a6d3b1393e..b011a424e23 100644
--- a/docs/api/gen_alias_api.py
+++ b/docs/api/gen_alias_api.py
@@ -121,7 +121,7 @@ def transform_file_to_api(self, file_path, api_last_name):
         return api
 
     # find the shortest path api which not starts with paddle.fluid
-    def _choose_recomment_api(self, api_list):
+    def _choose_recommend_api(self, api_list):
         min_len = len(api_list[0].split("."))
         rec_api = api_list[0]
         for api in api_list:
@@ -135,7 +135,7 @@ def sort_alias_name(self, api_list):
         real_api = self._choose_real_api(api_list)
         api_list.remove(real_api)
 
-        rec_api = self._choose_recomment_api(api_list)
+        rec_api = self._choose_recommend_api(api_list)
         api_list.remove(rec_api)
 
         # sort others api by path length
diff --git a/docs/design/mkldnn/acquire_api/acquire_api.md b/docs/design/mkldnn/acquire_api/acquire_api.md
index 622f777c304..726bebb186e 100644
--- a/docs/design/mkldnn/acquire_api/acquire_api.md
+++ b/docs/design/mkldnn/acquire_api/acquire_api.md
@@ -70,7 +70,7 @@ Having memory objects and computational primitive we may trigger its execution .
 #### 5. Registering MKL-DNN memory format in corresponding Tensor
 Last step is to register MKL-DNN output memory object format inside of Output tensor eg. set Tensor::format_ to MKL-DNN enum that corresponds the way Tensor data is arranged (NCHW, NCHW16C etc.) This enum can be taken from dst memory object (wrapper to Output tensor) in Forward pass or from diff_src memory object (wrapper to X_grad Tensor).
 
-Example of registring MKL-DNN format in output tensor:
+Example of registering MKL-DNN format in output tensor:
 
     out->set_layout(framework::DataLayout::kMKLDNN);
     out->set_format(platform::GetMKLDNNFormat(*dst_memory));
diff --git a/docs/design/mkldnn/gru/gru.md b/docs/design/mkldnn/gru/gru.md
index d24e4c25b6b..c4f719e2886 100644
--- a/docs/design/mkldnn/gru/gru.md
+++ b/docs/design/mkldnn/gru/gru.md
@@ -95,7 +95,7 @@ oneDNN `GRU` operator is based on Paddle Paddle `fusion_gru` operator. It uses p
 * PaddlePaddle Input LoD -> oneDNN TNC/NTC\
 Every time before executing `GRU`, each batch represented by PP tensor has to be converted into oneDNN tensor representation. It is done first by calculating length of the longest sentence in a batch to get `T` dimension and then creating oneDNN memory (or getting it from oneDNN cache). After that, based on the memory format chosen by oneDNN GRU primitive: `TNC` or `NTC` correct custom reorder is called.\
 \
-Because oneDNN assumes that all sentences are of equal length, before reorder, whole memory is set to 0 to add padding. Placement of this padding depends also on computation direction that is defined by `is_reverse` attribute. To get correct resuts, if computation is performed from left to right, the padding has to be on the right side of words. Otherwise, for right to left computation, it has to be on the left side.
+Because oneDNN assumes that all sentences are of equal length, before reorder, whole memory is set to 0 to add padding. Placement of this padding depends also on computation direction that is defined by `is_reverse` attribute. To get correct results, if computation is performed from left to right, the padding has to be on the right side of words. Otherwise, for right to left computation, it has to be on the left side.
 ![](images/input_is_reverse.svg)
 
 * PaddlePaddle WeightX -> oneDNN WeightX\
diff --git a/docs/design/others/releasing_process.md b/docs/design/others/releasing_process.md
index 4913524f381..1fd91564d1e 100644
--- a/docs/design/others/releasing_process.md
+++ b/docs/design/others/releasing_process.md
@@ -43,7 +43,7 @@ PaddlePaddle 开发过程使用[git-flow](http://nvie.com/posts/a-successful-git
 * 其他用户的 fork 版本库并不需要严格遵守[git-flow](http://nvie.com/posts/a-successful-git-branching-model/)分支规范，但所有 fork 的版本库的所有分支都相当于特性分支。
     * 建议，开发者 fork 的版本库使用`develop`分支同步主版本库的`develop`分支
     * 建议，开发者 fork 的版本库中，再基于`develop`版本 fork 出自己的功能分支。
-    * 当功能分支开发完毕后，向 PaddlePaddle 的主版本库提交`Pull Reuqest`，进而进行代码评审。
+    * 当功能分支开发完毕后，向 PaddlePaddle 的主版本库提交`Pull Request`，进而进行代码评审。
         * 在评审过程中，开发者修改自己的代码，可以继续在自己的功能分支提交代码。
 
 * BugFix 分支也是在开发者自己的 fork 版本库维护，与功能分支不同的是，BugFix 分支需要分别给主版本库的`master`、`develop`与可能有的`release/版本号`分支，同时提起`Pull Request`。
diff --git a/docs/design/phi/design_cn.md b/docs/design/phi/design_cn.md
index 6ccbf426fa8..ba673e69b8c 100644
--- a/docs/design/phi/design_cn.md
+++ b/docs/design/phi/design_cn.md
@@ -1670,7 +1670,7 @@ Fc(const Context& dev_ctx, const Tensor& x, const Tensor& w, const Tensor& b, Te
     phi::add<T, Context>(phi::mul<T，Context>(x, w), b, out);
 }
 
-PT_REGISTE_KERNEL("fc", Fc, ...)
+PT_REGISTER_KERNEL("fc", Fc, ...)
 ```
 
 mul 和 add 操作的拼接，代码量很少，再加一个注册声明。
diff --git a/docs/design/phi/kernel_migrate_en.md b/docs/design/phi/kernel_migrate_en.md
index f2a062ec0a8..e5d6987a2d6 100644
--- a/docs/design/phi/kernel_migrate_en.md
+++ b/docs/design/phi/kernel_migrate_en.md
@@ -304,7 +304,7 @@ Differences include:
 1. The name of the registered macro is different, here is `PD_REGISTER_PLUGIN_KERNEL`.
 2. The name of the Backend is the name of the CustomDevice registered by the user, here is `ascend`.
 
-The kernel that registerd by REGISTER_OP_KERNEL_WITH_CUSTOM_TYPE in Fluid is also registered using `PD_REGISTER_KERNEL` or `PD_REGISTER_PLUGIN_KERNEL` in PHI. It should be noted that if there are two types of kernel template parameters registered in fluid, since the kernel registered in PHI only supports one type, the first type is used in PHI registration. For example, the example under fluid:
+The kernel that registered by REGISTER_OP_KERNEL_WITH_CUSTOM_TYPE in Fluid is also registered using `PD_REGISTER_KERNEL` or `PD_REGISTER_PLUGIN_KERNEL` in PHI. It should be noted that if there are two types of kernel template parameters registered in fluid, since the kernel registered in PHI only supports one type, the first type is used in PHI registration. For example, the example under fluid:
 
 ```c++
 
diff --git a/docs/dev_guides/git_guides/code_review_en.md b/docs/dev_guides/git_guides/code_review_en.md
index 10f8cee4268..889684721e2 100644
--- a/docs/dev_guides/git_guides/code_review_en.md
+++ b/docs/dev_guides/git_guides/code_review_en.md
@@ -1,4 +1,4 @@
-# Code Reivew promise
+# Code Review promise
 
 In order that reviewers focus on code in the code review,please follow these rules every time you submit your code:
 
@@ -8,11 +8,11 @@ In order that reviewers focus on code in the code review,please follow these rul
 
 In addition,please follow the following regulations in response to the suggestion of reviewers:
 
-1）A reply to every comment of reviewers（It's a fundamental complimentary conduct in open source community.An expression of appreciation is a need for help from others):
+1）A reply to every comment of reviewers(It's a fundamental complimentary conduct in open source community.An expression of appreciation is a need for help from others):
 
    - If you adopt the suggestion of reviewer and make a modification accordingly, it's courteous to reply with a simple `Done` .
 
-   - Please clarify your reason to the disagreenment
+   - Please clarify your reason to the disagreement
 
 2）If there are many suggestions
 
diff --git a/docs/dev_guides/op_optimization/kernel_primitive_api/add_example_cn.md b/docs/dev_guides/op_optimization/kernel_primitive_api/add_example_cn.md
index f0f2532f90c..cb293690884 100644
--- a/docs/dev_guides/op_optimization/kernel_primitive_api/add_example_cn.md
+++ b/docs/dev_guides/op_optimization/kernel_primitive_api/add_example_cn.md
@@ -39,7 +39,7 @@ __device__ void ElementwiseAddImpl(InT *in0, InT * in1, OutT * out, OpFunc func,
   ReadData<InT, InT, VecSize, 1, 1, IsBoundary>(arg0, in0, num);
   ReadData<InT, InT, VecSize, 1, 1, IsBoundary>(arg1, in1, num);
 
-  // compute resut[i] = args[i] + arg1[i]
+  // compute result[i] = args[i] + arg1[i]
   ElementwiseBinary<InT, OutT, VecSize, 1, 1, OpFunc>(result, arg0, arg1, func);
 
   // write data
diff --git a/docs/dev_guides/op_optimization/kernel_primitive_api/add_example_en.md b/docs/dev_guides/op_optimization/kernel_primitive_api/add_example_en.md
index eb9cb65f665..d199f595452 100644
--- a/docs/dev_guides/op_optimization/kernel_primitive_api/add_example_en.md
+++ b/docs/dev_guides/op_optimization/kernel_primitive_api/add_example_en.md
@@ -38,7 +38,7 @@ __device__ void ElementwiseAddImpl(InT *in0, InT * in1, OutT * out, OpFunc func,
   ReadData<InT, InT, VecSize, 1, 1, IsBoundary>(arg0, in0, num);
   ReadData<InT, InT, VecSize, 1, 1, IsBoundary>(arg1, in1, num);
 
-  // compute resut[i] = args[i] + arg1[i]
+  // compute result[i] = args[i] + arg1[i]
   ElementwiseBinary<InT, OutT, VecSize, 1, 1, OpFunc>(result, arg0, arg1, func);
 
   // write data
diff --git a/docs/eval/evaluation_of_docs_system.md b/docs/eval/evaluation_of_docs_system.md
index 588ec95b9bc..04a5c0426d6 100644
--- a/docs/eval/evaluation_of_docs_system.md
+++ b/docs/eval/evaluation_of_docs_system.md
@@ -779,7 +779,7 @@ Paddle 当前文档中的 Tutorial，特别是初级内容部分，都很好的
 - 模型保存
 - 推理
 
-这里面包含了很多“干货”的内容，但是我觉得放在“升级指南”中有“明珠暗投”的风险。因为一般人对“升级指南”的刻板印象，应该类似是“relase log”级别的东西，可能会不会优先点开。
+这里面包含了很多“干货”的内容，但是我觉得放在“升级指南”中有“明珠暗投”的风险。因为一般人对“升级指南”的刻板印象，应该类似是“release log”级别的东西，可能会不会优先点开。
 
 据我体验，升级指南中的 [使用高层 API](https://www.paddlepaddle.org.cn/documentation/docs/zh/guides/01_paddle2.0_introduction/update_cn.html#id4) 和 [使用基础 API](https://www.paddlepaddle.org.cn/documentation/docs/zh/guides/01_paddle2.0_introduction/update_cn.html#id5) 包含了其它地方没有的内容，这些内容被用户错过的话，是可惜的。
 
diff --git a/docs/faq/2.0.md b/docs/faq/2.0.md
index d9a3043feaf..628aa60b57d 100644
--- a/docs/faq/2.0.md
+++ b/docs/faq/2.0.md
@@ -35,7 +35,7 @@
 
 1. 删除依赖这些库的 API，原来 Paddle 基于这些第三方库提供了一些 API，在删除这些依赖库的同时也删除了这些 API，如：移除 matplotlib 的同时，paddle.utils.plot 也被删除了。
 
-2. 删除依赖第三方库的数据集，如：移除 nltk 的同时，依赖 nltk 的数据集 sentiment(nltk.movie_reivew)也被删除了。
+2. 删除依赖第三方库的数据集，如：移除 nltk 的同时，依赖 nltk 的数据集 sentiment(nltk.movie_review)也被删除了。
 
 3. 删除依赖的第三方库后，如果需要使用这些库，需要重新安装`pip install objgraph`，直接 import objgraph 可能会报错。
 
diff --git a/docs/guides/jit/limitations_cn.md b/docs/guides/jit/limitations_cn.md
index 1063731868f..d25b02ae18d 100644
--- a/docs/guides/jit/limitations_cn.md
+++ b/docs/guides/jit/limitations_cn.md
@@ -351,7 +351,7 @@ TypeError: In transformed code:
             out.append(i)
         return out
 
-TypeError: All values in `initialized_list` should be Variable, but recevied <class 'list'>.
+TypeError: All values in `initialized_list` should be Variable, but received <class 'list'>.
 ```
 
 **修改建议**：推荐将 [1,2] 和 [2,3] 转为 tensor，变为单层 list。如下面写法：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/args_name_diff/torch.autograd.function.FunctionCtx.mark_non_differentiable.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/args_name_diff/torch.autograd.function.FunctionCtx.mark_non_differentiable.md
deleted file mode 100644
index 4b534c6392b..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/args_name_diff/torch.autograd.function.FunctionCtx.mark_non_differentiable.md
+++ /dev/null
@@ -1,18 +0,0 @@
-## [ 仅参数名不一致 ]torch.autograd.function.FunctionCtx.mark_non_differentiable
-### [torch.autograd.function.FunctionCtx.mark_non_differentiable](https://pytorch.org/docs/stable/generated/torch.autograd.function.FunctionCtx.mark_non_differentiable.html#torch.autograd.function.FunctionCtx.mark_non_differentiable)
-```python
-torch.autograd.function.FunctionCtx.mark_non_differentiable(*args)
-```
-
-### [paddle.autograd.PyLayerContext.mark_non_differentiable](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/autograd/PyLayerContext_cn.html#mark-non-differentiable-self-tensors)
-```python
-paddle.autograd.PyLayerContext.mark_non_differentiable(*tensors)
-```
-
-两者功能一致，仅参数名不一致，具体如下：
-
-### 参数映射
-
-| PyTorch | PaddlePaddle | 备注                          |
-| ------- | ------------ | ----------------------------- |
-| args    | tensors      | 需要标记不需要反向的 Tensor。 |
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/args_name_diff/torch.nn.Unfold.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/args_name_diff/torch.nn.Unfold.md
deleted file mode 100644
index 899dec470f1..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/args_name_diff/torch.nn.Unfold.md
+++ /dev/null
@@ -1,28 +0,0 @@
-## [ 仅参数名不一致 ]torch.nn.Unfold
-### [torch.nn.Unfold](https://pytorch.org/docs/stable/generated/torch.nn.Unfold.html?highlight=nn+unfold#torch.nn.Unfold)
-```python
-torch.nn.Unfold(kernel_size,
-                dilation=1,
-                padding=0,
-                stride=1)
-```
-
-### [paddle.nn.Unfold](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/nn/Unfold_cn.html#unfold)
-```python
-paddle.nn.Unfold(kernel_sizes=[3, 3],
-                    strides=1,
-                    paddings=1,
-                    dilations=1,
-                    name=None)
-```
-
-其中功能一致, 仅参数名不一致，具体如下：
-
-### 参数映射
-
-| PyTorch       | PaddlePaddle | 备注                                                   |
-| ------------- | ------------ | ------------------------------------------------------ |
-| kernel_size   | kernel_sizes  | 卷积核的尺寸。                    |
-| dilation      | dilations     | 卷积膨胀。                        |
-| padding       | paddings     | 每个维度的扩展，仅参数名不一致。  |
-| stride        | strides      | 卷积步长，仅参数名不一致。        |
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/args_name_diff/torch.nn.functional.log_sigmoid.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/args_name_diff/torch.nn.functional.logsigmoid.md
similarity index 100%
rename from docs/guides/model_convert/convert_from_pytorch/api_difference/args_name_diff/torch.nn.functional.log_sigmoid.md
rename to docs/guides/model_convert/convert_from_pytorch/api_difference/args_name_diff/torch.nn.functional.logsigmoid.md
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/args_name_diff/transformers.StoppingCriteriaList.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/args_name_diff/transformers.StoppingCriteriaList.md
deleted file mode 100644
index 330c2787468..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/args_name_diff/transformers.StoppingCriteriaList.md
+++ /dev/null
@@ -1,19 +0,0 @@
-## [ 仅参数名不一致 ]transformers.StoppingCriteriaList
-### [transformers.StoppingCriteriaList](https://github.com/huggingface/transformers/blob/d625294d79341662784495551abdf45e6cb9372f/src/transformers/generation/stopping_criteria.py#L503)
-```python
-transformers.StoppingCriteriaList(input_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs)
-```
-
-### [paddlenlp.generation.StoppingCriteriaList](https://github.com/PaddlePaddle/PaddleNLP/blob/e336e78c338d2514ee6c937982ce5d8c960b85ff/paddlenlp/generation/stopping_criteria.py#L72)
-```python
-paddlenlp.generation.StoppingCriteriaList(input_ids: paddle.Tensor, scores: paddle.Tensor, **kwargs)
-```
-
-两者功能一致，仅参数名不一致，具体如下：
-
-### 参数映射
-
-| transformers      | PaddlePaddle      | 备注                                     |
-| ----------------- | ----------------- | --------------------------------------- |
-| input_ids         | input_ids         | 输入(tokens) 的 id 组成的 Tensor。 |
-| scores            | scores            | 得分组成的 Tensor，仅参数名不一致。 |
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/composite_implement/torch.is_pinned.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/composite_implement/torch.Tensor.is_pinned.md
similarity index 100%
rename from docs/guides/model_convert/convert_from_pytorch/api_difference/composite_implement/torch.is_pinned.md
rename to docs/guides/model_convert/convert_from_pytorch/api_difference/composite_implement/torch.Tensor.is_pinned.md
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/input_args_type_diff/torchvision.transforms.RandomAffine.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/input_args_type_diff/torchvision.transforms.RandomAffine.md
deleted file mode 100644
index ae88388597e..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/input_args_type_diff/torchvision.transforms.RandomAffine.md
+++ /dev/null
@@ -1,55 +0,0 @@
-## [ 输入参数类型不一致 ]torchvision.transforms.RandomAffine
-### [torchvision.transforms.RandomAffine](https://pytorch.org/vision/main/generated/torchvision.transforms.RandomAffine.html)
-```python
-torchvision.transforms.RandomAffine(
-    degrees: Union[List[float], Tuple[float, ...], float],
-    translate: Optional[Tuple[float, float]] = None,
-    scale: Optional[Tuple[float, float]] = None,
-    shear: Union[List[float], Tuple[float, ...], float] = None,
-    interpolation: InterpolationMode = InterpolationMode.NEAREST,
-    fill: Union[int, float, List[float], Tuple[float, ...]] = 0,
-    center: Optional[Union[List[int], Tuple[int, ...]]] = None
-)
-```
-
-### [paddle.vision.transforms.RandomAffine](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/RandomAffine_cn.html)
-```python
-paddle.vision.transforms.RandomAffine(
-    degrees: Union[Tuple[float, float], float, int],
-    translate: Optional[Union[Sequence[float], float, int]] = None,
-    scale: Optional[Tuple[float, float]] = None,
-    shear: Optional[Union[Sequence[float], float, int]] = None,
-    interpolation: Union[str, int] = 'nearest',
-    fill: Union[int, List[int], Tuple[int, ...]] = 0,
-    center: Optional[Tuple[int, int]] = None,
-    keys: Optional[Union[List[str], Tuple[str, ...]]] = None
-)
-```
-
-两者功能一致但参数类型不一致，具体如下：
-
-### 参数映射
-
-| torchvision        | PaddlePaddle    | 备注                      |
-| ------------------ | ---------------- | ------------------------ |
-| degrees           | degrees           | 随机旋转变换的角度大小。 |
-| translate         | translate         | 随机水平平移和垂直平移变化的位移大小。 |
-| scale             | scale             | 随机伸缩变换的比例大小。  |
-| shear             | shear             | 随机剪切角度的大小范围。  |
-| interpolation     | interpolation     | 插值的方法，PyTorch 参数为 InterpolationMode 枚举类, Paddle 参数为 int 或 string，需要转写。 |
-| fill              | fill              | 对图像扩展时填充的像素值。   |
-| center            | center            | 仿射变换的中心点坐标。   |
-| -                 | keys              | 输入的类型，PyTorch 无此参数，Paddle 保持默认即可。     |
-
-
-### 转写示例
-#### interpolation：插值的方法
-```python
-# PyTorch 写法
-transform = torchvision.transforms.RandomAffine(degrees=30, translate=(0.1, 0.2), scale=(0.8, 1.2), shear=10, interpolation=torchvision.transforms.InterpolationMode.BILINEAR, fill=0, center=(100, 100))
-transformed_img = transform(img)
-
-# Paddle 写法
-transform = paddle.vision.transforms.RandomAffine(degrees=30, translate=(0.1, 0.2), scale=(0.8, 1.2), shear=10, interpolation='bilinear', fill=0, center=(100, 100))
-transformed_img = transform(img)
-```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/input_args_type_diff/torchvision.transforms.RandomRotation.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/input_args_type_diff/torchvision.transforms.RandomRotation.md
deleted file mode 100644
index 2e0e568f556..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/input_args_type_diff/torchvision.transforms.RandomRotation.md
+++ /dev/null
@@ -1,48 +0,0 @@
-## [ 输入参数类型不一致 ]torchvision.transforms.RandomRotation
-### [torchvision.transforms.RandomRotation](https://pytorch.org/vision/main/generated/torchvision.transforms.RandomRotation.html)
-```python
-torchvision.transforms.RandomRotation(
-    degrees: Union[int, List[float], Tuple[float, ...]],
-    interpolation: InterpolationMode = InterpolationMode.NEAREST,
-    expand: bool = False,
-    center: Optional[Union[List[float], Tuple[float, ...]]] = None,
-    fill: Union[int, float, Tuple[int, ...]] = 0
-)
-```
-
-### [paddle.vision.transforms.RandomRotation](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/RandomRotation_cn.html)
-```python
-paddle.vision.transforms.RandomRotation(
-    degrees: Union[int, List[float], Tuple[float, ...]],
-    interpolation: Union[str, int] = 'nearest',
-    expand: bool = False,
-    center: Optional[Tuple[int, int]] = None,
-    fill: int = 0,
-    keys: Optional[Union[List[str], Tuple[str, ...]]] = None
-)
-```
-
-两者功能一致，但输入参数类型不一致。
-
-### 参数映射
-
-| torchvision | PaddlePaddle | 备注                                                         |
-| ------------------- | ------------------ | ----------------------------------------------- |
-| degrees               | degrees           | 旋转角度范围。                   |
-| interpolation         | interpolation     | 插值的方法，两者类型不一致，PyTorch 为 InterpolationMode 枚举类, Paddle 为 int 或 string，需要转写。 |
-| expand                | expand            | 是否扩展图像尺寸。                    |
-| center                | center            | 旋转的中心点坐标。             |
-| fill                  | fill              | 对图像扩展时填充的值。               |
-| -                     | keys              | 输入的类型，PyTorch 无此参数，Paddle 保持默认即可。     |
-
-### 转写示例
-#### interpolation：插值的方法
-```python
-# PyTorch 写法
-transform = torchvision.transforms.RandomRotation(degrees=45, interpolation=torchvision.transforms.InterpolationMode.BILINEAR, expand=True, center=(100, 100), fill=(255, 0, 0))
-rotated_img = transform(img)
-
-# Paddle 写法
-transform = paddle.vision.transforms.RandomRotation(degrees=45, interpolation='bilinear', expand=True, center=(100, 100), fill=(255, 0, 0))
-rotated_img = transform(img)
-```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/input_args_type_diff/torchvision.transforms.functional.affine.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/input_args_type_diff/torchvision.transforms.functional.affine.md
deleted file mode 100644
index 54764e9ab5a..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/input_args_type_diff/torchvision.transforms.functional.affine.md
+++ /dev/null
@@ -1,51 +0,0 @@
-## [ 输入参数类型不一致 ]torchvision.transforms.functional.affine
-### [torchvision.transforms.functional.affine](https://pytorch.org/vision/main/generated/torchvision.transforms.functional.affine.html)
-```python
-torchvision.transforms.functional.affine(img: Tensor,
-                                        angle: float,
-                                        translate: List[int],
-                                        scale: float,
-                                        shear: List[float],
-                                        interpolation: InterpolationMode = InterpolationMode.NEAREST,
-                                        fill: Optional[List[float]] = None,
-                                        center: Optional[List[int]] = None)
-```
-
-### [paddle.vision.transforms.affine](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/affine_cn.html)
-```python
-paddle.vision.transforms.affine(
-    img: Union[PIL.Image.Image, np.ndarray, paddle.Tensor],
-    angle: Union[float, int],
-    translate: List[float],
-    scale: float,
-    shear: Union[List[float], Tuple[float, ...]],
-    interpolation: Union[str, int] = 'nearest',
-    fill: Union[int, List[int], Tuple[int, ...]] = 0,
-    center: Optional[Tuple[int, int]] = None
-)
-```
-
-两者功能一致，但输入参数类型不一致，具体如下：
-
-### 参数映射
-
-| torchvision | PaddlePaddle | 备注                                                         |
-| ----------- | ------------ | ------------------------------------------------------------ |
-| img               | img           | 输入图片。 |
-| angle             | angle         | 旋转角度。 |
-| translate         | translate     | 随机水平平移和垂直平移变化的位移大小。       |
-| scale             | scale         | 控制缩放比例。                             |
-| shear             | shear         | 剪切角度值。   |
-| interpolation     | interpolation | 插值的方法，两者类型不一致，PyTorch 为 InterpolationMode 枚举类, Paddle 为 int 或 string，需要转写。         |
-| fill              | fill          | 对图像扩展时填充的像素值。    |
-| center            | center        | 仿射变换的中心点坐标 。    |
-
-### 转写示例
-#### interpolation：插值的方法
-```python
-# PyTorch 写法
-rotated_img = torchvision.transforms.functional.affine(img, angle=30.0, translate=[10, 20], scale=1.2, shear=[10.0, 5.0], interpolation=torchvision.transforms.InterpolationMode.BILINEAR, fill=[0, 0, 0], center=[100, 100])
-
-# Paddle 写法
-rotated_img = paddle.vision.transforms.affine(img=img, angle=30.0, translate=[10, 20], scale=1.2, shear=[10.0, 5.0], interpolation='bilinear', fill=[0, 0, 0], center=[100, 100])
-```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/input_args_type_diff/torchvision.transforms.functional.perspective.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/input_args_type_diff/torchvision.transforms.functional.perspective.md
deleted file mode 100644
index 086695af1b1..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/input_args_type_diff/torchvision.transforms.functional.perspective.md
+++ /dev/null
@@ -1,45 +0,0 @@
-## [ 输入参数类型不一致 ]torchvision.transforms.functional.perspective
-### [torchvision.transforms.functional.perspective](https://pytorch.org/vision/main/generated/torchvision.transforms.functional.perspective.html#perspective)
-```python
-torchvision.transforms.functional.perspective(
-    img: Tensor,
-    startpoints: List[List[int]],
-    endpoints: List[List[int]],
-    interpolation: InterpolationMode = InterpolationMode.BILINEAR,
-    fill: Optional[List[float]] = None
-)
-```
-
-### [paddle.vision.transforms.perspective](https://www.paddlepaddle.org.cn/documentation/docs/zh/api/paddle/vision/transforms/perspective_cn.html#cn-api-paddle-vision-transforms-perspective)
-```python
-paddle.vision.transforms.perspective(
-    img: Union[PIL.Image.Image, np.ndarray, paddle.Tensor],
-    startpoints: List[List[float]],
-    endpoints: List[List[float]],
-    interpolation: Union[str, int] = 'nearest',
-    fill: Union[int, List[int], Tuple[int, ...]] = 0
-)
-```
-
-两者功能一致，但参数类型不一致。
-
-### 参数映射
-
-| torchvision       | PaddlePaddle | 备注              |
-| ----------------- | ----------------- | ------------ |
-| img               | img               | 输入图片。    |
-| startpoints       | startpoints       | 在原图上的四个角（左上、右上、右下、左下）的坐标。      |
-| endpoints         | endpoints         | 在原图上的四个角（左上、右上、右下、左下）的坐标。      |
-| interpolation     | interpolation     | 插值的方法，两者类型不一致，PyTorch 为 InterpolationMode 枚举类, Paddle 为 int 或 string，需要转写。    |
-| fill              | fill              | 对图像扩展时填充的像素值。             |
-
-
-### 转写示例
-#### interpolation：插值的方法
-```python
-# PyTorch 写法
-processed_img = torchvision.transforms.functional.perspective(img, startpoints, endpoints, interpolation=torchvision.transforms.InterpolationMode.BILINEAR, fill=[0, 0, 0])
-
-# Paddle 写法
-processed_img = paddle.vision.transforms.perspective(img=img, startpoints=startpoints, endpoints=endpoints, interpolation='bilinear', fill=[0, 0, 0])
-```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/input_args_type_diff/torchvision.transform.functional.resize.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/input_args_type_diff/torchvision.transforms.functional.resize.md
similarity index 100%
rename from docs/guides/model_convert/convert_from_pytorch/api_difference/input_args_type_diff/torchvision.transform.functional.resize.md
rename to docs/guides/model_convert/convert_from_pytorch/api_difference/input_args_type_diff/torchvision.transforms.functional.resize.md
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/input_args_type_diff/torchvision.transforms.functional.rotate.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/input_args_type_diff/torchvision.transforms.functional.rotate.md
deleted file mode 100644
index 63af0e66d10..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/input_args_type_diff/torchvision.transforms.functional.rotate.md
+++ /dev/null
@@ -1,34 +0,0 @@
-## [ 输入参数类型不一致 ]torchvision.transforms.functional.rotate
-### [torchvision.transforms.functional.rotate](https://pytorch.org/vision/stable/generated/torchvision.transforms.functional.rotate.html)
-```python
-torchvision.transforms.functional.rotate(img: Tensor, angle: float, interpolation: InterpolationMode = InterpolationMode.NEAREST, expand: bool = False, center: Optional[List[int]] = None, fill: Optional[List[float]] = None)
-```
-
-### [paddle.vision.transforms.rotate](https://www.paddlepaddle.org.cn/documentation/docs/zh/api/paddle/vision/transforms/rotate_cn.html#cn-api-paddle-vision-transforms-rotate)
-```python
-paddle.vision.transforms.rotate(img, angle, interpolation='nearest', expand=False, center=None, fill=0)
-```
-
-两者功能一致，但输入参数类型不一致。
-
-### 参数映射
-
-| torchvision                           | PaddlePaddle       | 备注      |
-| ------------------------------------- | ------------------ | -------- |
-| img                                   | img                | 输入图片。|
-| angle                                 | angle              | 旋转角度。|
-| interpolation                         | interpolation      | 插值的方法，两者类型不一致，PyTorch 为 InterpolationMode 枚举类, Paddle 为 int 或 string，需要转写。         |
-| expand                                | expand             | 是否要对旋转后的图片进行大小扩展。|
-| center                                | center             | 旋转中心。|
-| fill                                  | fill               | 旋转图像外部区域的 RGB 像素填充值。|
-
-
-### 转写示例
-#### interpolation：插值的方法
-```python
-# PyTorch 写法
-torchvision.transforms.functional.rotate(img, angle=90, interpolation=torchvision.transforms.InterpolationMode.BILINEAR)
-
-# Paddle 写法
-paddle.vision.transforms.rotate(img=img, angle=90, interpolation='bilinear')
-```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/input_args_usage_diff/torch.cuda.Stream__upper.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/input_args_usage_diff/torch.cuda.Stream.md
similarity index 100%
rename from docs/guides/model_convert/convert_from_pytorch/api_difference/input_args_usage_diff/torch.cuda.Stream__upper.md
rename to docs/guides/model_convert/convert_from_pytorch/api_difference/input_args_usage_diff/torch.cuda.Stream.md
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/input_args_usage_diff/torch.rand.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/input_args_usage_diff/torch.rand.md
deleted file mode 100644
index f5a85a60955..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/input_args_usage_diff/torch.rand.md
+++ /dev/null
@@ -1,83 +0,0 @@
-## [ 输入参数用法不一致 ]torch.rand
-### [torch.rand](https://pytorch.org/docs/stable/generated/torch.rand.html?highlight=rand#torch.rand)
-```python
-torch.rand(*size,
-           *,
-           generator=None,
-           out=None,
-           dtype=None,
-           layout=torch.strided,
-           device=None,
-           requires_grad=False,
-           pin_memory=False)
-```
-
-### [paddle.rand](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/rand_cn.html#rand)
-```python
-paddle.rand(shape,
-            dtype=None,
-            name=None)
-```
-
-其中 torch 的 `size` 和 paddle 的 `shape` 用法不一致，torch 还支持更多其他参数，具体如下：
-### 参数映射
-
-| PyTorch       | PaddlePaddle | 备注                                                   |
-| ------------- | ------------ | ------------------------------------------------------ |
-| *size         | shape        | 表示输出形状大小，PyTorch 以可变参数方式传入，Paddle 以 list 或 tuple 的方式传入。                                     |
-| generator     | -      | 用于采样的伪随机数生成器， Paddle 无此参数，一般对网络训练结果影响不大，可直接删除。 |
-| out           | -            | 表示输出的 Tensor，Paddle 无此参数。               |
-| dtype           | dtype            | 表示数据类型。               |
-| layout        | -            | 表示布局方式，Paddle 无此参数，一般对网络训练结果影响不大，可直接删除。                   |
-| device        | -            | 表示 Tensor 存放位置，Paddle 无此参数，需要转写。                   |
-| requires_grad | -            | 表示是否不阻断梯度传导，Paddle 无此参数，需要转写。 |
-| pin_memory    | -            | 表示是否使用锁页内存， Paddle 无此参数，需要转写。       |
-
-
-### 转写示例
-#### *size：输出形状大小
-```python
-# PyTorch 写法
-torch.rand(3, 5)
-
-# Paddle 写法
-paddle.rand([3, 5])
-```
-
-#### out：指定输出
-```python
-# PyTorch 写法
-torch.rand([3, 5], out=y)
-
-# Paddle 写法
-paddle.assign(paddle.rand([3, 5]), y)
-```
-
-#### device: Tensor 的设备
-```python
-# PyTorch 写法
-torch.rand(3, 5, device=torch.device('cpu'))
-
-# Paddle 写法
-y = paddle.rand([3, 5])
-y.cpu()
-```
-
-#### requires_grad：是否需要求反向梯度，需要修改该 Tensor 的 stop_gradient 属性
-```python
-# PyTorch 写法
-x = torch.rand([3, 5], requires_grad=True)
-
-# Paddle 写法
-x = paddle.rand([3, 5])
-x.stop_gradient = False
-```
-
-#### pin_memory：是否分配到固定内存上
-```python
-# PyTorch 写法
-torch.rand(3, 5, pin_memory=True)
-
-# Paddle 写法
-paddle.rand([3, 5]).pin_memory()
-```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/input_args_usage_diff/torch.split.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/input_args_usage_diff/torch.split.md
deleted file mode 100644
index a757f119d4c..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/input_args_usage_diff/torch.split.md
+++ /dev/null
@@ -1,38 +0,0 @@
-## [ 输入参数用法不一致 ]torch.split
-### [torch.split](https://pytorch.org/docs/stable/generated/torch.split.html?highlight=torch%20split#torch.split)
-```python
-torch.split(tensor,
-            split_size_or_sections,
-            dim=0)
-```
-
-### [paddle.split](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/split_cn.html#split)
-```python
-paddle.split(x,
-             num_or_sections,
-             axis=0,
-             name=None)
-```
-
-其中 PyTorch 的 `split_size_or_sections` 与 Paddle 的 `num_or_sections` 用法不一致，具体如下：
-### 参数映射
-
-| PyTorch       | PaddlePaddle | 备注                                                   |
-| ------------- | ------------ | ------------------------------------------------------ |
-| tensor        | x            | 表示输入 Tensor ，仅参数名不一致。                                     |
-| split_size_or_sections | num_or_sections | 当类型为 int 时，torch 表示单个块大小，paddle 表示结果有多少个块，需要转写。 |
-| dim           | axis         | 表示需要分割的维度，仅参数名不一致。                   |
-
-
-### 转写示例
-#### split_size_or_sections：单个块大小
-```python
-split_size = 2
-dim = 1
-# PyTorch 写法
-torch.split(a, split_size, dim)
-# 在输入 dim 时，返回 (values, indices)
-
-# Paddle 写法
-paddle.split(a, a.shape[dims]/split_size, dim)
-```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/fairscale.nn.model_parallel.initialize.get_model_parallel_rank.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/fairscale.nn.model_parallel.initialize.get_model_parallel_rank.md
deleted file mode 100644
index a4e7e1a9d81..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/fairscale.nn.model_parallel.initialize.get_model_parallel_rank.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]fairscale.nn.model_parallel.initialize.get_model_parallel_rank
-### [fairscale.nn.model_parallel.initialize.get_model_parallel_rank](https://github.com/facebookresearch/fairscale/blob/164cc0f3170b4a3951dd84dda29c3e1504ac4d6e/fairscale/nn/model_parallel/initialize.py#L155)
-```python
-fairscale.nn.model_parallel.initialize.get_model_parallel_rank()
-```
-
-### [paddle.distributed.fleet.base.topology._HYBRID_PARALLEL_GROUP.get_model_parallel_rank](https://github.com/PaddlePaddle/Paddle/blob/ddac1b431483ddc0f1ee600e799aa31fc0a75961/python/paddle/distributed/fleet/base/topology.py#L463)
-```python
-paddle.distributed.fleet.base.topology._HYBRID_PARALLEL_GROUP.get_model_parallel_rank()
-```
-
-两者功能一致，均无参数。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/fairscale.nn.model_parallel.initialize.get_model_parallel_world_size.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/fairscale.nn.model_parallel.initialize.get_model_parallel_world_size.md
deleted file mode 100644
index f7e77ed3b12..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/fairscale.nn.model_parallel.initialize.get_model_parallel_world_size.md
+++ /dev/null
@@ -1,11 +0,0 @@
-## [ 仅 API 调用方式不一致 ]fairscale.nn.model_parallel.initialize.get_model_parallel_world_size
-### [fairscale.nn.model_parallel.initialize.get_model_parallel_world_size](https://github.com/facebookresearch/fairscale/blob/164cc0f3170b4a3951dd84dda29c3e1504ac4d6e/fairscale/nn/model_parallel/initialize.py#L150)
-```python
-fairscale.nn.model_parallel.initialize.get_model_parallel_world_size()
-```
-
-### [paddle.distributed.fleet.base.topology._HYBRID_PARALLEL_GROUP._mp_degree](https://github.com/PaddlePaddle/Paddle/blob/ddac1b431483ddc0f1ee600e799aa31fc0a75961/python/paddle/distributed/fleet/base/topology.py#L185)
-```python
-paddle.distributed.fleet.base.topology._HYBRID_PARALLEL_GROUP._mp_degree
-```
-两者功能一致，均无参数。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/flash_attn.__version__.split.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/flash_attn.__version__.split.md
deleted file mode 100644
index 4864b6a4514..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/flash_attn.__version__.split.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]flash_attn._\_version__.split
-### [flash_attn._\_version__.split](https://github.com/Dao-AILab/flash-attention/blob/72e27c6320555a37a83338178caa25a388e46121/flash_attn/__init__.py)
-```python
-flash_attn.__version__.split(sep=None, maxsplit=-1)
-```
-
-### [paddle._\_version__.split](https://github.com/PaddlePaddle/Paddle/tree/develop)
-```python
-paddle.__version__.split(sep=None, maxsplit=-1)
-```
-
-两者功能一致，参数完全一致，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.clamp_.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.clamp_.md
deleted file mode 100644
index d0194099d89..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.clamp_.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.Tensor.clamp_
-### [torch.Tensor.clamp_](https://pytorch.org/docs/stable/generated/torch.Tensor.clamp_.html?highlight=clamp_#torch.Tensor.clamp_)
-```python
-torch.Tensor.clamp_(min=None, max=None)
-```
-
-### [paddle.Tensor.clip_](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor_cn.html#id6)
-```python
-paddle.Tensor.clip_(min=None, max=None, name=None)
-```
-
-两者功能一致，参数完全一致，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.col_indices.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.col_indices.md
deleted file mode 100644
index 18d95da9805..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.col_indices.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.Tensor.col_indices
-### [torch.Tensor.col_indices](https://pytorch.org/docs/stable/generated/torch.Tensor.col_indices.html)
-```python
-torch.Tensor.col_indices()
-```
-
-### [paddle.Tensor.cols]()
-```python
-paddle.Tensor.cols()
-```
-
-两者功能一致，无参数。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.conj_physical.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.conj_physical.md
deleted file mode 100644
index 0012606562e..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.conj_physical.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.Tensor.conj_physical
-### [torch.Tensor.conj_physical](https://pytorch.org/docs/stable/generated/torch.Tensor.conj_physical.html#torch.Tensor.conj_physical)
-```python
-torch.Tensor.conj_physical()
-```
-
-### [paddle.Tensor.conj](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor_cn.html#conj-name-none)
-```python
-paddle.Tensor.conj(name=None)
-```
-
-两者功能一致，无参数。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.crow_indices.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.crow_indices.md
deleted file mode 100644
index 8fae880836d..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.crow_indices.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.Tensor.crow_indices
-### [torch.Tensor.crow_indices](https://pytorch.org/docs/stable/generated/torch.Tensor.crow_indices.html)
-```python
-torch.Tensor.crow_indices()
-```
-
-### [paddle.Tensor.crows]()
-```python
-paddle.Tensor.crows()
-```
-
-两者功能一致，无参数。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.det.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.det.md
deleted file mode 100644
index af2ea21c9f7..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.det.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.Tensor.det
-### [torch.Tensor.det](https://pytorch.org/docs/stable/generated/torch.Tensor.det.html?highlight=det#torch.Tensor.det)
-```python
-torch.Tensor.det()
-```
-
-### [paddle.linalg.det](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/linalg/det_cn.html#det)
-```python
-paddle.linalg.det(x, name=None)
-```
-
-Pytorch 为 Tensor 类方法，PaddlePaddle 为普通函数，将调用 torch.Tensor 类方法的 self Tensor 传入到 Paddle 接口中即可。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.device.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.device.md
deleted file mode 100644
index 0d6a778b9c9..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.device.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.Tensor.device
-### [torch.Tensor.device](https://pytorch.org/docs/stable/generated/torch.Tensor.device.html)
-```python
-torch.Tensor.device
-```
-
-### [paddle.Tensor.place](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor_cn.html#place)
-```python
-paddle.Tensor.place
-```
-
-两者功能一致，均无参数，都用来查看一个 Tensor 的设备位置。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.erf_.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.erf_.md
deleted file mode 100644
index 2522212c24f..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.erf_.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.Tensor.erf_
-### [torch.Tensor.erf_](https://pytorch.org/docs/stable/generated/torch.Tensor.erf_.html)
-```python
-torch.Tensor.erf_()
-```
-
-### [paddle.erf_]()
-```python
-paddle.erf_(x)
-```
-
-两者功能一致，无参数。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.expm1_.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.expm1_.md
deleted file mode 100644
index bbb1b16a69b..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.expm1_.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.Tensor.expm1_
-### [torch.Tensor.expm1_](https://pytorch.org/docs/stable/generated/torch.Tensor.expm1_.html)
-```python
-torch.Tensor.expm1_()
-```
-
-### [paddle.expm1_]()
-```python
-paddle.expm1_(x)
-```
-
-两者功能一致，无参数。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.fix.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.fix.md
deleted file mode 100644
index 8467e925391..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.fix.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.Tensor.fix
-### [torch.Tensor.fix](https://pytorch.org/docs/stable/generated/torch.Tensor.fix.html?highlight=fix#torch.Tensor.fix)
-```python
-torch.Tensor.fix()
-```
-
-### [paddle.Tensor.trunc](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor_cn.html#trunc-name-none)
-```python
-paddle.Tensor.trunc(name=None)
-```
-
-两者功能一致，无参数。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.fix_.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.fix_.md
deleted file mode 100644
index 319329edbf7..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.fix_.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.Tensor.fix_
-### [torch.Tensor.fix_](https://pytorch.org/docs/stable/generated/torch.Tensor.fix_.html)
-```python
-torch.Tensor.fix_()
-```
-
-### [paddle.Tensor.trunc_]()
-```python
-paddle.Tensor.trunc_()
-```
-
-两者功能一致，均无参数。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.imag.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.imag.md
deleted file mode 100644
index 4f2715a5bca..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.imag.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.Tensor.imag
-### [torch.Tensor.imag](https://pytorch.org/docs/stable/generated/torch.Tensor.imag.html)
-```python
-torch.Tensor.imag
-```
-
-### [paddle.Tensor.imag](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor_cn.html#imag-name-none)
-```python
-paddle.Tensor.imag
-```
-
-两者功能一致，均无参数，用于返回原复数 Tensor 的虚部数值。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.is_inference.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.is_inference.md
deleted file mode 100644
index ff578646bfd..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.is_inference.md
+++ /dev/null
@@ -1,21 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.Tensor.is_inference
-### [torch.Tensor.is_inference](https://pytorch.org/docs/stable/generated/torch.Tensor.is_inference.html)
-```python
-torch.Tensor.is_inference()
-```
-
-### [paddle.Tensor.stop_gradient]()
-```python
-paddle.Tensor.stop_gradient
-```
-
-两者功能一致，无参数。 `is_inference` 会强制关闭梯度记录。并且不能在中途设置梯度，而 `stop_gradient` 仅为停止计算该算子梯度，可在中途重新设为 `True` ，`Paddle` 为近似实现。
-
-### 转写示例
-```python
-# PyTorch 写法
-x.is_inference()
-
-# Paddle 写法
-x.stop_gradient
-```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.is_sparse.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.is_sparse.md
deleted file mode 100644
index 344fa5dc258..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.is_sparse.md
+++ /dev/null
@@ -1,23 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.Tensor.is_sparse
-### [torch.Tensor.is_sparse](https://pytorch.org/docs/stable/generated/torch.Tensor.is_sparse.html)
-```python
-torch.Tensor.is_sparse
-```
-
-### [paddle.Tensor.is_sparse](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor_cn.html)
-```python
-paddle.Tensor.is_sparse()
-```
-
-两者功能一致，但使用方式不一致，前者可以直接访问属性，后者需要调用方法，具体如下：
-
-### 转写示例
-```python
-# torch 版本可以直接访问属性
-# x = torch.rand(3)
-# print(x.is_sparse)
-
-# Paddle 版本需要调用
-x = paddle.rand([3])
-print(x.is_sparse())
-```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.is_sparse_csr.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.is_sparse_csr.md
deleted file mode 100644
index a621b5ab2c9..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.is_sparse_csr.md
+++ /dev/null
@@ -1,21 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.Tensor.is_sparse_csr
-### [torch.Tensor.is_sparse_csr](https://pytorch.org/docs/stable/generated/torch.Tensor.is_sparse_csr.html)
-```python
-torch.Tensor.is_sparse_csr
-```
-
-### [paddle.Tensor.is_sparse_csr](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor_cn.html)
-```python
-paddle.Tensor.is_sparse_csr()
-```
-
-两者功能一致，但使用方式不一致，前者可以直接访问属性，后者需要调用方法，具体如下：
-
-### 转写示例
-```python
-# torch 版本可以直接访问属性
-x.is_sparse_csr
-
-# Paddle 版本需要调用
-x.is_sparse_csr()
-```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.movedim.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.movedim.md
deleted file mode 100644
index a2273b00a4d..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.movedim.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.Tensor.movedim
-### [torch.Tensor.movedim](https://pytorch.org/docs/stable/generated/torch.Tensor.movedim.html)
-```python
-torch.Tensor.movedim(source, destination)
-```
-
-### [paddle.Tensor.moveaxis](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/moveaxis_cn.html)
-```python
-paddle.Tensor.moveaxis(source, destination, name = None)
-```
-
-两者功能一致且参数用法一致，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.mvlgamma.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.mvlgamma.md
deleted file mode 100644
index 16785a43b35..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.mvlgamma.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.Tensor.mvlgamma
-### [torch.Tensor.mvlgamma](https://pytorch.org/docs/stable/generated/torch.Tensor.mvlgamma.html#torch-tensor-mvlgamma)
-```python
-torch.Tensor.mvlgamma(p)
-```
-
-### [paddle.Tensor.multigammaln](https://github.com/PaddlePaddle/Paddle/blob/be090bd0bc9ac7a8595296c316b3a6ed3dc60ba6/python/paddle/tensor/math.py#L5099)
-```python
-paddle.Tensor.multigammaln(p, name=None)
-```
-
-两者功能一致，参数完全一致，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.mvlgamma_.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.mvlgamma_.md
deleted file mode 100644
index 420cb3624c6..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.mvlgamma_.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.Tensor.mvlgamma_
-### [torch.Tensor.mvlgamma_](https://pytorch.org/docs/stable/generated/torch.Tensor.mvlgamma_.html#torch-tensor-mvlgamma)
-```python
-torch.Tensor.mvlgamma_(p)
-```
-
-### [paddle.Tensor.multigammaln_](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/multigammaln__cn.html#multigammaln)
-```python
-paddle.Tensor.multigammaln_(p, name=None)
-```
-
-两者功能一致，参数完全一致，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.negative.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.negative.md
deleted file mode 100644
index 7b70d7a3760..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.negative.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.Tensor.negative
-### [torch.Tensor.negative](https://pytorch.org/docs/stable/generated/torch.negative.html#torch.negative)
-```python
-torch.Tensor.negative()
-```
-
-### [paddle.Tensor.neg](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/neg_cn.html#cn-api-paddle-neg)
-```python
-paddle.Tensor.neg()
-```
-
-两者功能一致，均无参数，用于计算输入 x 的相反数并返回。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.negative_.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.negative_.md
deleted file mode 100644
index c294b75b952..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.negative_.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.Tensor.negative_
-### [torch.Tensor.negative_](https://pytorch.org/docs/stable/generated/torch.Tensor.negative_.html)
-```python
-torch.Tensor.negative_()
-```
-
-### [paddle.Tensor.neg_]()
-```python
-paddle.Tensor.neg_()
-```
-
-两者功能一致，无参数。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.nelement.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.nelement.md
deleted file mode 100644
index 5525ed9db9f..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.nelement.md
+++ /dev/null
@@ -1,14 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.Tensor.nelement
-### [torch.Tensor.nelement](https://pytorch.org/docs/stable/generated/torch.Tensor.nelement.html?highlight=nelement#torch.Tensor.nelement)
-```python
-torch.Tensor.nelement()
-```
-
-### [paddle.Tensor.size](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/fluid/layers/size_cn.html#cn-api-fluid-layers-size)
-```python
-paddle.Tensor.size()
-```
-
-
-
-两者功能一致，均无参数，用于返回张量的单元数量，是一个 int 型的整数。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.numel.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.numel.md
deleted file mode 100644
index 59e977371d9..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.numel.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.Tensor.numel
-### [torch.Tensor.numel](https://pytorch.org/docs/stable/generated/torch.numel.html?highlight=numel#torch.numel)
-```python
-torch.Tensor.numel()
-```
-
-### [paddle.Tensor.size](https://www.paddlepaddle.org.cn/documentation/docs/guides/beginner/tensor_cn.html#tensor-shape)
-```python
-paddle.Tensor.size
-```
-
-两者功能一致，均无参数，用于返回张量的单元数量，是一个 int 型的整数。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.positive.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.positive.md
deleted file mode 100644
index 1ca198147d5..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.positive.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.Tensor.positive
-### [torch.Tensor.positive](https://pytorch.org/docs/stable/generated/torch.Tensor.positive.html#torch.Tensor.positive)
-```python
-torch.Tensor.positive()
-```
-
-### [paddle.positive](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/positive_cn.html#positive)
-```python
-paddle.positive(x)
-```
-
-Pytorch 为 Tensor 类方法，Paddle 为普通函数，将调用 torch.Tensor 类方法的 self Tensor 传入到 Paddle 接口中即可。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.real.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.real.md
deleted file mode 100644
index 312bd67fe7a..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.real.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.Tensor.real
-### [torch.Tensor.real](https://pytorch.org/docs/stable/generated/torch.Tensor.real.html)
-```python
-torch.Tensor.real
-```
-
-### [paddle.Tensor.real](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor_cn.html#real-name-none)
-```python
-paddle.Tensor.real
-```
-
-两者功能一致，均无参数，用于返回 Tensor 的实部数值。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.retain_grad.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.retain_grad.md
deleted file mode 100644
index 0a003bcc91f..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.retain_grad.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.Tensor.retain_grad
-### [torch.Tensor.retain_grad](https://pytorch.org/docs/stable/generated/torch.Tensor.retain_grad.html)
-```python
-torch.Tensor.retain_grad()
-```
-
-### [paddle.Tensor.retain_grads](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Overview_cn.html#paddle)
-```python
-paddle.Tensor.retain_grads()
-```
-
-两者功能一致，无参数。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.sparse_mask.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.sparse_mask.md
deleted file mode 100644
index 8f7814e550d..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.sparse_mask.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.Tensor.sparse_mask
-### [torch.Tensor.sparse_mask](https://pytorch.org/docs/stable/generated/torch.Tensor.sparse_mask.html)
-```python
-torch.Tensor.sparse_mask(mask)
-```
-
-### [paddle.sparse.mask_as](https://www.paddlepaddle.org.cn/documentation/docs/zh/api/paddle/sparse/mask_as_cn.html)
-```python
-paddle.sparse.mask_as(x, mask, name=None)
-```
-
-两者功能一致，但调用方式不同，torch 通过 Tensor 类方法调用，而 paddle 是直接调用函数，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.square_.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.square_.md
deleted file mode 100644
index 857e6b30c80..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.square_.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.Tensor.square_
-### [torch.Tensor.square_](https://pytorch.org/docs/stable/generated/torch.Tensor.square_.html)
-```python
-torch.Tensor.square_()
-```
-
-### [paddle.square_]()
-```python
-paddle.square_(x)
-```
-
-两者功能一致，无参数。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.to_sparse.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.to_sparse.md
deleted file mode 100644
index 970d2a6c512..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.to_sparse.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.Tensor.to_sparse
-### [torch.Tensor.to_sparse](https://pytorch.org/docs/stable/generated/torch.Tensor.to_sparse.html#torch.Tensor.to_sparse)
-```python
-torch.Tensor.to_sparse(sparse_dim)
-```
-
-### [paddle.Tensor.to_sparse_coo]()
-```python
-paddle.Tensor.to_sparse_coo(sparse_dim)
-```
-
-两者功能一致，参数用法一致，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.autograd.Function.forward.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.autograd.Function.forward.md
deleted file mode 100644
index 504fb2b5c6e..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.autograd.Function.forward.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.autograd.Function.forward
-### [torch.autograd.Function.forward](https://pytorch.org/docs/stable/generated/torch.autograd.Function.forward.html#torch.autograd.Function.forward)
-```python
-torch.autograd.Function.forward(ctx, *args, **kwargs)
-```
-
-### [paddle.autograd.PyLayer.forward](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/autograd/PyLayer_cn.html#forward-ctx-args-kwargs)
-```python
-paddle.autograd.PyLayer.forward(ctx, *args, **kwargs)
-```
-
-两者功能一致，参数完全一致，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.autograd.enable_grad.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.autograd.enable_grad.md
deleted file mode 100644
index 5cb1fecbde5..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.autograd.enable_grad.md
+++ /dev/null
@@ -1,10 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.autograd.enable_grad
-### [torch.autograd.enable_grad](https://pytorch.org/docs/stable/generated/torch.enable_grad.html#enable-grad)
-```python
-torch.autograd.enable_grad()
-```
-
-### [paddle.enable_grad](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/enable_grad.html#enable-grad)
-```python
-paddle.enable_grad()
-```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.autograd.function.FunctionCtx.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.autograd.function.FunctionCtx.md
deleted file mode 100644
index 54f529aa4dd..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.autograd.function.FunctionCtx.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.autograd.function.FunctionCtx
-### [torch.autograd.function.FunctionCtx]()
-```python
-torch.autograd.function.FunctionCtx
-```
-
-### [paddle.autograd.PyLayerContext](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/autograd/PyLayerContext_cn.html#pylayercontext)
-```python
-paddle.autograd.PyLayerContext
-```
-
-两者功能一致，无参数。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.autograd.function.FunctionCtx.save_for_backward.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.autograd.function.FunctionCtx.save_for_backward.md
deleted file mode 100644
index 5a63180e878..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.autograd.function.FunctionCtx.save_for_backward.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.autograd.function.FunctionCtx.save_for_backward
-### [torch.autograd.function.FunctionCtx.save_for_backward](https://pytorch.org/docs/stable/generated/torch.autograd.function.FunctionCtx.save_for_backward.html#torch.autograd.function.FunctionCtx.save_for_backward)
-```python
-torch.autograd.function.FunctionCtx.save_for_backward(*tensors)
-```
-
-### [paddle.autograd.PyLayerContext.save_for_backward](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/autograd/PyLayerContext_cn.html#save-for-backward-tensors)
-```python
-paddle.autograd.PyLayerContext.save_for_backward(*tensors)
-```
-
-两者功能一致，参数完全一致，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.autograd.function.FunctionCtx.set_materialize_grads.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.autograd.function.FunctionCtx.set_materialize_grads.md
deleted file mode 100644
index ffd92e6cd48..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.autograd.function.FunctionCtx.set_materialize_grads.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.autograd.function.FunctionCtx.set_materialize_grads
-### [torch.autograd.function.FunctionCtx.set_materialize_grads](https://pytorch.org/docs/stable/generated/torch.autograd.function.FunctionCtx.set_materialize_grads.html#torch.autograd.function.FunctionCtx.set_materialize_grads)
-```python
-torch.autograd.function.FunctionCtx.set_materialize_grads(value)
-```
-
-### [paddle.autograd.PyLayerContext.set_materialize_grads](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/autograd/PyLayerContext_cn.html#set-materialize-grads-self-value)
-```python
-paddle.autograd.PyLayerContext.set_materialize_grads(value)
-```
-
-两者功能一致，参数完全一致，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.autograd.grad_mode.set_grad_enabled.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.autograd.grad_mode.set_grad_enabled.md
deleted file mode 100644
index f47abbdf0bf..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.autograd.grad_mode.set_grad_enabled.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.autograd.grad_mode.set_grad_enabled
-### [torch.autograd.grad_mode.set_grad_enabled](https://docs.pytorch.org/docs/stable/generated/torch.autograd.grad_mode.set_grad_enabled.html#torch.autograd.grad_mode.set_grad_enabled)
-```python
-torch.autograd.grad_mode.set_grad_enabled(mode)
-```
-
-### [paddle.set_grad_enabled](https://www.paddlepaddle.org.cn/documentation/docs/zh/api/paddle/set_grad_enabled_cn.html)
-```python
-paddle.set_grad_enabled(mode)
-```
-
-两者功能一致，参数完全一致，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.autograd.graph.saved_tensors_hooks.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.autograd.graph.saved_tensors_hooks.md
deleted file mode 100644
index ff6c4e522d9..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.autograd.graph.saved_tensors_hooks.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.autograd.graph.saved_tensors_hooks
-### [torch.autograd.graph.saved_tensors_hooks](https://pytorch.org/docs/stable/autograd.html?highlight=saved_tensors_hooks#torch.autograd.graph.saved_tensors_hooks)
-```python
-torch.autograd.graph.saved_tensors_hooks(pack_hook, unpack_hook)
-```
-
-### [paddle.autograd.saved_tensors_hooks](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/autograd/saved_tensors_hooks_cn.html)
-```python
-paddle.autograd.saved_tensors_hooks(pack_hook, unpack_hook)
-```
-
-两者功能一致，参数完全一致，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.backends.cuda.is_built.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.backends.cuda.is_built.md
deleted file mode 100644
index bcf05bb6a1b..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.backends.cuda.is_built.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.backends.cuda.is_built
-### [torch.backends.cuda.is_built](https://pytorch.org/docs/stable/backends.html?highlight=torch+backends+cudnn+is_available#torch.backends.cuda.is_built)
-```python
-torch.backends.cuda.is_built()
-```
-
-### [paddle.device.is_compiled_with_cuda](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/device/is_compiled_with_cuda_cn.html#is-compiled-with-cuda)
-```python
-paddle.device.is_compiled_with_cuda()
-```
-
-检测是否在 cuda 环境下编译安装包。无参数。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.backends.cudnn.version.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.backends.cudnn.version.md
deleted file mode 100644
index 2b9a38727cc..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.backends.cudnn.version.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.backends.cudnn.version
-### [torch.backends.cudnn.version](https://pytorch.org/docs/stable/generated/torch.backends.cudnn.version.html)
-```python
-torch.backends.cudnn.version()
-```
-
-### [paddle.device.get\_cudnn\_version](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/device/get_cudnn_version_cn.html#get-cudnn-version)
-```python
-paddle.device.get_cudnn_version()
-```
-
-两者功能一致，无参数。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.cda.StreamContext.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.cda.StreamContext.md
deleted file mode 100644
index c83df4e7edd..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.cda.StreamContext.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.cuda.StreamContext
-### [torch.cuda.StreamContext](https://pytorch.org/docs/stable/generated/torch.cuda.StreamContext.html#torch.cuda.StreamContext)
-```python
-torch.cuda.StreamContext(stream)
-```
-
-### [paddle.device.stream_guard](https://www.paddlepaddle.org.cn/documentation/docs/zh/api/paddle/device/stream_guard_cn.html#stream-guard)
-```python
-paddle.device.stream_guard(stream)
-```
-
-功能一致，参数完全一致，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.cpu.current_device.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.cpu.current_device.md
deleted file mode 100644
index e66413d08e0..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.cpu.current_device.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.cpu.current_device
-### [torch.cpu.current_device](https://pytorch.org/docs/stable/generated/torch.cpu.current_device.html)
-```python
-torch.cpu.current_device()
-```
-
-### [paddle.get_device](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/device/get_device_cn.html#get-device)
-```python
-paddle.get_device()
-```
-
-功能一致，无参数。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.cuda.get_device_name.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.cuda.get_device_name.md
deleted file mode 100644
index 02192c8d79d..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.cuda.get_device_name.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.cuda.get_device_name
-### [torch.cuda.get_device_name](https://pytorch.org/docs/stable/generated/torch.cuda.get_device_name.html)
-```python
-torch.cuda.get_device_name(device=None)
-```
-
-### [paddle.device.cuda.get_device_name](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/device/cuda/get_device_name_cn.html)
-```python
-paddle.device.cuda.get_device_name(device=None)
-```
-
-功能一致，参数完全一致，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.cuda.is_bf16_supported.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.cuda.is_bf16_supported.md
deleted file mode 100644
index ca2a674f51a..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.cuda.is_bf16_supported.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.cuda.is_bf16_supported
-### [torch.cuda.is_bf16_supported](https://pytorch.org/docs/stable/cuda.html)
-```python
-torch.cuda.is_bf16_supported()
-```
-
-### [paddle.amp.is_bfloat16_supported](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/amp/is_bfloat16_supported_cn.html#is-bfloat16-supported)
-```python
-paddle.amp.is_bfloat16_supported()
-```
-
-功能一致，无参数。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.cuda.max_memory_allocated.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.cuda.max_memory_allocated.md
deleted file mode 100644
index 8dd6856a6ee..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.cuda.max_memory_allocated.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.cuda.max_memory_allocated
-### [torch.cuda.max_memory_allocated](https://pytorch.org/docs/stable/generated/torch.cuda.max_memory_allocated.html#torch.cuda.max_memory_allocated)
-```python
-torch.cuda.max_memory_allocated(device)
-```
-
-### [paddle.device.cuda.max_memory_allocated](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/device/cuda/max_memory_allocated_cn.html)
-```python
-paddle.device.cuda.max_memory_allocated(device)
-```
-
-功能一致，参数完全一致（PyTorch 参数是 PaddlePaddle 参数子集），具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.cuda.max_memory_reserved.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.cuda.max_memory_reserved.md
deleted file mode 100644
index d428dcc16a1..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.cuda.max_memory_reserved.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.cuda.max_memory_reserved
-### [torch.cuda.max_memory_reserved](https://pytorch.org/docs/stable/generated/torch.cuda.max_memory_reserved.html#torch.cuda.max_memory_reserved)
-```python
-torch.cuda.max_memory_reserved(device)
-```
-
-### [paddle.device.cuda.max_memory_reserved](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/device/cuda/max_memory_reserved_cn.html)
-```python
-paddle.device.cuda.max_memory_reserved(device)
-```
-
-功能一致，参数完全一致（PyTorch 参数是 PaddlePaddle 参数子集），具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.cuda.nvtx.range_pop.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.cuda.nvtx.range_pop.md
deleted file mode 100644
index 51598ede266..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.cuda.nvtx.range_pop.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.cuda.nvtx.range_pop
-### [torch.cuda.nvtx.range_pop](https://pytorch.org/docs/stable/generated/torch.cuda.nvtx.range_pop.html#torch.cuda.nvtx.range_pop)
-```python
-torch.cuda.nvtx.range_pop()
-```
-
-### [paddle.framework.core.nvprof_nvtx_pop](https://github.com/PaddlePaddle/Paddle/blob/645dfb4040a15712cea9ccfed4dcb0655aeeb0ea/paddle/fluid/pybind/pybind.cc#L2468)
-```python
-paddle.framework.core.nvprof_nvtx_pop()
-```
-
-功能一致，无参数。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.cuda.reset_max_memory_allocated.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.cuda.reset_max_memory_allocated.md
deleted file mode 100644
index 1f49b45e0d6..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.cuda.reset_max_memory_allocated.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.cuda.reset_max_memory_allocated
-### [torch.cuda.reset_max_memory_allocated](https://pytorch.org/docs/stable/generated/torch.cuda.reset_max_memory_allocated.html#torch.cuda.reset_max_memory_allocated)
-```python
-torch.cuda.reset_max_memory_allocated(device)
-```
-
-### [paddle.device.cuda.reset_max_memory_allocated](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/device/cuda/reset_max_memory_allocated_cn.html)
-```python
-paddle.device.cuda.reset_max_memory_allocated(device)
-```
-
-功能不一致（Pytorch 通过调用 reset_peak_memory_stats 函数实现，重置所有 CUDA 内存分配器跟踪的峰值统计。PaddlePaddle 仅重置分配给 Tensor 的显存峰值统计），参数完全一致（PyTorch 参数是 PaddlePaddle 参数子集），具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.cuda.reset_max_memory_cached.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.cuda.reset_max_memory_cached.md
deleted file mode 100644
index 63c64aaf0fb..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.cuda.reset_max_memory_cached.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.cuda.reset_max_memory_cached
-### [torch.cuda.reset_max_memory_cached](https://docs.pytorch.org/docs/stable/generated/torch.cuda.reset_max_memory_cached.html#torch-cuda-reset-max-memory-cached)
-```python
-torch.cuda.reset_max_memory_cached(device)
-```
-
-### [paddle.device.cuda.reset_max_memory_reserved](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/device/cuda/reset_max_memory_reserved_cn.html)
-```python
-paddle.device.cuda.reset_max_memory_reserved(device)
-```
-
-功能不一致（Pytorch 目前已弃用该函数。类似函数通过调用 reset_peak_memory_stats 函数实现，重置所有 CUDA 内存分配器跟踪的峰值统计。PaddlePaddle 仅重置由 Allocator 管理的显存峰值统计），参数完全一致（PyTorch 参数是 PaddlePaddle 参数子集），具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.cuda.set_stream.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.cuda.set_stream.md
deleted file mode 100644
index fbc123a820d..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.cuda.set_stream.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.cuda.set_stream
-### [torch.cuda.set_stream](https://pytorch.org/docs/stable/generated/torch.cuda.set_stream.html#torch.cuda.set_stream)
-```python
-torch.cuda.set_stream(stream)
-```
-
-### [paddle.device.set_stream](https://www.paddlepaddle.org.cn/documentation/docs/zh/api/paddle/device/set_stream_cn.html#set-stream)
-```python
-paddle.device.set_stream(stream=None)
-```
-
-功能一致，参数完全一致，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.cuda.stream.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.cuda.stream.md
deleted file mode 100644
index e7c79abd0ad..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.cuda.stream.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.cuda.stream
-### [torch.cuda.stream](https://pytorch.org/docs/stable/generated/torch.cuda.stream.html)
-```python
-torch.cuda.stream(stream)
-```
-
-### [paddle.device.stream_guard](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/device/stream_guard_cn.html#stream-guard)
-```python
-paddle.device.stream_guard(stream)
-```
-
-功能一致，参数完全一致，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.distributed.ReduceOp.PRODUCT.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.distributed.ReduceOp.PRODUCT.md
deleted file mode 100644
index 50b1149ed5b..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.distributed.ReduceOp.PRODUCT.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.distributed.ReduceOp.PRODUCT
-### [torch.distributed.ReduceOp.PRODUCT](https://pytorch.org/docs/stable/distributed.html#torch.distributed.ReduceOp)
-```python
-torch.distributed.ReduceOp.PRODUCT
-```
-
-### [paddle.distributed.ReduceOp.PROD](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/distributed/ReduceOp_cn.html#reduceop)
-```python
-paddle.distributed.ReduceOp.PROD
-```
-
-两者功能一致，无参数。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.distributed.is_nccl_available.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.distributed.is_nccl_available.md
deleted file mode 100644
index 7f9cd0c9568..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.distributed.is_nccl_available.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.distributed.is_nccl_available
-### [torch.distributed.is_nccl_available](https://pytorch.org/docs/stable/distributed.html#torch.distributed.is_nccl_available)
-```python
-torch.distributed.is_nccl_available()
-```
-
-### [paddle.core.is_compiled_with_nccl](https://github.com/PaddlePaddle/Paddle/blob/61de6003525166856157b6220205fe53df638376/python/paddle/jit/sot/utils/paddle_api_config.py#L159)
-```python
-paddle.core.is_compiled_with_nccl()
-```
-
-两者功能一致，无参数。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.distributions.constraints.Constraint.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.distributions.constraints.Constraint.md
deleted file mode 100644
index 0619f720026..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.distributions.constraints.Constraint.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.distributions.constraints.Constraint
-### [torch.distributions.constraints.Constraint](https://pytorch.org/docs/stable/distributions.html#module-torch.distributions.constraints)
-```python
-torch.distributions.constraints.Constraint()
-```
-
-### [paddle.distribution.constraint.Constraint](https://github.com/PaddlePaddle/Paddle/blob/develop/python/paddle/distribution/constraint.py)
-```python
-paddle.distribution.constraint.Constraint()
-```
-
-两者功能一致，无参数，对象均使用 `check` 进行回调。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.distributions.distribution.Distribution.log_prob.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.distributions.distribution.Distribution.log_prob.md
deleted file mode 100644
index b963db968e0..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.distributions.distribution.Distribution.log_prob.md
+++ /dev/null
@@ -1,13 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.distributions.distribution.Distribution.log_prob
-### [torch.distributions.distribution.Distribution.log\_prob](https://pytorch.org/docs/stable/distributions.html#torch.distributions.distribution.Distribution.log_prob)
-```python
-torch.distributions.distribution.Distribution.log_prob(value)
-```
-
-### [paddle.distribution.Distribution.log\_prob](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/distribution/Distribution_cn.html#log-prob-value)
-```python
-paddle.distribution.Distribution.log_prob(value)
-```
-
-
-功能一致，参数完全一致，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.distributions.kl.kl_divergence.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.distributions.kl.kl_divergence.md
deleted file mode 100644
index d034adb8b25..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.distributions.kl.kl_divergence.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.distributions.kl.kl_divergence
-### [torch.distributions.kl.kl_divergence](https://pytorch.org/docs/stable/distributions.html?highlight=torch+distributions+kl+kl_divergence#torch.distributions.kl.kl_divergence)
-```python
-torch.distributions.kl.kl_divergence(p, q)
-```
-
-### [paddle.distribution.kl_divergence](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/distribution/kl_divergence_cn.html)
-```python
-paddle.distribution.kl_divergence(p, q)
-```
-
-功能一致，参数完全一致，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.is_inference.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.is_inference.md
deleted file mode 100644
index 62fb2d91143..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.is_inference.md
+++ /dev/null
@@ -1,21 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.is_inference
-### [torch.is_inference]()
-```python
-torch.is_inference(input)
-```
-
-### [paddle.Tensor.stop_gradient]()
-```python
-paddle.Tensor.stop_gradient
-```
-
-两者功能一致，无参数。 `is_inference` 会强制关闭梯度记录。并且不能在中途设置梯度，而 `stop_gradient` 仅为停止计算该算子梯度，可在中途重新设为 `True` ，`Paddle` 为近似实现。
-
-### 转写示例
-```python
-# PyTorch 写法
-torch.is_inference(x)
-
-# Paddle 写法
-x.stop_gradient
-```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.nn.AdaptiveAvgPool1d.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.nn.AdaptiveAvgPool1d.md
deleted file mode 100644
index c5e144950c6..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.nn.AdaptiveAvgPool1d.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.nn.AdaptiveAvgPool1d
-### [torch.nn.AdaptiveAvgPool1d](https://pytorch.org/docs/stable/generated/torch.nn.AdaptiveAvgPool1d.html)
-```python
-torch.nn.AdaptiveAvgPool1d(output_size)
-```
-
-### [paddle.nn.AdaptiveAvgPool1D](https://www.paddlepaddle.org.cn/documentation/docs/zh/api/paddle/nn/AdaptiveAvgPool1D_cn.html#adaptiveavgpool1d)
-```python
-paddle.nn.AdaptiveAvgPool1D(output_size, name=None)
-```
-
-两者功能一致，参数完全一致。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.nn.Module.apply.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.nn.Module.apply.md
deleted file mode 100644
index b80bea2f945..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.nn.Module.apply.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.nn.Module.apply
-### [torch.nn.Module.apply](https://pytorch.org/docs/stable/generated/torch.nn.Module.html?highlight=torch+nn+module+apply#torch.nn.Module.apply)
-```python
-torch.nn.Module.apply(fn)
-```
-
-### [paddle.nn.Layer.apply](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/nn/Layer_cn.html)
-```python
-paddle.nn.Layer.apply(fn)
-```
-
-两者功能一致，参数完全一致。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.nn.Module.children.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.nn.Module.children.md
deleted file mode 100644
index d77ca465257..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.nn.Module.children.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.nn.Module.children
-### [torch.nn.Module.children](https://pytorch.org/docs/stable/generated/torch.nn.Module.html#torch.nn.Module.children)
-```python
-torch.nn.Module.children()
-```
-
-### [paddle.nn.Layer.children](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/nn/Layer_cn.html#children)
-```python
-paddle.nn.Layer.children()
-```
-
-两者功能一致，无参数。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.nn.Module.eval.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.nn.Module.eval.md
deleted file mode 100644
index 696c615a036..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.nn.Module.eval.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.nn.Module.eval
-### [torch.nn.Module.eval](https://pytorch.org/docs/stable/generated/torch.nn.Module.html#torch.nn.Module.eval)
-```python
-torch.nn.Module.eval()
-```
-
-### [paddle.nn.Layer.eval](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/nn/Layer_cn.html#eval)
-```python
-paddle.nn.Layer.eval()
-```
-
-两者功能一致，无参数。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.nn.Module.named_children.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.nn.Module.named_children.md
deleted file mode 100644
index 1ca22ac10a4..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.nn.Module.named_children.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.nn.Module.named_children
-### [torch.nn.Module.named_children](https://pytorch.org/docs/stable/generated/torch.nn.Module.html#torch.nn.Module.named_children)
-```python
-torch.nn.Module.named_children()
-```
-
-### [paddle.nn.Layer.named_children](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/nn/Layer_cn.html#named-children)
-```python
-paddle.nn.Layer.named_children()
-```
-
-两者功能一致，无参数。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.nn.Module.train.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.nn.Module.train.md
deleted file mode 100644
index 8f7d7fd7965..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.nn.Module.train.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.nn.Module.train
-### [torch.nn.Module.train](https://pytorch.org/docs/stable/generated/torch.nn.Module.html#torch.nn.Module.train)
-```python
-torch.nn.Module.train()
-```
-
-### [paddle.nn.Layer.train](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/nn/Layer_cn.html#train)
-```python
-paddle.nn.Layer.train()
-```
-
-两者功能一致，无参数。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.optim.Optimizer.add_param_group.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.optim.Optimizer.add_param_group.md
deleted file mode 100644
index 79c3cf3fef6..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.optim.Optimizer.add_param_group.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.optim.Optimizer.add_param_group
-### [torch.optim.Optimizer.add_param_group](https://pytorch.org/docs/stable/generated/torch.optim.Optimizer.add_param_group.html?highlight=torch+optim+optimizer+add_param_group#torch.optim.Optimizer.add_param_group)
-```python
-torch.optim.Optimizer.add_param_group(param_group)
-```
-
-### [paddle.optimizer.Optimizer._add_param_group]()
-```python
-paddle.optimizer.Optimizer._add_param_group(param_group)
-```
-
-参数完全一致，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.optim.Optimizer.load_state_dict.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.optim.Optimizer.load_state_dict.md
deleted file mode 100644
index c7ef34004d5..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.optim.Optimizer.load_state_dict.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.optim.Optimizer.load_state_dict
-### [torch.optim.Optimizer.load_state_dict](https://pytorch.org/docs/stable/generated/torch.optim.Optimizer.load_state_dict.html#torch.optim.Optimizer.load_state_dict)
-```python
-torch.optim.Optimizer.load_state_dict(state_dict)
-```
-
-### [paddle.optimizer.Optimizer.load_state_dict](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/optimizer/Optimizer_cn.html)
-```python
-paddle.optimizer.Optimizer.load_state_dict(state_dict)
-```
-
-两者功能一致，参数完全一致。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.optim.Optimizer.state_dict.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.optim.Optimizer.state_dict.md
deleted file mode 100644
index 48bf3fcccad..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.optim.Optimizer.state_dict.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.optim.Optimizer.state_dict
-### [torch.optim.Optimizer.state_dict](https://pytorch.org/docs/stable/generated/torch.optim.Optimizer.state_dict.html?highlight=torch+optim+optimizer+state_dict#torch.optim.Optimizer.state_dict)
-```python
-torch.optim.Optimizer.state_dict()
-```
-
-### [paddle.optimizer.Optimizer.state_dict](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/optimizer/Optimizer_cn.html)
-```python
-paddle.optimizer.Optimizer.state_dict()
-```
-
-两者功能一致，均无参数。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.utils.data.ChainDataset.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.utils.data.ChainDataset.md
deleted file mode 100644
index d9af795d1aa..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.utils.data.ChainDataset.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.utils.data.ChainDataset
-### [torch.utils.data.ChainDataset](https://pytorch.org/docs/stable/data.html#torch.utils.data.ChainDataset)
-```python
-torch.utils.data.ChainDataset(datasets)
-```
-
-### [paddle.io.ChainDataset](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/io/ChainDataset_cn.html)
-```python
-paddle.io.ChainDataset(datasets)
-```
-
-paddle 参数和 torch 参数完全一致，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.utils.data.ConcatDataset.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.utils.data.ConcatDataset.md
deleted file mode 100644
index 128339e940c..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.utils.data.ConcatDataset.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.utils.data.ConcatDataset
-### [torch.utils.data.ConcatDataset](https://pytorch.org/docs/stable/data.html#torch.utils.data.ConcatDataset)
-```python
-torch.utils.data.ConcatDataset(datasets)
-```
-
-### [paddle.io.ConcatDataset](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/io/ConcatDataset_cn.html)
-```python
-paddle.io.ConcatDataset(datasets)
-```
-
-paddle 参数和 torch 参数完全一致，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.utils.data.Dataset.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.utils.data.Dataset.md
deleted file mode 100644
index 8de0920b70f..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.utils.data.Dataset.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.utils.data.Dataset
-### [torch.utils.data.Dataset](https://pytorch.org/docs/stable/data.html?highlight=torch%20utils%20data%20dataset#torch.utils.data.Dataset)
-```python
-torch.utils.data.Dataset()
-```
-
-### [paddle.io.Dataset](https://www.paddlepaddle.org.cn/documentation/docs/zh/api/paddle/io/Dataset_cn.html#dataset)
-```python
-paddle.io.Dataset()
-```
-
-功能一致，参数完全一致
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.utils.data.IterableDataset.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.utils.data.IterableDataset.md
deleted file mode 100644
index c25ee737715..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.utils.data.IterableDataset.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.utils.data.IterableDataset
-### [torch.utils.data.IterableDataset](https://pytorch.org/docs/stable/data.html#torch.utils.data.IterableDataset)
-```python
-torch.utils.data.IterableDataset()
-```
-
-### [paddle.io.IterableDataset](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/io/IterableDataset_cn.html#iterabledataset)
-```python
-paddle.io.IterableDataset()
-```
-
-无参数，二者都为可迭代数据集的基类。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.utils.data.Sampler.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.utils.data.Sampler.md
deleted file mode 100644
index 0a2031c2dbf..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.utils.data.Sampler.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.utils.data.Sampler
-### [torch.utils.data.Sampler](https://pytorch.org/docs/stable/data.html#torch.utils.data.Sampler)
-```python
-torch.utils.data.Sampler(data_source)
-```
-
-### [paddle.io.Sampler](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/io/Sampler_cn.html)
-```python
-paddle.io.Sampler(data_source)
-```
-
-paddle 参数和 torch 参数完全一致，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.utils.data.SequentialSampler.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.utils.data.SequentialSampler.md
deleted file mode 100644
index be273516023..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.utils.data.SequentialSampler.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.utils.data.SequentialSampler
-### [torch.utils.data.SequentialSampler](https://pytorch.org/docs/stable/generated/torch.utils.data.SequentialSampler.html)
-```python
-torch.utils.data.SequentialSampler(data_source)
-```
-
-### [paddle.io.SequenceSampler](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/io/SequenceSampler_cn.html#sequencesampler)
-```python
-paddle.io.SequenceSampler(data_source)
-```
-
-功能一致，参数完全一致，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.utils.data.Subset.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.utils.data.Subset.md
deleted file mode 100644
index 2d463d88f56..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.utils.data.Subset.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.utils.data.Subset
-### [torch.utils.data.Subset](https://pytorch.org/docs/stable/data.html#torch.utils.data.Subset)
-```python
-torch.utils.data.Subset(dataset, indices)
-```
-
-### [paddle.io.Subset](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/io/Subset_cn.html)
-```python
-paddle.io.Subset(dataset, indices)
-```
-
-paddle 参数和 torch 参数完全一致，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.utils.data.random_split.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.utils.data.random_split.md
deleted file mode 100644
index bf764184e26..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.utils.data.random_split.md
+++ /dev/null
@@ -1,16 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torch.utils.data.random_split
-### [torch.utils.data.random_split](https://pytorch.org/docs/stable/data.html?highlight=torch+utils+data+random_split#torch.utils.data.random_split)
-```python
-torch.utils.data.random_split(dataset,
-                            lengths,
-                            generator=<torch._C.Generator object>)
-```
-
-### [paddle.io.random_split](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/io/random_split_cn.html)
-```python
-paddle.io.random_split(dataset,
-                    lengths,
-                    generator=None)
-```
-
-两者功能一致，参数完全一致，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.ops.RoIPool.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.ops.RoIPool.md
deleted file mode 100644
index 534335c0234..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.ops.RoIPool.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torchvision.ops.RoIPool
-### [torchvision.ops.RoIPool](https://pytorch.org/vision/main/generated/torchvision.ops.RoIPool.html)
-```python
-torchvision.ops.RoIPool(output_size: None, spatial_scale: float)
-```
-
-### [paddle.vision.ops.RoIPool](https://www.paddlepaddle.org.cn/documentation/docs/zh/api/paddle/vision/ops/RoIPool_cn.html)
-```python
-paddle.vision.ops.RoIPool(output_size, spatial_scale=1.0)
-```
-
-功能一致，参数完全一致，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transform.functional.pad.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transform.functional.pad.md
deleted file mode 100644
index 170a6794f2a..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transform.functional.pad.md
+++ /dev/null
@@ -1,22 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torchvision.transforms.functional.pad
-### [torchvision.transforms.functional.pad](https://pytorch.org/vision/main/generated/torchvision.transforms.functional.pad.html)
-```python
-torchvision.transforms.functional.pad(
-    img: Union[PIL.Image.Image, torch.Tensor],
-    padding: Union[int, List[int], Tuple[int, ...]],
-    fill: Union[int, List[int], Tuple[int, ...]] = 0,
-    padding_mode: Literal['constant', 'edge', 'reflect', 'symmetric'] = 'constant'
-)
-```
-
-### [paddle.vision.transforms.pad](https://www.paddlepaddle.org.cn/documentation/docs/zh/api/paddle/vision/transforms/pad_cn.html)
-```python
-paddle.vision.transforms.pad(
-    img: Union[PIL.Image.Image, np.ndarray, paddle.Tensor],
-    padding: Union[int, List[int], Tuple[int, ...]],
-    fill: Union[int, List[int], Tuple[int, ...]] = 0,
-    padding_mode: Literal['constant', 'edge', 'reflect', 'symmetric'] = 'constant'
-)
-```
-
-功能一致，参数完全一致，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.Compose.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.Compose.md
deleted file mode 100644
index 2afeb4331b9..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.Compose.md
+++ /dev/null
@@ -1,16 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torchvision.transforms.Compose
-### [torchvision.transforms.Compose](https://pytorch.org/vision/main/generated/torchvision.transforms.Compose.html)
-```python
-torchvision.transforms.Compose(
-    transforms: List[Transform]
-)
-```
-
-### [paddle.vision.transforms.Compose](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/Compose_cn.html)
-```python
-paddle.vision.transforms.Compose(
-    transforms: Union[List[Transform], Tuple[Transform, ...]]
-)
-```
-
-功能一致，参数完全一致，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.InterpolationMode.BICUBIC.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.InterpolationMode.BICUBIC.md
deleted file mode 100644
index 66cb335dd1d..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.InterpolationMode.BICUBIC.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torchvision.transforms.InterpolationMode.BICUBIC
-### [torchvision.transforms.InterpolationMode.BICUBIC](https://pytorch.org/vision/stable/index.html)
-```python
-torchvision.transforms.InterpolationMode.BICUBIC
-```
-
-### ['bicubic']()
-```python
-'bicubic'
-```
-
-枚举对应到字符串，两者功能一致，无参数。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.InterpolationMode.BILINEAR.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.InterpolationMode.BILINEAR.md
deleted file mode 100644
index f29d36366d2..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.InterpolationMode.BILINEAR.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torchvision.transforms.InterpolationMode.BILINEAR
-### [torchvision.transforms.InterpolationMode.BILINEAR](https://pytorch.org/vision/stable/index.html)
-```python
-torchvision.transforms.InterpolationMode.BILINEAR
-```
-
-### ['bilinear']()
-```python
-'bilinear'
-```
-
-枚举对应到字符串，两者功能一致，无参数。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.InterpolationMode.BOX.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.InterpolationMode.BOX.md
deleted file mode 100644
index b6b9604b3d9..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.InterpolationMode.BOX.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torchvision.transforms.InterpolationMode.BOX
-### [torchvision.transforms.InterpolationMode.BOX](https://pytorch.org/vision/stable/index.html)
-```python
-torchvision.transforms.InterpolationMode.BOX
-```
-
-### ['box']()
-```python
-'box'
-```
-
-枚举对应到字符串，两者功能一致，无参数。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.InterpolationMode.HAMMING.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.InterpolationMode.HAMMING.md
deleted file mode 100644
index 207bb5033d4..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.InterpolationMode.HAMMING.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torchvision.transforms.InterpolationMode.HAMMING
-### [torchvision.transforms.InterpolationMode.HAMMING](https://pytorch.org/vision/stable/index.html)
-```python
-torchvision.transforms.InterpolationMode.HAMMING
-```
-
-### ['hamming']()
-```python
-'hamming'
-```
-
-枚举对应到字符串，两者功能一致，无参数。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.InterpolationMode.LANCZOS.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.InterpolationMode.LANCZOS.md
deleted file mode 100644
index ffa836ce394..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.InterpolationMode.LANCZOS.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torchvision.transforms.InterpolationMode.LANCZOS
-### [torchvision.transforms.InterpolationMode.LANCZOS](https://pytorch.org/vision/stable/index.html)
-```python
-torchvision.transforms.InterpolationMode.LANCZOS
-```
-
-### ['lanczos']()
-```python
-'lanczos'
-```
-
-枚举对应到字符串，两者功能一致，无参数。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.InterpolationMode.NEAREST.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.InterpolationMode.NEAREST.md
deleted file mode 100644
index 9daacb7e048..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.InterpolationMode.NEAREST.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torchvision.transforms.InterpolationMode.NEAREST
-### [torchvision.transforms.InterpolationMode.NEAREST](https://pytorch.org/vision/stable/index.html)
-```python
-torchvision.transforms.InterpolationMode.NEAREST
-```
-
-### ['nearest']()
-```python
-'nearest'
-```
-
-枚举对应到字符串，两者功能一致，无参数。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.InterpolationMode.NEAREST_EXACT.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.InterpolationMode.NEAREST_EXACT.md
deleted file mode 100644
index 44b9a0ff852..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.InterpolationMode.NEAREST_EXACT.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torchvision.transforms.InterpolationMode.NEAREST_EXACT
-### [torchvision.transforms.InterpolationMode.NEAREST_EXACT](https://pytorch.org/vision/stable/index.html)
-```python
-torchvision.transforms.InterpolationMode.NEAREST_EXACT
-```
-
-### ['nearest_exact']()
-```python
-'nearest_exact'
-```
-
-枚举对应到字符串，两者功能一致，无参数。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.functional.adjust_brightness.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.functional.adjust_brightness.md
deleted file mode 100644
index 63b5c780e63..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.functional.adjust_brightness.md
+++ /dev/null
@@ -1,15 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torchvision.transforms.functional.adjust_brightness
-### [torchvision.transforms.functional.adjust_brightness](https://pytorch.org/vision/main/generated/torchvision.transforms.functional.adjust_brightness.html)
-```python
-torchvision.transforms.functional.adjust_brightness(img: Tensor, brightness_factor: float)
-```
-
-### [paddle.vision.transforms.adjust_brightness](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/adjust_brightness_cn.html)
-```python
-paddle.vision.transforms.adjust_brightness(
-    img: Union[PIL.Image.Image, np.ndarray, paddle.Tensor],
-    brightness_factor: float
-)
-```
-
-功能一致，参数完全一致，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.functional.adjust_contrast.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.functional.adjust_contrast.md
deleted file mode 100644
index d2eb7fe3752..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.functional.adjust_contrast.md
+++ /dev/null
@@ -1,15 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torchvision.transforms.functional.adjust_contrast
-### [torchvision.transforms.functional.adjust_contrast](https://pytorch.org/vision/main/generated/torchvision.transforms.functional.adjust_contrast.html)
-```python
-torchvision.transforms.functional.adjust_contrast(img: Tensor, contrast_factor: float)
-```
-
-### [paddle.vision.transforms.adjust_contrast](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/adjust_contrast_cn.html)
-```python
-paddle.vision.transforms.adjust_contrast(
-    img: Union[PIL.Image.Image, np.ndarray, paddle.Tensor],
-    contrast_factor: float
-)
-```
-
-功能一致，参数完全一致，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.functional.adjust_hue.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.functional.adjust_hue.md
deleted file mode 100644
index 93f127dcf8b..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.functional.adjust_hue.md
+++ /dev/null
@@ -1,15 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torchvision.transforms.functional.adjust_hue
-### [torchvision.transforms.functional.adjust_hue](https://pytorch.org/vision/main/generated/torchvision.transforms.functional.adjust_hue.html)
-```python
-torchvision.transforms.functional.adjust_hue(img: Tensor, hue_factor: float)
-```
-
-### [paddle.vision.transforms.adjust_hue](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/adjust_hue_cn.html)
-```python
-paddle.vision.transforms.adjust_hue(
-    img: Union[PIL.Image.Image, np.ndarray, paddle.Tensor],
-    hue_factor: float
-)
-```
-
-功能一致，参数完全一致，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.functional.center_crop.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.functional.center_crop.md
deleted file mode 100644
index fccde598f5a..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.functional.center_crop.md
+++ /dev/null
@@ -1,15 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torchvision.transforms.functional.center_crop
-### [torchvision.transforms.functional.center_crop](https://pytorch.org/vision/main/generated/torchvision.transforms.functional.center_crop.html)
-```python
-torchvision.transforms.functional.center_crop(img: Tensor, output_size: List[int])
-```
-
-### [paddle.vision.transforms.center_crop](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/center_crop_cn.html)
-```python
-paddle.vision.transforms.center_crop(
-    img: Union[PIL.Image.Image, paddle.Tensor, np.ndarray],
-    output_size: List[int]
-)
-```
-
-两者功能一致，参数完全一致，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.functional.crop.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.functional.crop.md
deleted file mode 100644
index d1475bb4e1e..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.functional.crop.md
+++ /dev/null
@@ -1,24 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torchvision.transforms.functional.crop
-### [torchvision.transforms.functional.crop](https://pytorch.org/vision/main/generated/torchvision.transforms.functional.crop.html)
-```python
-torchvision.transforms.functional.crop(
-    img: Union[PIL.Image.Image, torch.Tensor],
-    top: int,
-    left: int,
-    height: int,
-    width: int
-)
-```
-
-### [paddle.vision.transforms.crop](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/crop_cn.html)
-```python
-paddle.vision.transforms.crop(
-    img: Union[PIL.Image.Image, np.ndarray, paddle.Tensor],
-    top: int,
-    left: int,
-    height: int,
-    width: int
-)
-```
-
-两者功能一致，参数完全一致，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.functional.erase.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.functional.erase.md
deleted file mode 100644
index 597d609eb55..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.functional.erase.md
+++ /dev/null
@@ -1,28 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torchvision.transforms.functional.erase
-### [torchvision.transforms.functional.erase](https://pytorch.org/vision/main/generated/torchvision.transforms.functional.erase.html?highlight=erase#torchvision.transforms.functional.erase)
-```python
-torchvision.transforms.functional.erase(
-    img: Tensor,
-    i: int,
-    j: int,
-    h: int,
-    w: int,
-    v: Tensor,
-    inplace: bool = False
-)
-```
-
-### [paddle.vision.transforms.erase](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/erase_cn.html)
-```python
-paddle.vision.transforms.erase(
-    img: Union[paddle.Tensor, np.ndarray, PIL.Image.Image],
-    i: int,
-    j: int,
-    h: int,
-    w: int,
-    v: Union[paddle.Tensor, np.ndarray],
-    inplace: bool = False
-)
-```
-
-两者功能一致，参数完全一致，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.functional.hflip.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.functional.hflip.md
deleted file mode 100644
index 9164c718754..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.functional.hflip.md
+++ /dev/null
@@ -1,16 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torchvision.transforms.functional.hflip
-### [torchvision.transforms.functional.hflip](https://pytorch.org/vision/main/generated/torchvision.transforms.functional.hflip.html)
-```python
-torchvision.transforms.functional.hflip(
-    img: Union[PIL.Image.Image, torch.Tensor]
-)
-```
-
-### [paddle.vision.transforms.hflip](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/hflip_cn.html)
-```python
-paddle.vision.transforms.hflip(
-    img: Union[PIL.Image.Image, np.ndarray, paddle.Tensor]
-)
-```
-
-两者功能一致，参数完全一致，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.functional.to_grayscale.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.functional.to_grayscale.md
deleted file mode 100644
index 63f0672b728..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.functional.to_grayscale.md
+++ /dev/null
@@ -1,16 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torchvision.transforms.functional.to_grayscale
-### [torchvision.transforms.functional.to_grayscale](https://pytorch.org/vision/main/generated/torchvision.transforms.functional.to_grayscale.html?highlight=to_grayscale#torchvision.transforms.functional.to_grayscale)
-```python
-torchvision.transforms.functional.to_grayscale(img: PIL.Image.Image,
-                                               num_output_channels: int = 1)
-```
-
-### [paddle.vision.transforms.to_grayscale](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/to_grayscale_cn.html#to-grayscale)
-```python
-paddle.vision.transforms.to_grayscale(
-    img: Union[PIL.Image.Image, np.ndarray],
-    num_output_channels: int = 1
-)
-```
-
-功能一致，参数完全一致，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.functional.vflip.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.functional.vflip.md
deleted file mode 100644
index c1eaa58646a..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torchvision.transforms.functional.vflip.md
+++ /dev/null
@@ -1,16 +0,0 @@
-## [ 仅 API 调用方式不一致 ]torchvision.transforms.functional.vflip
-### [torchvision.transforms.functional.vflip](https://pytorch.org/vision/main/generated/torchvision.transforms.functional.vflip.html)
-```python
-torchvision.transforms.functional.vflip(
-    img: Union[PIL.Image.Image, torch.Tensor]
-)
-```
-
-### [paddle.vision.transforms.vflip](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/vflip_cn.html)
-```python
-paddle.vision.transforms.vflip(
-    img: Union[PIL.Image.Image, np.ndarray, paddle.Tensor]
-)
-```
-
-功能一致，参数完全一致，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/transformers.generation.LogitsProcessorList.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/transformers.generation.LogitsProcessorList.md
deleted file mode 100644
index 7c122ed9a17..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/transformers.generation.LogitsProcessorList.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]transformers.generation.LogitsProcessorList
-### [transformers.generation.LogitsProcessorList](https://hf-mirror.com/docs/transformers/v4.42.0/en/internal/generation_utils#transformers.LogitsProcessorList)
-```python
-transformers.generation.LogitsProcessorList()
-```
-
-### [paddlenlp.generation.LogitsProcessorList](https://github.com/PaddlePaddle/PaddleNLP/blob/e336e78c338d2514ee6c937982ce5d8c960b85ff/paddlenlp/transformers/bloom/processor.py#L24)
-```python
-paddlenlp.generation.LogitsProcessorList()
-```
-
-虚基类，用于被继承。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/transformers.generation.utils.GenerateOutput.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/transformers.generation.utils.GenerateOutput.md
deleted file mode 100644
index be6681c5ed4..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/transformers.generation.utils.GenerateOutput.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]transformers.generation.utils.GenerateOutput
-### [transformers.generation.utils.GenerateOutput](https://github.com/huggingface/transformers/blob/v4.42.0/src/transformers/generation/utils.py#L345)
-```python
-transformers.generation.utils.GenerateOutput()
-```
-
-### [paddlenlp.transformers.model_outputs.BaseModelOutput](https://github.com/PaddlePaddle/PaddleNLP/blob/e336e78c338d2514ee6c937982ce5d8c960b85ff/paddlenlp/transformers/model_outputs.py#L513)
-```python
-paddlenlp.transformers.model_outputs.BaseModelOutput()
-```
-
-两者功能一致且无参数。
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/transformers.modeling_outputs.BaseModelOutputWithPast.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/transformers.modeling_outputs.BaseModelOutputWithPast.md
deleted file mode 100644
index d14561c9037..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/transformers.modeling_outputs.BaseModelOutputWithPast.md
+++ /dev/null
@@ -1,13 +0,0 @@
-## [ 仅 API 调用方式不一致 ]transformers.modeling_outputs.BaseModelOutputWithPast
-### [transformers.modeling_outputs.BaseModelOutputWithPast](https://hf-mirror.com/docs/transformers/v4.42.0/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPast)
-```python
-transformers.modeling_outputs.BaseModelOutputWithPast(last_hidden_state: FloatTensor = None, past_key_values: Optional = None, hidden_states: Optional = None, attentions: Optional = None)
-```
-
-### [paddlenlp.transformers.model_outputs.BaseModelOutputWithPast](https://github.com/PaddlePaddle/PaddleNLP/blob/e336e78c338d2514ee6c937982ce5d8c960b85ff/paddlenlp/transformers/model_outputs.py#L590)
-```python
-paddlenlp.transformers.model_outputs.BaseModelOutputWithPast(last_hidden_state: paddle.Tensor = None, past_key_values: Optional[Tuple[Tuple[paddle.Tensor]]] = None, hidden_states: Optional[Tuple[paddle.Tensor]] = None, attentions: Optional[Tuple[paddle.Tensor]] = None)
-```
-
-
-功能一致，参数完全一致，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/transformers.modeling_outputs.CausalLMOutputWithPast.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/transformers.modeling_outputs.CausalLMOutputWithPast.md
deleted file mode 100644
index d4024f02265..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/transformers.modeling_outputs.CausalLMOutputWithPast.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]transformers.modeling_outputs.CausalLMOutputWithPast
-### [transformers.modeling_outputs.CausalLMOutputWithPast](https://hf-mirror.com/docs/transformers/v4.42.0/en/main_classes/output#transformers.modeling_outputs.CausalLMOutputWithPast)
-```python
-transformers.modeling_outputs.CausalLMOutputWithPast(loss: Optional = None, logits: FloatTensor = None, past_key_values: Optional = None, hidden_states: Optional = None, attentions: Optional = None)
-```
-
-### [paddlenlp.transformers.model_outputs.CausalLMOutputWithPast](https://github.com/PaddlePaddle/PaddleNLP/blob/e336e78c338d2514ee6c937982ce5d8c960b85ff/paddlenlp/transformers/model_outputs.py#L874)
-```python
-paddlenlp.transformers.model_outputs.CausalLMOutputWithPast(loss: Optional[paddle.Tensor] = None, logits: paddle.Tensor = None, past_key_values: Optional[Tuple[Tuple[paddle.Tensor]]] = None, hidden_states: Optional[Tuple[paddle.Tensor]] = None, attentions: Optional[Tuple[paddle.Tensor]] = None)
-```
-
-功能一致，参数完全一致，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/transformers.utils.add_start_docstrings_to_model_forward.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/transformers.utils.add_start_docstrings_to_model_forward.md
deleted file mode 100644
index 6c88fcbc2e8..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/transformers.utils.add_start_docstrings_to_model_forward.md
+++ /dev/null
@@ -1,12 +0,0 @@
-## [ 仅 API 调用方式不一致 ]transformers.utils.add_start_docstrings_to_model_forward
-### [transformers.utils.add_start_docstrings_to_model_forward](https://github.com/huggingface/transformers/blob/44b231671db25974cfebcdae34402ad5099bf37a/src/transformers/utils/doc.py#L45)
-```python
-transformers.utils.add_start_docstrings_to_model_forward(*docstr)
-```
-
-### [paddlenlp.trainer.utils.add_start_docstrings_to_model_forward](https://github.com/PaddlePaddle/PaddleNLP/blob/8fd74f0b74cdae12e74518b9dbbb8f6c6219c338/paddlenlp/trainer/utils/doc.py#L27)
-```python
-paddlenlp.trainer.utils.add_start_docstrings_to_model_forward(*docstr)
-```
-
-功能一致，参数完全一致，具体如下：
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.argwhere.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.argwhere.md
new file mode 100644
index 00000000000..cf4e280a4f6
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.argwhere.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.Tensor.argwhere
+
+### [torch.Tensor.argwhere](https://pytorch.org/docs/stable/tensors.html#torch.Tensor.argwhere)
+
+```python
+torch.Tensor.argwhere()
+```
+
+### [paddle.Tensor.nonzero](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor/nonzero_cn.html#paddle/Tensor/nonzero_cn#cn-api-paddle-Tensor-nonzero)
+
+```python
+paddle.Tensor.nonzero(as_tuple=False)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = input.argwhere()
+
+# Paddle 写法
+result = input.nonzero()
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.bernoulli.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.bernoulli.md
new file mode 100644
index 00000000000..b365829e860
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.bernoulli.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.Tensor.bernoulli
+
+### [torch.Tensor.bernoulli](https://pytorch.org/docs/stable/tensors.html#torch.Tensor.bernoulli)
+
+```python
+torch.Tensor.bernoulli(generator=None)
+```
+
+### [paddle.bernoulli](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/bernoulli_cn.html#paddle/bernoulli_cn#cn-api-paddle-bernoulli)
+
+```python
+paddle.bernoulli(x, name=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = a.bernoulli()
+
+# Paddle 写法
+result = paddle.bernoulli(a)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.clamp_.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.clamp_.md
new file mode 100644
index 00000000000..bd6c968f52a
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.clamp_.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.Tensor.clamp_
+
+### [torch.Tensor.clamp_](https://pytorch.org/docs/stable/tensors.html#torch.Tensor.clamp_)
+
+```python
+torch.Tensor.clamp_(min=None, max=None)
+```
+
+### [paddle.Tensor.clip_](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor/clip__cn.html#paddle/Tensor/clip__cn#cn-api-paddle-Tensor-clip_)
+
+```python
+paddle.Tensor.clip_(min=None, max=None, name=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = a.clamp_(-0.5, 0.5)
+
+# Paddle 写法
+result = a.clip_(-0.5, 0.5)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.col_indices.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.col_indices.md
new file mode 100644
index 00000000000..3a71d945cbc
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.col_indices.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.Tensor.col_indices
+
+### [torch.Tensor.col_indices](https://pytorch.org/docs/stable/tensors.html#torch.Tensor.col_indices)
+
+```python
+torch.Tensor.col_indices()
+```
+
+### [paddle.Tensor.cols](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor/cols_cn.html#paddle/Tensor/cols_cn#cn-api-paddle-Tensor-cols)
+
+```python
+paddle.Tensor.cols()
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = a.col_indices()
+
+# Paddle 写法
+result = a.cols()
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.conj_physical.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.conj_physical.md
new file mode 100644
index 00000000000..875f029843d
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.conj_physical.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.Tensor.conj_physical
+
+### [torch.Tensor.conj_physical](https://pytorch.org/docs/stable/tensors.html#torch.Tensor.conj_physical)
+
+```python
+torch.Tensor.conj_physical()
+```
+
+### [paddle.Tensor.conj](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor/conj_cn.html#paddle/Tensor/conj_cn#cn-api-paddle-Tensor-conj)
+
+```python
+paddle.Tensor.conj(name=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = src.conj_physical()
+
+# Paddle 写法
+result = src.conj()
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.crow_indices.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.crow_indices.md
new file mode 100644
index 00000000000..b2117d87f3b
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.crow_indices.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.Tensor.crow_indices
+
+### [torch.Tensor.crow_indices](https://pytorch.org/docs/stable/tensors.html#torch.Tensor.crow_indices)
+
+```python
+torch.Tensor.crow_indices()
+```
+
+### [paddle.Tensor.crows](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor/crows_cn.html#paddle/Tensor/crows_cn#cn-api-paddle-Tensor-crows)
+
+```python
+paddle.Tensor.crows()
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = a.crow_indices()
+
+# Paddle 写法
+result = a.crows()
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.det.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.det.md
new file mode 100644
index 00000000000..4522f22fdc4
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.det.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.Tensor.det
+
+### [torch.Tensor.det](https://pytorch.org/docs/stable/tensors.html#torch.Tensor.det)
+
+```python
+torch.Tensor.det()
+```
+
+### [paddle.linalg.det](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/linalg/det_cn.html#paddle/linalg/det_cn#cn-api-paddle-linalg-det)
+
+```python
+paddle.linalg.det(x, name=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = x.det()
+
+# Paddle 写法
+result = paddle.linalg.det(x)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.device.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.device.md
new file mode 100644
index 00000000000..36654568596
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.device.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.Tensor.device
+
+### [torch.Tensor.device](https://pytorch.org/docs/stable/tensors.html#torch.Tensor.device)
+
+```python
+torch.Tensor.device
+```
+
+### [paddle.Tensor.place](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor/place_cn.html#paddle/Tensor/place_cn#cn-api-paddle-Tensor-place)
+
+```python
+paddle.Tensor.place
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = src.device
+
+# Paddle 写法
+result = src.place
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.erf_.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.erf_.md
new file mode 100644
index 00000000000..20dc16b9d0c
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.erf_.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.Tensor.erf_
+
+### [torch.Tensor.erf_](https://pytorch.org/docs/stable/tensors.html#torch.Tensor.erf_)
+
+```python
+torch.Tensor.erf_()
+```
+
+### [paddle.erf_](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/erf__cn.html#paddle/erf__cn#cn-api-paddle-erf_)
+
+```python
+paddle.erf_(x, name=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+a.erf_()
+
+# Paddle 写法
+paddle.erf_(a)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.expm1_.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.expm1_.md
new file mode 100644
index 00000000000..9e38efae281
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.expm1_.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.Tensor.expm1_
+
+### [torch.Tensor.expm1_](https://pytorch.org/docs/stable/tensors.html#torch.Tensor.expm1_)
+
+```python
+torch.Tensor.expm1_()
+```
+
+### [paddle.expm1_](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/expm1__cn.html#paddle/expm1__cn#cn-api-paddle-expm1_)
+
+```python
+paddle.expm1_(x, name=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+a.expm1_()
+
+# Paddle 写法
+paddle.expm1_(a)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.fix.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.fix.md
new file mode 100644
index 00000000000..7609bb41268
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.fix.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.Tensor.fix
+
+### [torch.Tensor.fix](https://pytorch.org/docs/stable/tensors.html#torch.Tensor.fix)
+
+```python
+torch.Tensor.fix()
+```
+
+### [paddle.Tensor.trunc](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor/trunc_cn.html#paddle/Tensor/trunc_cn#cn-api-paddle-Tensor-trunc)
+
+```python
+paddle.Tensor.trunc(name=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = input.fix()
+
+# Paddle 写法
+result = input.trunc()
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.fix_.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.fix_.md
new file mode 100644
index 00000000000..77fce690efb
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.fix_.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.Tensor.fix_
+
+### [torch.Tensor.fix_](https://pytorch.org/docs/stable/tensors.html#torch.Tensor.fix_)
+
+```python
+torch.Tensor.fix_()
+```
+
+### [paddle.Tensor.trunc_](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor/trunc__cn.html#paddle/Tensor/trunc__cn#cn-api-paddle-Tensor-trunc_)
+
+```python
+paddle.Tensor.trunc_(name=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = input.fix_()
+
+# Paddle 写法
+result = input.trunc_()
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.hardshrink.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.hardshrink.md
new file mode 100644
index 00000000000..cb5e71976fc
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.hardshrink.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.Tensor.hardshrink
+
+### [torch.Tensor.hardshrink](https://pytorch.org/docs/stable/tensors.html#torch.Tensor.hardshrink)
+
+```python
+torch.Tensor.hardshrink()
+```
+
+### [paddle.nn.functional.hardshrink](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/nn/functional/hardshrink_cn.html#paddle/nn/functional/hardshrink_cn#cn-api-paddle-nn-functional-hardshrink)
+
+```python
+paddle.nn.functional.hardshrink(x, threshold=0.5, name=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = x.hardshrink()
+
+# Paddle 写法
+result = paddle.nn.functional.hardshrink(x)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.imag.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.imag.md
new file mode 100644
index 00000000000..23385c8c093
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.imag.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.Tensor.imag
+
+### [torch.Tensor.imag](https://pytorch.org/docs/stable/tensors.html#torch.Tensor.imag)
+
+```python
+torch.Tensor.imag
+```
+
+### [paddle.Tensor.imag](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor/imag_cn.html#paddle/Tensor/imag_cn#cn-api-paddle-Tensor-imag)
+
+```python
+paddle.Tensor.imag(name=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = src.imag
+
+# Paddle 写法
+result = src.imag()
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.is_inference.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.is_inference.md
new file mode 100644
index 00000000000..a7ebe4efbd7
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.is_inference.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.Tensor.is_inference
+
+### [torch.Tensor.is_inference](https://pytorch.org/docs/stable/tensors.html#torch.Tensor.is_inference)
+
+```python
+torch.Tensor.is_inference()
+```
+
+### [paddle.Tensor.stop_gradient](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor/stop_gradient_cn.html#paddle/Tensor/stop_gradient_cn#cn-api-paddle-Tensor-stop_gradient)
+
+```python
+paddle.Tensor.stop_gradient
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = x.is_inference()
+
+# Paddle 写法
+result = x.stop_gradient
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.is_sparse.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.is_sparse.md
new file mode 100644
index 00000000000..5aa2d54d0b0
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.is_sparse.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.Tensor.is_sparse
+
+### [torch.Tensor.is_sparse](https://pytorch.org/docs/stable/tensors.html#torch.Tensor.is_sparse)
+
+```python
+torch.Tensor.is_sparse
+```
+
+### [paddle.Tensor.is_sparse](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor/is_sparse_cn.html#paddle/Tensor/is_sparse_cn#cn-api-paddle-Tensor-is_sparse)
+
+```python
+paddle.Tensor.is_sparse()
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = a.is_sparse
+
+# Paddle 写法
+result = a.is_sparse()
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.is_sparse_csr.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.is_sparse_csr.md
new file mode 100644
index 00000000000..2af468637f6
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.is_sparse_csr.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.Tensor.is_sparse_csr
+
+### [torch.Tensor.is_sparse_csr](https://pytorch.org/docs/stable/tensors.html#torch.Tensor.is_sparse_csr)
+
+```python
+torch.Tensor.is_sparse_csr
+```
+
+### [paddle.Tensor.is_sparse_csr](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor/is_sparse_csr_cn.html#paddle/Tensor/is_sparse_csr_cn#cn-api-paddle-Tensor-is_sparse_csr)
+
+```python
+paddle.Tensor.is_sparse_csr()
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = a.is_sparse_csr
+
+# Paddle 写法
+result = a.is_sparse_csr()
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.matrix_exp.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.matrix_exp.md
similarity index 54%
rename from docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.matrix_exp.md
rename to docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.matrix_exp.md
index 9cd9974b6f9..eb4bd4baad7 100644
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.Tensor.matrix_exp.md
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.matrix_exp.md
@@ -1,21 +1,25 @@
 ## [ 仅 API 调用方式不一致 ]torch.Tensor.matrix_exp
-### [torch.Tensor.matrix_exp](https://pytorch.org/docs/stable/generated/torch.Tensor.matrix_exp.html#torch-tensor-matrix-exp)
+
+### [torch.Tensor.matrix_exp](https://pytorch.org/docs/stable/tensors.html#torch.Tensor.matrix_exp)
+
 ```python
 torch.Tensor.matrix_exp()
 ```
 
-### [paddle.linalg.matrix_exp](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/linalg/matrix_exp_cn.html)
+### [paddle.linalg.matrix_exp](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/linalg/matrix_exp_cn.html#paddle/linalg/matrix_exp_cn#cn-api-paddle-linalg-matrix_exp)
+
 ```python
 paddle.linalg.matrix_exp(x, name=None)
 ```
 
-两者功能一致，无参数。
+两者功能一致，但调用方式不一致，具体如下：
 
 ### 转写示例
+
 ```python
 # PyTorch 写法
-out = x.matrix_exp()
+result = x.matrix_exp()
 
 # Paddle 写法
-out = paddle.linalg.matrix_exp(x)
+result = paddle.linalg.matrix_exp(x)
 ```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.movedim.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.movedim.md
new file mode 100644
index 00000000000..e630f6c64ac
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.movedim.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.Tensor.movedim
+
+### [torch.Tensor.movedim](https://pytorch.org/docs/stable/tensors.html#torch.Tensor.movedim)
+
+```python
+torch.Tensor.movedim(source, destination)
+```
+
+### [paddle.Tensor.moveaxis](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor/moveaxis_cn.html#paddle/Tensor/moveaxis_cn#cn-api-paddle-Tensor-moveaxis)
+
+```python
+paddle.Tensor.moveaxis(source, destination, name=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = x.movedim(1, 0)
+
+# Paddle 写法
+result = x.moveaxis(1, 0)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.mvlgamma.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.mvlgamma.md
new file mode 100644
index 00000000000..c82127db9ee
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.mvlgamma.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.Tensor.mvlgamma
+
+### [torch.Tensor.mvlgamma](https://pytorch.org/docs/stable/tensors.html#torch.Tensor.mvlgamma)
+
+```python
+torch.Tensor.mvlgamma(p)
+```
+
+### [paddle.Tensor.multigammaln](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor/multigammaln_cn.html#paddle/Tensor/multigammaln_cn#cn-api-paddle-Tensor-multigammaln)
+
+```python
+paddle.Tensor.multigammaln(p, name=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = x.mvlgamma(2)
+
+# Paddle 写法
+result = x.multigammaln(2)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.mvlgamma_.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.mvlgamma_.md
new file mode 100644
index 00000000000..eb86818b1dd
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.mvlgamma_.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.Tensor.mvlgamma_
+
+### [torch.Tensor.mvlgamma_](https://pytorch.org/docs/stable/tensors.html#torch.Tensor.mvlgamma_)
+
+```python
+torch.Tensor.mvlgamma_(p)
+```
+
+### [paddle.Tensor.multigammaln_](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor/multigammaln__cn.html#paddle/Tensor/multigammaln__cn#cn-api-paddle-Tensor-multigammaln_)
+
+```python
+paddle.Tensor.multigammaln_(p, name=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = x.mvlgamma_(2)
+
+# Paddle 写法
+result = x.multigammaln_(2)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.negative.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.negative.md
new file mode 100644
index 00000000000..2766d94f6f6
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.negative.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.Tensor.negative
+
+### [torch.Tensor.negative](https://pytorch.org/docs/stable/tensors.html#torch.Tensor.negative)
+
+```python
+torch.Tensor.negative()
+```
+
+### [paddle.Tensor.neg](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor/neg_cn.html#paddle/Tensor/neg_cn#cn-api-paddle-Tensor-neg)
+
+```python
+paddle.Tensor.neg(name=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = a.negative()
+
+# Paddle 写法
+result = a.neg()
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.negative_.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.negative_.md
new file mode 100644
index 00000000000..38677c1268f
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.negative_.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.Tensor.negative_
+
+### [torch.Tensor.negative_](https://pytorch.org/docs/stable/tensors.html#torch.Tensor.negative_)
+
+```python
+torch.Tensor.negative_()
+```
+
+### [paddle.Tensor.neg_](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor/neg__cn.html#paddle/Tensor/neg__cn#cn-api-paddle-Tensor-neg_)
+
+```python
+paddle.Tensor.neg_(name=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+a.negative_()
+
+# Paddle 写法
+a.neg_()
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.nelement.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.nelement.md
new file mode 100644
index 00000000000..0fc364b423b
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.nelement.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.Tensor.nelement
+
+### [torch.Tensor.nelement](https://pytorch.org/docs/stable/tensors.html#torch.Tensor.nelement)
+
+```python
+torch.Tensor.nelement()
+```
+
+### [paddle.Tensor.size](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor/size_cn.html#paddle/Tensor/size_cn#cn-api-paddle-Tensor-size)
+
+```python
+paddle.Tensor.size
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = a.nelement()
+
+# Paddle 写法
+result = a.size
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.numel.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.numel.md
new file mode 100644
index 00000000000..e80f89f6a02
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.numel.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.Tensor.numel
+
+### [torch.Tensor.numel](https://pytorch.org/docs/stable/tensors.html#torch.Tensor.numel)
+
+```python
+torch.Tensor.numel()
+```
+
+### [paddle.Tensor.size](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor/size_cn.html#paddle/Tensor/size_cn#cn-api-paddle-Tensor-size)
+
+```python
+paddle.Tensor.size
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = a.numel()
+
+# Paddle 写法
+result = a.size
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.pinverse.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.pinverse.md
new file mode 100644
index 00000000000..89810be491a
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.pinverse.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.Tensor.pinverse
+
+### [torch.Tensor.pinverse](https://pytorch.org/docs/stable/tensors.html#torch.Tensor.pinverse)
+
+```python
+torch.Tensor.pinverse()
+```
+
+### [paddle.Tensor.pinv](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor/pinv_cn.html#paddle/Tensor/pinv_cn#cn-api-paddle-Tensor-pinv)
+
+```python
+paddle.Tensor.pinv(rcond=1e-15, hermitian=False, name=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = a.pinverse()
+
+# Paddle 写法
+result = a.pinv()
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.positive.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.positive.md
new file mode 100644
index 00000000000..061b26d0ffc
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.positive.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.Tensor.positive
+
+### [torch.Tensor.positive](https://pytorch.org/docs/stable/tensors.html#torch.Tensor.positive)
+
+```python
+torch.Tensor.positive()
+```
+
+### [paddle.positive](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/positive_cn.html#paddle/positive_cn#cn-api-paddle-positive)
+
+```python
+paddle.positive(x)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = x.positive()
+
+# Paddle 写法
+result = paddle.positive(x)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.real.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.real.md
new file mode 100644
index 00000000000..2736e15e5f0
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.real.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.Tensor.real
+
+### [torch.Tensor.real](https://pytorch.org/docs/stable/tensors.html#torch.Tensor.real)
+
+```python
+torch.Tensor.real
+```
+
+### [paddle.Tensor.real](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor/real_cn.html#paddle/Tensor/real_cn#cn-api-paddle-Tensor-real)
+
+```python
+paddle.Tensor.real(name=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = src.real
+
+# Paddle 写法
+result = src.real()
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.retain_grad.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.retain_grad.md
new file mode 100644
index 00000000000..f7d725a96fc
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.retain_grad.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.Tensor.retain_grad
+
+### [torch.Tensor.retain_grad](https://pytorch.org/docs/stable/tensors.html#torch.Tensor.retain_grad)
+
+```python
+torch.Tensor.retain_grad()
+```
+
+### [paddle.Tensor.retain_grads](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor/retain_grads_cn.html#paddle/Tensor/retain_grads_cn#cn-api-paddle-Tensor-retain_grads)
+
+```python
+paddle.Tensor.retain_grads()
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result.retain_grad()
+
+# Paddle 写法
+result.retain_grads()
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.square_.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.square_.md
new file mode 100644
index 00000000000..b78d706f0d4
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.square_.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.Tensor.square_
+
+### [torch.Tensor.square_](https://pytorch.org/docs/stable/tensors.html#torch.Tensor.square_)
+
+```python
+torch.Tensor.square_()
+```
+
+### [paddle.square_](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/square__cn.html#paddle/square__cn#cn-api-paddle-square_)
+
+```python
+paddle.square_(x, name=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+x.square_()
+
+# Paddle 写法
+paddle.square_(x)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.to_sparse.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.to_sparse.md
new file mode 100644
index 00000000000..effb7248a25
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.Tensor.to_sparse.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.Tensor.to_sparse
+
+### [torch.Tensor.to_sparse](https://pytorch.org/docs/stable/tensors.html#torch.Tensor.to_sparse)
+
+```python
+torch.Tensor.to_sparse(sparse_dim)
+```
+
+### [paddle.Tensor.to_sparse_coo](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor/to_sparse_coo_cn.html#paddle/Tensor/to_sparse_coo_cn#cn-api-paddle-Tensor-to_sparse_coo)
+
+```python
+paddle.Tensor.to_sparse_coo(sparse_dim)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+b = a.to_sparse(1)
+
+# Paddle 写法
+b = a.to_sparse_coo(1)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.autograd.Function.forward.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.autograd.Function.forward.md
new file mode 100644
index 00000000000..84e8ff2a1fc
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.autograd.Function.forward.md
@@ -0,0 +1,45 @@
+## [ 仅 API 调用方式不一致 ]torch.autograd.Function.forward
+
+### [torch.autograd.Function.forward](https://pytorch.org/docs/stable/generated/torch.autograd.Function.html#torch.autograd.Function.forward)
+
+```python
+torch.autograd.Function.forward(*args, **kwargs)
+```
+
+### [paddle.autograd.PyLayer.forward](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/autograd/PyLayer/forward_cn.html#paddle/autograd/PyLayer/forward_cn#cn-api-paddle-autograd-PyLayer-forward)
+
+```python
+paddle.autograd.PyLayer.forward(ctx, *args, **kwargs)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+class cus_tanh(torch.autograd.Function):
+    @staticmethod
+    def forward(ctx, x, func=torch.square):
+        ctx.func = func
+        y = func(x)
+        return y
+
+    @staticmethod
+    def backward(ctx, dy):
+        grad = dy + 1
+        return grad
+
+# Paddle 写法
+class cus_tanh(paddle.autograd.PyLayer):
+    @staticmethod
+    def forward(ctx, x, func=paddle.square):
+        ctx.func = func
+        y = func(x)
+        return y
+
+    @staticmethod
+    def backward(ctx, dy):
+        grad = dy + 1
+        return grad
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.autograd.enable_grad.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.autograd.enable_grad.md
new file mode 100644
index 00000000000..11ba79ee671
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.autograd.enable_grad.md
@@ -0,0 +1,36 @@
+## [ 仅 API 调用方式不一致 ]torch.autograd.enable_grad
+
+### [torch.autograd.enable_grad](https://pytorch.org/docs/stable/generated/torch.autograd.html#torch.autograd.enable_grad)
+
+```python
+torch.autograd.enable_grad(*args, **kwargs)
+```
+
+### [paddle.enable_grad](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/enable_grad_cn.html#paddle/enable_grad_cn#cn-api-paddle-enable_grad)
+
+```python
+paddle.enable_grad(*args, **kwargs)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+@torch.autograd.enable_grad()
+def doubler(x):
+    return x * 2
+
+with torch.no_grad():
+    result = doubler(x)
+
+# Paddle 写法
+@paddle.enable_grad()
+def doubler(x):
+    return x * 2
+
+with paddle.no_grad():
+    result = doubler(x)
+
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.autograd.function.FunctionCtx.mark_non_differentiable.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.autograd.function.FunctionCtx.mark_non_differentiable.md
new file mode 100644
index 00000000000..7f01c9f93e8
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.autograd.function.FunctionCtx.mark_non_differentiable.md
@@ -0,0 +1,47 @@
+## [ 仅 API 调用方式不一致 ]torch.autograd.function.FunctionCtx.mark_non_differentiable
+
+### [torch.autograd.function.FunctionCtx.mark_non_differentiable](https://pytorch.org/docs/stable/generated/torch.autograd.function.FunctionCtx.html#torch.autograd.function.FunctionCtx.mark_non_differentiable)
+
+```python
+torch.autograd.function.FunctionCtx.mark_non_differentiable(*args)
+```
+
+### [paddle.autograd.PyLayerContext.mark_non_differentiable](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/autograd/PyLayerContext/mark_non_differentiable_cn.html#paddle/autograd/PyLayerContext/mark_non_differentiable_cn#cn-api-paddle-autograd-PyLayerContext-mark_non_differentiable)
+
+```python
+paddle.autograd.PyLayerContext.mark_non_differentiable(*args)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+class cus_func(torch.autograd.Function):
+    @staticmethod
+    def forward(ctx, x):
+        a = x + x
+        b = x + x + x
+        ctx.mark_non_differentiable(a)
+        return a, b
+
+    @staticmethod
+    def backward(ctx, grad_a, grad_b):
+        grad_x = 3 * grad_b
+        return grad_x
+
+# Paddle 写法
+class cus_func(paddle.autograd.PyLayer):
+    @staticmethod
+    def forward(ctx, x):
+        a = x + x
+        b = x + x + x
+        ctx.mark_non_differentiable(a)
+        return a, b
+
+    @staticmethod
+    def backward(ctx, grad_a, grad_b):
+        grad_x = 3 * grad_b
+        return grad_x
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.autograd.function.FunctionCtx.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.autograd.function.FunctionCtx.md
new file mode 100644
index 00000000000..9916d548db9
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.autograd.function.FunctionCtx.md
@@ -0,0 +1,45 @@
+## [ 仅 API 调用方式不一致 ]torch.autograd.function.FunctionCtx
+
+### [torch.autograd.function.FunctionCtx](https://pytorch.org/docs/stable/generated/torch.autograd.function.FunctionCtx.html#torch.autograd.function.FunctionCtx)
+
+```python
+torch.autograd.function.FunctionCtx(*args, **kwargs)
+```
+
+### [paddle.autograd.PyLayerContext](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/autograd/PyLayerContext_cn.html#paddle/autograd/PyLayerContext_cn#cn-api-paddle-autograd-PyLayerContext)
+
+```python
+paddle.autograd.PyLayerContext(*args, **kwargs)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+class MyFunction(torch.autograd.Function):
+    @staticmethod
+    def forward(ctx, x):
+        ctx.x = x
+        return x * 2
+
+    @staticmethod
+    def backward(ctx, grad_output):
+        x = ctx.x
+        grad_input = grad_output * 2
+        return grad_input
+
+# Paddle 写法
+class MyFunction(paddle.autograd.PyLayer):
+    @staticmethod
+    def forward(ctx, x):
+        ctx.x = x
+        return x * 2
+
+    @staticmethod
+    def backward(ctx, grad_output):
+        x = ctx.x
+        grad_input = grad_output * 2
+        return grad_input
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.autograd.function.FunctionCtx.save_for_backward.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.autograd.function.FunctionCtx.save_for_backward.md
new file mode 100644
index 00000000000..b29b29160f2
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.autograd.function.FunctionCtx.save_for_backward.md
@@ -0,0 +1,45 @@
+## [ 仅 API 调用方式不一致 ]torch.autograd.function.FunctionCtx.save_for_backward
+
+### [torch.autograd.function.FunctionCtx.save_for_backward](https://pytorch.org/docs/stable/generated/torch.autograd.function.FunctionCtx.html#torch.autograd.function.FunctionCtx.save_for_backward)
+
+```python
+torch.autograd.function.FunctionCtx.save_for_backward(*tensors)
+```
+
+### [paddle.autograd.PyLayerContext.save_for_backward](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/autograd/PyLayerContext/save_for_backward_cn.html#paddle/autograd/PyLayerContext/save_for_backward_cn#cn-api-paddle-autograd-PyLayerContext-save_for_backward)
+
+```python
+paddle.autograd.PyLayerContext.save_for_backward(*tensors)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+class cus_tanh(torch.autograd.Function):
+    @staticmethod
+    def forward(ctx, x):
+        y = torch.nn.functional.tanh(x)
+        ctx.save_for_backward(y)
+        return y
+
+    @staticmethod
+    def backward(ctx, dy):
+        grad = dy + 1
+        return grad
+
+# Paddle 写法
+class cus_tanh(paddle.autograd.PyLayer):
+    @staticmethod
+    def forward(ctx, x):
+        y = paddle.nn.functional.tanh(x=x)
+        ctx.save_for_backward(y)
+        return y
+
+    @staticmethod
+    def backward(ctx, dy):
+        grad = dy + 1
+        return grad
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.autograd.function.FunctionCtx.saved_tensors.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.autograd.function.FunctionCtx.saved_tensors.md
new file mode 100644
index 00000000000..f56e2392d77
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.autograd.function.FunctionCtx.saved_tensors.md
@@ -0,0 +1,47 @@
+## [ 仅 API 调用方式不一致 ]torch.autograd.function.FunctionCtx.saved_tensors
+
+### [torch.autograd.function.FunctionCtx.saved_tensors](https://pytorch.org/docs/stable/generated/torch.autograd.function.FunctionCtx.html#torch.autograd.function.FunctionCtx.saved_tensors)
+
+```python
+torch.autograd.function.FunctionCtx.saved_tensors
+```
+
+### [paddle.autograd.PyLayerContext.saved_tensor](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/autograd/PyLayerContext/saved_tensor_cn.html#paddle/autograd/PyLayerContext/saved_tensor_cn#cn-api-paddle-autograd-PyLayerContext-saved_tensor)
+
+```python
+paddle.autograd.PyLayerContext.saved_tensor()
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+class cus_tanh(torch.autograd.Function):
+    @staticmethod
+    def forward(ctx, x):
+        y = torch.nn.functional.tanh(x)
+        ctx.save_for_backward(x, y)
+        return y
+
+    @staticmethod
+    def backward(ctx, dy):
+        x, y = ctx.saved_tensors
+        grad = y + dy + 1
+        return grad
+
+# Paddle 写法
+class cus_tanh(paddle.autograd.PyLayer):
+    @staticmethod
+    def forward(ctx, x):
+        y = paddle.nn.functional.tanh(x=x)
+        ctx.save_for_backward(x, y)
+        return y
+
+    @staticmethod
+    def backward(ctx, dy):
+        x, y = ctx.saved_tensor()
+        grad = y + dy + 1
+        return grad
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.autograd.function.FunctionCtx.set_materialize_grads.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.autograd.function.FunctionCtx.set_materialize_grads.md
new file mode 100644
index 00000000000..0b27f929aad
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.autograd.function.FunctionCtx.set_materialize_grads.md
@@ -0,0 +1,43 @@
+## [ 仅 API 调用方式不一致 ]torch.autograd.function.FunctionCtx.set_materialize_grads
+
+### [torch.autograd.function.FunctionCtx.set_materialize_grads](https://pytorch.org/docs/stable/generated/torch.autograd.function.FunctionCtx.html#torch.autograd.function.FunctionCtx.set_materialize_grads)
+
+```python
+torch.autograd.function.FunctionCtx.set_materialize_grads(value)
+```
+
+### [paddle.autograd.PyLayerContext.set_materialize_grads](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/autograd/PyLayerContext/set_materialize_grads_cn.html#paddle/autograd/PyLayerContext/set_materialize_grads_cn#cn-api-paddle-autograd-PyLayerContext-set_materialize_grads)
+
+```python
+paddle.autograd.PyLayerContext.set_materialize_grads(value)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+class cus_tanh(torch.autograd.Function):
+    @staticmethod
+    def forward(ctx, x):
+        ctx.set_materialize_grads(False)
+        return x + x + x, x + x
+
+    @staticmethod
+    def backward(ctx, grad, grad2):
+        assert grad2 == None
+        return grad
+
+# Paddle 写法
+class cus_tanh(paddle.autograd.PyLayer):
+    @staticmethod
+    def forward(ctx, x):
+        ctx.set_materialize_grads(False)
+        return x + x + x, x + x
+
+    @staticmethod
+    def backward(ctx, grad, grad2):
+        assert grad2 == None
+        return grad
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.autograd.grad_mode.set_grad_enabled.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.autograd.grad_mode.set_grad_enabled.md
new file mode 100644
index 00000000000..c246e3ea2a2
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.autograd.grad_mode.set_grad_enabled.md
@@ -0,0 +1,27 @@
+## [ 仅 API 调用方式不一致 ]torch.autograd.grad_mode.set_grad_enabled
+
+### [torch.autograd.grad_mode.set_grad_enabled](https://pytorch.org/docs/stable/generated/torch.autograd.grad_mode.html#torch.autograd.grad_mode.set_grad_enabled)
+
+```python
+torch.autograd.grad_mode.set_grad_enabled(mode)
+```
+
+### [paddle.set_grad_enabled](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/set_grad_enabled_cn.html#paddle/set_grad_enabled_cn#cn-api-paddle-set_grad_enabled)
+
+```python
+paddle.set_grad_enabled(mode)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+with torch.autograd.grad_mode.set_grad_enabled(is_train):
+    y = x * 2
+
+# Paddle 写法
+with paddle.set_grad_enabled(is_train):
+    y = x * 2
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.autograd.graph.saved_tensors_hooks.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.autograd.graph.saved_tensors_hooks.md
new file mode 100644
index 00000000000..d99c7189205
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.autograd.graph.saved_tensors_hooks.md
@@ -0,0 +1,27 @@
+## [ 仅 API 调用方式不一致 ]torch.autograd.graph.saved_tensors_hooks
+
+### [torch.autograd.graph.saved_tensors_hooks](https://pytorch.org/docs/stable/generated/torch.autograd.graph.html#torch.autograd.graph.saved_tensors_hooks)
+
+```python
+torch.autograd.graph.saved_tensors_hooks(pack_hook, unpack_hook)
+```
+
+### [paddle.autograd.saved_tensors_hooks](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/autograd/saved_tensors_hooks_cn.html#paddle/autograd/saved_tensors_hooks_cn#cn-api-paddle-autograd-saved_tensors_hooks)
+
+```python
+paddle.autograd.saved_tensors_hooks(pack_hook, unpack_hook)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+with torch.autograd.graph.saved_tensors_hooks(pack_hook, unpack_hook):
+    y = torch.mul(a, b)
+
+# Paddle 写法
+with paddle.autograd.saved_tensors_hooks(pack_hook, unpack_hook):
+    y = paddle.mul(a, b)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.backends.cuda.is_built.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.backends.cuda.is_built.md
new file mode 100644
index 00000000000..2487d9c57cb
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.backends.cuda.is_built.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.backends.cuda.is_built
+
+### [torch.backends.cuda.is_built](https://pytorch.org/docs/stable/generated/torch.backends.cuda.html#torch.backends.cuda.is_built)
+
+```python
+torch.backends.cuda.is_built()
+```
+
+### [paddle.device.is_compiled_with_cuda](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/device/is_compiled_with_cuda_cn.html#paddle/device/is_compiled_with_cuda_cn#cn-api-paddle-device-is_compiled_with_cuda)
+
+```python
+paddle.device.is_compiled_with_cuda()
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = torch.backends.cuda.is_built()
+
+# Paddle 写法
+result = paddle.device.is_compiled_with_cuda()
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.backends.cudnn.version.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.backends.cudnn.version.md
new file mode 100644
index 00000000000..ef3ae4ef111
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.backends.cudnn.version.md
@@ -0,0 +1,26 @@
+## [ 仅 API 调用方式不一致 ]torch.backends.cudnn.version
+
+### [torch.backends.cudnn.version](https://pytorch.org/docs/stable/generated/torch.backends.cudnn.html#torch.backends.cudnn.version)
+
+```python
+torch.backends.cudnn.version()
+```
+
+### [paddle.device.get_cudnn_version](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/device/get_cudnn_version_cn.html#paddle/device/get_cudnn_version_cn#cn-api-paddle-device-get_cudnn_version)
+
+```python
+paddle.device.get_cudnn_version()
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = torch.backends.cudnn.version()
+
+# Paddle 写法
+result = paddle.device.get_cudnn_version()
+
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cpu.current_device.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cpu.current_device.md
new file mode 100644
index 00000000000..9067e2b2ce4
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cpu.current_device.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.cpu.current_device
+
+### [torch.cpu.current_device](https://pytorch.org/docs/stable/generated/torch.cpu.html#torch.cpu.current_device)
+
+```python
+torch.cpu.current_device()
+```
+
+### [paddle.get_device](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/get_device_cn.html#paddle/get_device_cn#cn-api-paddle-get_device)
+
+```python
+paddle.get_device()
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = torch.cpu.current_device()
+
+# Paddle 写法
+result = paddle.get_device()
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.cuda.Event.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cuda.Event.md
similarity index 61%
rename from docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.cuda.Event.md
rename to docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cuda.Event.md
index 91089728d97..63ab7639d36 100644
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.cuda.Event.md
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cuda.Event.md
@@ -1,12 +1,25 @@
 ## [ 仅 API 调用方式不一致 ]torch.cuda.Event
+
 ### [torch.cuda.Event](https://pytorch.org/docs/stable/generated/torch.cuda.Event.html#torch.cuda.Event)
+
 ```python
 torch.cuda.Event(enable_timing=False, blocking=False, interprocess=False)
 ```
 
-### [paddle.device.cuda.Event](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/device/cuda/Event_cn.html)
+### [paddle.device.cuda.Event](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/device/cuda/Event_cn.html#paddle/device/cuda/Event_cn#cn-api-paddle-device-cuda-Event)
+
 ```python
 paddle.device.cuda.Event(enable_timing=False, blocking=False, interprocess=False)
 ```
 
-功能一致，参数完全一致，具体如下：
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = torch.cuda.Event(enable_timing=True)
+
+# Paddle 写法
+result = paddle.device.cuda.Event(enable_timing=True)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cuda.StreamContext.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cuda.StreamContext.md
new file mode 100644
index 00000000000..b84878e5b90
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cuda.StreamContext.md
@@ -0,0 +1,27 @@
+## [ 仅 API 调用方式不一致 ]torch.cuda.StreamContext
+
+### [torch.cuda.StreamContext](https://pytorch.org/docs/stable/generated/torch.cuda.StreamContext.html#torch.cuda.StreamContext)
+
+```python
+torch.cuda.StreamContext(stream)
+```
+
+### [paddle.device.stream_guard](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/device/stream_guard_cn.html#paddle/device/stream_guard_cn#cn-api-paddle-device-stream_guard)
+
+```python
+paddle.device.stream_guard(stream)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+with torch.cuda.StreamContext(stream=s1):
+    result = a + b
+
+# Paddle 写法
+with paddle.device.stream_guard(stream=s1):
+    result = a + b
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cuda.get_device_name.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cuda.get_device_name.md
new file mode 100644
index 00000000000..c96c63d9617
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cuda.get_device_name.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.cuda.get_device_name
+
+### [torch.cuda.get_device_name](https://pytorch.org/docs/stable/generated/torch.cuda.get_device_name.html#torch.cuda.get_device_name)
+
+```python
+torch.cuda.get_device_name(device)
+```
+
+### [paddle.device.cuda.get_device_name](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/device/cuda/get_device_name_cn.html#paddle/device/cuda/get_device_name_cn#cn-api-paddle-device-cuda-get_device_name)
+
+```python
+paddle.device.cuda.get_device_name(device)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = torch.cuda.get_device_name(current_device)
+
+# Paddle 写法
+result = paddle.device.cuda.get_device_name(current_device)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cuda.get_rng_state_all.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cuda.get_rng_state_all.md
new file mode 100644
index 00000000000..f5039d37f1a
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cuda.get_rng_state_all.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.cuda.get_rng_state_all
+
+### [torch.cuda.get_rng_state_all](https://pytorch.org/docs/stable/generated/torch.cuda.get_rng_state_all.html#torch.cuda.get_rng_state_all)
+
+```python
+torch.cuda.get_rng_state_all()
+```
+
+### [paddle.get_rng_state](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/get_rng_state_cn.html#paddle/get_rng_state_cn#cn-api-paddle-get_rng_state)
+
+```python
+paddle.get_rng_state(device=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = torch.cuda.get_rng_state_all()
+
+# Paddle 写法
+result = paddle.get_rng_state()
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cuda.is_bf16_supported.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cuda.is_bf16_supported.md
new file mode 100644
index 00000000000..53a118d8bcb
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cuda.is_bf16_supported.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.cuda.is_bf16_supported
+
+### [torch.cuda.is_bf16_supported](https://pytorch.org/docs/stable/generated/torch.cuda.is_bf16_supported.html#torch.cuda.is_bf16_supported)
+
+```python
+torch.cuda.is_bf16_supported(including_emulation=True)
+```
+
+### [paddle.amp.is_bfloat16_supported](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/amp/is_bfloat16_supported_cn.html#paddle/amp/is_bfloat16_supported_cn#cn-api-paddle-amp-is_bfloat16_supported)
+
+```python
+paddle.amp.is_bfloat16_supported(device=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = torch.cuda.is_bf16_supported()
+
+# Paddle 写法
+result = paddle.amp.is_bfloat16_supported()
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cuda.manual_seed.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cuda.manual_seed.md
new file mode 100644
index 00000000000..8df630e5af6
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cuda.manual_seed.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.cuda.manual_seed
+
+### [torch.cuda.manual_seed](https://pytorch.org/docs/stable/generated/torch.cuda.manual_seed.html#torch.cuda.manual_seed)
+
+```python
+torch.cuda.manual_seed(seed)
+```
+
+### [paddle.seed](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/seed_cn.html#paddle/seed_cn#cn-api-paddle-seed)
+
+```python
+paddle.seed(seed)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+torch.cuda.manual_seed(123)
+
+# Paddle 写法
+paddle.seed(123)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cuda.max_memory_allocated.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cuda.max_memory_allocated.md
new file mode 100644
index 00000000000..c42af001279
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cuda.max_memory_allocated.md
@@ -0,0 +1,24 @@
+## [ 仅 API 调用方式不一致 ]torch.cuda.max_memory_allocated
+
+### [torch.cuda.max_memory_allocated](https://pytorch.org/docs/stable/generated/torch.cuda.max_memory_allocated.html#torch.cuda.max_memory_allocated)
+
+```python
+torch.cuda.max_memory_allocated(device=None)
+```
+### [paddle.device.cuda.max_memory_allocated](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/device/cuda/max_memory_allocated_cn.html#paddle/device/cuda/max_memory_allocated_cn#cn-api-paddle-device-cuda-max_memory_allocated)
+
+```python
+paddle.device.cuda.max_memory_allocated(device=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = torch.cuda.max_memory_allocated()
+
+# Paddle 写法
+result = paddle.device.cuda.max_memory_allocated()
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cuda.max_memory_reserved.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cuda.max_memory_reserved.md
new file mode 100644
index 00000000000..6d2124a8c15
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cuda.max_memory_reserved.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.cuda.max_memory_reserved
+
+### [torch.cuda.max_memory_reserved](https://pytorch.org/docs/stable/generated/torch.cuda.max_memory_reserved.html#torch.cuda.max_memory_reserved)
+
+```python
+torch.cuda.max_memory_reserved(device=None)
+```
+
+### [paddle.device.cuda.max_memory_reserved](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/device/cuda/max_memory_reserved_cn.html#paddle/device/cuda/max_memory_reserved_cn#cn-api-paddle-device-cuda-max_memory_reserved)
+
+```python
+paddle.device.cuda.max_memory_reserved(device=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = torch.cuda.max_memory_reserved()
+
+# Paddle 写法
+result = paddle.device.cuda.max_memory_reserved()
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cuda.nvtx.range_pop.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cuda.nvtx.range_pop.md
new file mode 100644
index 00000000000..76200f4aa84
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cuda.nvtx.range_pop.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.cuda.nvtx.range_pop
+
+### [torch.cuda.nvtx.range_pop](https://pytorch.org/docs/stable/generated/torch.cuda.nvtx.range_pop.html#torch.cuda.nvtx.range_pop)
+
+```python
+torch.cuda.nvtx.range_pop()
+```
+
+### [paddle.core.nvprof_nvtx_pop](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/framework/core/nvprof_nvtx_pop_cn.html#paddle/core/nvprof_nvtx_pop_cn#cn-api-paddle-core-nvprof_nvtx_pop)
+
+```python
+paddle.core.nvprof_nvtx_pop()
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = torch.cuda.nvtx.range_pop()
+
+# Paddle 写法
+result = paddle.core.nvprof_nvtx_pop()
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cuda.reset_max_memory_allocated.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cuda.reset_max_memory_allocated.md
new file mode 100644
index 00000000000..987b230acf3
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cuda.reset_max_memory_allocated.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.cuda.reset_max_memory_allocated
+
+### [torch.cuda.reset_max_memory_allocated](https://pytorch.org/docs/stable/generated/torch.cuda.reset_max_memory_allocated.html#torch.cuda.reset_max_memory_allocated)
+
+```python
+torch.cuda.reset_max_memory_allocated(device=None)
+```
+
+### [paddle.device.cuda.reset_max_memory_allocated](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/device/cuda/reset_max_memory_allocated_cn.html#paddle/device/cuda/reset_max_memory_allocated_cn#cn-api-paddle-device-cuda-reset_max_memory_allocated)
+
+```python
+paddle.device.cuda.reset_max_memory_allocated(device=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = torch.cuda.reset_max_memory_allocated()
+
+# Paddle 写法
+result = paddle.device.cuda.reset_max_memory_allocated()
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cuda.reset_max_memory_cached.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cuda.reset_max_memory_cached.md
new file mode 100644
index 00000000000..76c47040abf
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cuda.reset_max_memory_cached.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.cuda.reset_max_memory_cached
+
+### [torch.cuda.reset_max_memory_cached](https://pytorch.org/docs/stable/generated/torch.cuda.reset_max_memory_cached.html#torch.cuda.reset_max_memory_cached)
+
+```python
+torch.cuda.reset_max_memory_cached(device=None)
+```
+
+### [paddle.device.cuda.reset_max_memory_reserved](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/device/cuda/reset_max_memory_reserved_cn.html#paddle/device/cuda/reset_max_memory_reserved_cn#cn-api-paddle-device-cuda-reset_max_memory_reserved)
+
+```python
+paddle.device.cuda.reset_max_memory_reserved(device=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = torch.cuda.reset_max_memory_cached()
+
+# Paddle 写法
+result = paddle.device.cuda.reset_max_memory_reserved()
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cuda.set_stream.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cuda.set_stream.md
new file mode 100644
index 00000000000..4b151ae4c10
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cuda.set_stream.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.cuda.set_stream
+
+### [torch.cuda.set_stream](https://pytorch.org/docs/stable/generated/torch.cuda.set_stream.html#torch.cuda.set_stream)
+
+```python
+torch.cuda.set_stream(stream)
+```
+
+### [paddle.device.set_stream](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/device/set_stream_cn.html#paddle/device/set_stream_cn#cn-api-paddle-device-set_stream)
+
+```python
+paddle.device.set_stream(stream)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = torch.cuda.set_stream(stream)
+
+# Paddle 写法
+result = paddle.device.set_stream(stream)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cuda.stream.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cuda.stream.md
new file mode 100644
index 00000000000..e4d7534d312
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.cuda.stream.md
@@ -0,0 +1,28 @@
+## [ 仅 API 调用方式不一致 ]torch.cuda.stream
+
+### [torch.cuda.stream](https://pytorch.org/docs/stable/generated/torch.cuda.stream.html#torch.cuda.stream)
+
+```python
+torch.cuda.stream(stream)
+```
+
+### [paddle.device.stream_guard](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/device/stream_guard_cn.html#paddle/device/stream_guard_cn#cn-api-paddle-device-stream_guard)
+
+```python
+paddle.device.stream_guard(stream)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+with torch.cuda.stream(stream=s):
+    result = data1 + data2
+
+# Paddle 写法
+with paddle.device.stream_guard(stream=s):
+    result = data1 + data2
+
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.distributed.ReduceOp.PRODUCT.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.distributed.ReduceOp.PRODUCT.md
new file mode 100644
index 00000000000..5f4c8d86a84
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.distributed.ReduceOp.PRODUCT.md
@@ -0,0 +1,37 @@
+## [ 仅 API 调用方式不一致 ]torch.distributed.ReduceOp.PRODUCT
+
+### [torch.distributed.ReduceOp.PRODUCT](https://pytorch.org/docs/stable/distributed.html#torch.distributed.ReduceOp.PRODUCT)
+
+```python
+torch.distributed.ReduceOp.PRODUCT
+```
+
+### [paddle.distributed.ReduceOp.PROD](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/distributed/ReduceOp/PROD_cn.html#paddle/distributed/ReduceOp/PROD_cn#cn-api-paddle-distributed-ReduceOp-PROD)
+
+```python
+paddle.distributed.ReduceOp.PROD
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+torch.distributed.reduce_scatter(
+    data1,
+    [data1, data2],
+    op=torch.distributed.ReduceOp.PRODUCT,
+    group=None,
+    async_op=False
+)
+
+# Paddle 写法
+paddle.distributed.reduce_scatter(
+    tensor=data1,
+    tensor_list=[data1, data2],
+    op=paddle.distributed.ReduceOp.PROD,
+    group=None,
+    sync_op=not False,
+)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.distributed.ReduceOp.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.distributed.ReduceOp.md
new file mode 100644
index 00000000000..cd276737220
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.distributed.ReduceOp.md
@@ -0,0 +1,27 @@
+## [ 仅 API 调用方式不一致 ]torch.distributed.ReduceOp
+
+### [torch.distributed.ReduceOp](https://pytorch.org/docs/stable/generated/torch.distributed.ReduceOp.html#torch.distributed.ReduceOp)
+
+```python
+torch.distributed.ReduceOp
+```
+
+### [paddle.distributed.ReduceOp](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/distributed/ReduceOp_cn.html#paddle/distributed/ReduceOp_cn#cn-api-paddle-distributed-ReduceOp)
+
+```python
+paddle.distributed.ReduceOp
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+torch.distributed.init_process_group(backend="nccl")
+print(torch.distributed.ReduceOp)
+
+# Paddle 写法
+paddle.distributed.init_parallel_env()
+print(paddle.distributed.ReduceOp)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.distributed.is_nccl_available.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.distributed.is_nccl_available.md
new file mode 100644
index 00000000000..25b4fe80f51
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.distributed.is_nccl_available.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.distributed.is_nccl_available
+
+### [torch.distributed.is_nccl_available](https://pytorch.org/docs/stable/distributed.html#torch.distributed.is_nccl_available)
+
+```python
+torch.distributed.is_nccl_available()
+```
+
+### [paddle.core.is_compiled_with_nccl](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/core/is_compiled_with_nccl_cn.html#paddle/core/is_compiled_with_nccl_cn#cn-api-paddle-core-is_compiled_with_nccl)
+
+```python
+paddle.core.is_compiled_with_nccl()
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = torch.distributed.is_nccl_available()
+
+# Paddle 写法
+result = paddle.core.is_compiled_with_nccl()
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.distributions.constraints.Constraint.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.distributions.constraints.Constraint.md
new file mode 100644
index 00000000000..5d9150f4274
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.distributions.constraints.Constraint.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.distributions.constraints.Constraint
+
+### [torch.distributions.constraints.Constraint](https://pytorch.org/docs/stable/generated/torch.distributions.constraints.Constraint.html#torch.distributions.constraints.Constraint)
+
+```python
+torch.distributions.constraints.Constraint(*args, **kwargs)
+```
+
+### [paddle.distribution.constraint.Constraint](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/distribution/constraint/Constraint_cn.html#paddle/distribution/constraint/Constraint_cn#cn-api-paddle-distribution-constraint-Constraint)
+
+```python
+paddle.distribution.constraint.Constraint(*args, **kwargs)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = torch.distributions.constraints.Constraint().check(1)
+
+# Paddle 写法
+result = paddle.distribution.constraint.Constraint().check(1)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.distributions.kl.kl_divergence.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.distributions.kl.kl_divergence.md
new file mode 100644
index 00000000000..dd12d031c11
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.distributions.kl.kl_divergence.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.distributions.kl.kl_divergence
+
+### [torch.distributions.kl.kl_divergence](https://pytorch.org/docs/stable/generated/torch.distributions.kl.html#torch.distributions.kl.kl_divergence)
+
+```python
+torch.distributions.kl.kl_divergence(p, q)
+```
+
+### [paddle.distribution.kl_divergence](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/distribution/kl_divergence_cn.html#paddle/distribution/kl_divergence_cn#cn-api-paddle-distribution-kl_divergence)
+
+```python
+paddle.distribution.kl_divergence(p, q)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = torch.distributions.kl.kl_divergence(m, n)
+
+# Paddle 写法
+result = paddle.distribution.kl_divergence(m, n)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.is_inference.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.is_inference.md
new file mode 100644
index 00000000000..d20d4a1b7a7
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.is_inference.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.is_inference
+
+### [torch.is_inference](https://pytorch.org/docs/stable/generated/torch.is_inference.html)
+
+```python
+torch.is_inference(input)
+```
+
+### [paddle.Tensor.stop_gradient](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor/stop_gradient_cn.html#paddle/Tensor/stop_gradient_cn#cn-api-paddle-Tensor-stop_gradient)
+
+```python
+paddle.Tensor.stop_gradient
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = torch.is_inference(x)
+
+# Paddle 写法
+result = x.stop_gradient
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.AdaptiveAvgPool1d.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.AdaptiveAvgPool1d.md
new file mode 100644
index 00000000000..ba5e32ad431
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.AdaptiveAvgPool1d.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.nn.AdaptiveAvgPool1d
+
+### [torch.nn.AdaptiveAvgPool1d](https://pytorch.org/docs/stable/generated/torch.nn.AdaptiveAvgPool1d.html#torch.nn.AdaptiveAvgPool1d)
+
+```python
+torch.nn.AdaptiveAvgPool1d(output_size)
+```
+
+### [paddle.nn.AdaptiveAvgPool1D](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/nn/AdaptiveAvgPool1D_cn.html#paddle/nn/AdaptiveAvgPool1D_cn#cn-api-paddle-nn-AdaptiveAvgPool1D)
+
+```python
+paddle.nn.AdaptiveAvgPool1D(output_size, name=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+model = torch.nn.AdaptiveAvgPool1d(5)
+
+# Paddle 写法
+model = paddle.nn.AdaptiveAvgPool1D(5)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.AdaptiveAvgPool2d.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.AdaptiveAvgPool2d.md
new file mode 100644
index 00000000000..77cd446bdf8
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.AdaptiveAvgPool2d.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.nn.AdaptiveAvgPool2d
+
+### [torch.nn.AdaptiveAvgPool2d](https://pytorch.org/docs/stable/generated/torch.nn.AdaptiveAvgPool2d.html#torch.nn.AdaptiveAvgPool2d)
+
+```python
+torch.nn.AdaptiveAvgPool2d(output_size)
+```
+
+### [paddle.nn.AdaptiveAvgPool2D](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/nn/AdaptiveAvgPool2D_cn.html#paddle/nn/AdaptiveAvgPool2D_cn#cn-api-paddle-nn-AdaptiveAvgPool2D)
+
+```python
+paddle.nn.AdaptiveAvgPool2D(output_size, data_format="NCHW", name=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+model = torch.nn.AdaptiveAvgPool2d(5)
+
+# Paddle 写法
+model = paddle.nn.AdaptiveAvgPool2D(5)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.AdaptiveAvgPool3d.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.AdaptiveAvgPool3d.md
new file mode 100644
index 00000000000..d60017ce4e4
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.AdaptiveAvgPool3d.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.nn.AdaptiveAvgPool3d
+
+### [torch.nn.AdaptiveAvgPool3d](https://pytorch.org/docs/stable/generated/torch.nn.AdaptiveAvgPool3d.html#torch.nn.AdaptiveAvgPool3d)
+
+```python
+torch.nn.AdaptiveAvgPool3d(output_size)
+```
+
+### [paddle.nn.AdaptiveAvgPool3D](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/nn/AdaptiveAvgPool3D_cn.html#paddle/nn/AdaptiveAvgPool3D_cn#cn-api-paddle-nn-AdaptiveAvgPool3D)
+
+```python
+paddle.nn.AdaptiveAvgPool3D(output_size, data_format="NCDHW", name=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+model = torch.nn.AdaptiveAvgPool3d(1)
+
+# Paddle 写法
+model = paddle.nn.AdaptiveAvgPool3D(1)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.nn.HuberLoss.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.HuberLoss.md
similarity index 54%
rename from docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.nn.HuberLoss.md
rename to docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.HuberLoss.md
index 0d9bf858ff6..50016a891a6 100644
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.nn.HuberLoss.md
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.HuberLoss.md
@@ -1,12 +1,25 @@
 ## [ 仅 API 调用方式不一致 ]torch.nn.HuberLoss
+
 ### [torch.nn.HuberLoss](https://pytorch.org/docs/stable/generated/torch.nn.HuberLoss.html#torch.nn.HuberLoss)
+
 ```python
 torch.nn.HuberLoss(reduction='mean', delta=1.0)
 ```
 
-### [paddle.nn.SmoothL1Loss](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/nn/SmoothL1Loss_cn.html)
+### [paddle.nn.SmoothL1Loss](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/nn/SmoothL1Loss_cn.html#paddle/nn/SmoothL1Loss_cn#cn-api-paddle-nn-SmoothL1Loss)
+
 ```python
 paddle.nn.SmoothL1Loss(reduction='mean', delta=1.0, name=None)
 ```
 
-功能一致，参数完全一致，具体如下：
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+loss = torch.nn.HuberLoss()
+
+# Paddle 写法
+loss = paddle.nn.SmoothL1Loss()
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.MaxUnpool1d.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.MaxUnpool1d.md
new file mode 100644
index 00000000000..0730bfdd975
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.MaxUnpool1d.md
@@ -0,0 +1,24 @@
+## [ 仅 API 调用方式不一致 ]torch.nn.MaxUnpool1d
+
+### [torch.nn.MaxUnpool1d](https://pytorch.org/docs/stable/generated/torch.nn.MaxUnpool1d.html#torch.nn.MaxUnpool1d)
+
+```python
+torch.nn.MaxUnpool1d(kernel_size, stride=None, padding=0)
+```
+
+### [paddle.nn.MaxUnPool1D](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/nn/MaxUnPool1D_cn.html#paddle/nn/MaxUnPool1D_cn#cn-api-paddle-nn-MaxUnPool1D)
+
+```python
+paddle.nn.MaxUnPool1D(kernel_size, stride=None, padding=0, data_format='NCL', output_size=None, name=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+unpool = torch.nn.MaxUnpool1d(2, 2)
+# Paddle 写法)
+unpool = paddle.nn.MaxUnPool1D(2, 2)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.MaxUnpool2d.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.MaxUnpool2d.md
new file mode 100644
index 00000000000..b6341ca64d9
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.MaxUnpool2d.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.nn.MaxUnpool2d
+
+### [torch.nn.MaxUnpool2d](https://pytorch.org/docs/stable/generated/torch.nn.MaxUnpool2d.html#torch.nn.MaxUnpool2d)
+
+```python
+torch.nn.MaxUnpool2d(kernel_size, stride=None, padding=0)
+```
+
+### [paddle.nn.MaxUnPool2D](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/nn/MaxUnPool2D_cn.html#paddle/nn/MaxUnPool2D_cn#cn-api-paddle-nn-MaxUnPool2D)
+
+```python
+paddle.nn.MaxUnPool2D(kernel_size, stride=None, padding=0, data_format='NCHW', output_size=None, name=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+unpool = torch.nn.MaxUnpool2d(2, stride=2)
+
+# Paddle 写法
+unpool = paddle.nn.MaxUnPool2D(2, stride=2)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.MaxUnpool3d.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.MaxUnpool3d.md
new file mode 100644
index 00000000000..7e6080d9417
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.MaxUnpool3d.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.nn.MaxUnpool3d
+
+### [torch.nn.MaxUnpool3d](https://pytorch.org/docs/stable/generated/torch.nn.MaxUnpool3d.html#torch.nn.MaxUnpool3d)
+
+```python
+torch.nn.MaxUnpool3d(kernel_size, stride=None, padding=0)
+```
+
+### [paddle.nn.MaxUnPool3D](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/nn/MaxUnPool3D_cn.html#paddle/nn/MaxUnPool3D_cn#cn-api-paddle-nn-MaxUnPool3D)
+
+```python
+paddle.nn.MaxUnPool3D(kernel_size, stride=None, padding=0, data_format='NCDHW', output_size=None, name=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+unpool = torch.nn.MaxUnpool3d(3, stride=2)
+
+# Paddle 写法
+unpool = paddle.nn.MaxUnPool3D(3, stride=2)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.Module.apply.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.Module.apply.md
new file mode 100644
index 00000000000..caa662004a4
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.Module.apply.md
@@ -0,0 +1,36 @@
+## [ 仅 API 调用方式不一致 ]torch.nn.Module.apply
+
+### [torch.nn.Module.apply](https://pytorch.org/docs/stable/generated/torch.nn.Module.html#torch.nn.Module.apply)
+
+```python
+torch.nn.Module.apply(fn)
+```
+
+### [paddle.nn.Layer.apply](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/nn/Layer/apply_cn.html#paddle/nn/Layer/apply_cn#cn-api-paddle-nn-Layer-apply)
+
+```python
+paddle.nn.Layer.apply(fn)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+def init_weights(m):
+    pass
+net = torch.nn.Sequential(
+    torch.nn.Linear(2, 2, bias=False), torch.nn.Linear(2, 2, bias=False)
+)
+net.apply(init_weights)
+
+# Paddle 写法
+def init_weights(m):
+    pass
+net = paddle.nn.Sequential(
+    paddle.nn.Linear(in_features=2, out_features=2, bias_attr=False),
+    paddle.nn.Linear(in_features=2, out_features=2, bias_attr=False),
+)
+net.apply(init_weights)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.Module.children.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.Module.children.md
new file mode 100644
index 00000000000..7a045d52274
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.Module.children.md
@@ -0,0 +1,29 @@
+## [ 仅 API 调用方式不一致 ]torch.nn.Module.children
+
+### [torch.nn.Module.children](https://pytorch.org/docs/stable/generated/torch.nn.Module.html#torch.nn.Module.children)
+
+```python
+torch.nn.Module.children()
+```
+
+### [paddle.nn.Layer.children](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/nn/Layer/children_cn.html#paddle/nn/Layer/children_cn#cn-api-paddle-nn-Layer-children)
+
+```python
+paddle.nn.Layer.children()
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+model = torch.nn.Sequential(net1, net2)
+for layer in model.children():
+    print(layer)
+
+# Paddle 写法
+model = paddle.nn.Sequential(net1, net2)
+for layer in model.children():
+    print(layer)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.Module.eval.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.Module.eval.md
new file mode 100644
index 00000000000..1f3a502ef15
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.Module.eval.md
@@ -0,0 +1,27 @@
+## [ 仅 API 调用方式不一致 ]torch.nn.Module.eval
+
+### [torch.nn.Module.eval](https://pytorch.org/docs/stable/generated/torch.nn.Module.html#torch.nn.Module.eval)
+
+```python
+torch.nn.Module.eval()
+```
+
+### [paddle.nn.Layer.eval](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/nn/Layer/eval_cn.html#paddle/nn/Layer/eval_cn#cn-api-paddle-nn-Layer-eval)
+
+```python
+paddle.nn.Layer.eval()
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+model = torch.nn.Linear(10, 10)
+model.eval()
+
+# Paddle 写法
+model = paddle.nn.Linear(10, 10)
+model.eval()
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.Module.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.Module.md
new file mode 100644
index 00000000000..658d27804d3
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.Module.md
@@ -0,0 +1,45 @@
+## [ 仅 API 调用方式不一致 ]torch.nn.Module
+
+### [torch.nn.Module](https://pytorch.org/docs/stable/generated/torch.nn.Module.html)
+
+```python
+torch.nn.Module(*args, **kwargs)
+```
+
+### [paddle.nn.Layer](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/nn/Layer_cn.html#paddle/nn/Layer_cn#cn-api-paddle-nn-Layer)
+
+```python
+paddle.nn.Layer(name_scope=None, dtype='float32')
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+class MLP(torch.nn.Module):
+    def __init__(self, input_size, hidden_size, output_size):
+        super(MLP, self).__init__()
+        self.fc1 = torch.nn.Linear(input_size, hidden_size)
+        with torch.no_grad():
+            self.fc1.weight.fill_(1.0)
+            self.fc1.bias.fill_(0.1)
+
+    def forward(self, x):
+        x = self.fc1(x)
+        return x
+
+# Paddle 写法
+class MLP(paddle.nn.Layer):
+    def __init__(self, input_size, hidden_size, output_size):
+        super(MLP, self).__init__()
+        self.fc1 = paddle.nn.Linear(in_features=input_size, out_features=hidden_size)
+        with paddle.no_grad():
+            self.fc1.weight.fill_(1.0)
+            self.fc1.bias.fill_(0.1)
+
+    def forward(self, x):
+        x = self.fc1(x)
+        return x
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.Module.modules.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.Module.modules.md
new file mode 100644
index 00000000000..3e0dd9bb523
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.Module.modules.md
@@ -0,0 +1,29 @@
+## [ 仅 API 调用方式不一致 ]torch.nn.Module.modules
+
+### [torch.nn.Module.modules](https://pytorch.org/docs/stable/generated/torch.nn.Module.html#torch.nn.Module.modules)
+
+```python
+torch.nn.Module.modules()
+```
+
+### [paddle.nn.Layer.sublayers](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/nn/Layer/sublayers_cn.html#paddle/nn/Layer/sublayers_cn#cn-api-paddle-nn-Layer-sublayers)
+
+```python
+paddle.nn.Layer.sublayers(include_self=False)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+model = torch.nn.Sequential(net1, net2)
+for layer in model.modules():
+    print(layer)
+
+# Paddle 写法
+model = paddle.nn.Sequential(net1, net2)
+for layer in model.sublayers():
+    print(layer)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.Module.named_children.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.Module.named_children.md
new file mode 100644
index 00000000000..b63dbef1d97
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.Module.named_children.md
@@ -0,0 +1,29 @@
+## [ 仅 API 调用方式不一致 ]torch.nn.Module.named_children
+
+### [torch.nn.Module.named_children](https://pytorch.org/docs/stable/generated/torch.nn.Module.html#torch.nn.Module.named_children)
+
+```python
+torch.nn.Module.named_children()
+```
+
+### [paddle.nn.Layer.named_children](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/nn/Layer/named_children_cn.html#paddle/nn/Layer/named_children_cn#cn-api-paddle-nn-Layer-named_children)
+
+```python
+paddle.nn.Layer.named_children()
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+model = torch.nn.Sequential(OrderedDict([("wfs", l), ("wfs1", l1)]))
+for name, module in model.named_children():
+    print(name, module)
+
+# Paddle 写法
+model = paddle.nn.Sequential(OrderedDict([("wfs", l), ("wfs1", l1)]))
+for name, module in model.named_children():
+    print(name, module)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.Module.train.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.Module.train.md
new file mode 100644
index 00000000000..03f832fdfb6
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.Module.train.md
@@ -0,0 +1,27 @@
+## [ 仅 API 调用方式不一致 ]torch.nn.Module.train
+
+### [torch.nn.Module.train](https://pytorch.org/docs/stable/generated/torch.nn.Module.html#torch.nn.Module.train)
+
+```python
+torch.nn.Module.train(mode=True)
+```
+
+### [paddle.nn.Layer.train](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/nn/Layer/train_cn.html#paddle/nn/Layer/train_cn#cn-api-paddle-nn-Layer-train)
+
+```python
+paddle.nn.Layer.train()
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+model = torch.nn.Linear(10, 20)
+model.train()
+
+# Paddle 写法
+model = paddle.nn.Linear(10, 20)
+model.train()
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.UpsamplingBilinear2d.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.UpsamplingBilinear2d.md
new file mode 100644
index 00000000000..5370178305b
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.UpsamplingBilinear2d.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.nn.UpsamplingBilinear2d
+
+### [torch.nn.UpsamplingBilinear2d](https://pytorch.org/docs/stable/generated/torch.nn.UpsamplingBilinear2d.html#torch.nn.UpsamplingBilinear2d)
+
+```python
+torch.nn.UpsamplingBilinear2d(size=None, scale_factor=None)
+```
+
+### [paddle.nn.UpsamplingBilinear2D](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/nn/UpsamplingBilinear2D_cn.html#paddle/nn/UpsamplingBilinear2D_cn#cn-api-paddle-nn-UpsamplingBilinear2D)
+
+```python
+paddle.nn.UpsamplingBilinear2D(size=None, scale_factor=None, data_format='NCHW', name=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+model = torch.nn.UpsamplingBilinear2d(scale_factor=2)
+
+# Paddle 写法
+model = paddle.nn.UpsamplingBilinear2D(scale_factor=2)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.UpsamplingNearest2d.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.UpsamplingNearest2d.md
new file mode 100644
index 00000000000..59903f373e1
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.UpsamplingNearest2d.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.nn.UpsamplingNearest2d
+
+### [torch.nn.UpsamplingNearest2d](https://pytorch.org/docs/stable/generated/torch.nn.UpsamplingNearest2d.html#torch.nn.UpsamplingNearest2d)
+
+```python
+torch.nn.UpsamplingNearest2d(size=None, scale_factor=None)
+```
+
+### [paddle.nn.UpsamplingNearest2D](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/nn/UpsamplingNearest2D_cn.html#paddle/nn/UpsamplingNearest2D_cn#cn-api-paddle-nn-UpsamplingNearest2D)
+
+```python
+paddle.nn.UpsamplingNearest2D(size=None, scale_factor=None, data_format='NCHW', name=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+model = torch.nn.UpsamplingNearest2d(scale_factor=2)
+
+# Paddle 写法
+model = paddle.nn.UpsamplingNearest2D(scale_factor=2)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.ZeroPad2d.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.ZeroPad2d.md
new file mode 100644
index 00000000000..74f3177ddca
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.nn.ZeroPad2d.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.nn.ZeroPad2d
+
+### [torch.nn.ZeroPad2d](https://pytorch.org/docs/stable/generated/torch.nn.ZeroPad2d.html#torch.nn.ZeroPad2d)
+
+```python
+torch.nn.ZeroPad2d(padding)
+```
+
+### [paddle.nn.ZeroPad2D](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/nn/ZeroPad2D_cn.html#paddle/nn/ZeroPad2D_cn#cn-api-paddle-nn-ZeroPad2D)
+
+```python
+paddle.nn.ZeroPad2D(padding, data_format='NCHW', name=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+model = torch.nn.ZeroPad2d(1)
+
+# Paddle 写法
+model = paddle.nn.ZeroPad2D(1)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.numel.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.numel.md
similarity index 57%
rename from docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.numel.md
rename to docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.numel.md
index 0ba0c9a7736..65083702ccd 100644
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.numel.md
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.numel.md
@@ -1,21 +1,25 @@
 ## [ 仅 API 调用方式不一致 ]torch.numel
-### [torch.numel](https://pytorch.org/docs/stable/generated/torch.numel.html?highlight=numel#torch.numel)
+
+### [torch.numel](https://pytorch.org/docs/stable/generated/torch.numel.html)
+
 ```python
 torch.numel(input)
 ```
 
-### [paddle.Tensor.size](https://www.paddlepaddle.org.cn/documentation/docs/guides/beginner/tensor_cn.html#tensor-shape)
+### [paddle.Tensor.size](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor/size_cn.html#paddle/Tensor/size_cn#cn-api-paddle-Tensor-size)
+
 ```python
 paddle.Tensor.size
 ```
 
-两者功能一致，均无参数。
+两者功能一致，但调用方式不一致，具体如下：
 
 ### 转写示例
+
 ```python
 # PyTorch 写法
-torch.numel(x)
+result = torch.numel(a)
 
 # Paddle 写法
-x.size
+result = a.size
 ```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.optim.Optimizer.state_dict.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.optim.Optimizer.state_dict.md
new file mode 100644
index 00000000000..bffa352b1c8
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.optim.Optimizer.state_dict.md
@@ -0,0 +1,27 @@
+## [ 仅 API 调用方式不一致 ]torch.optim.Optimizer.state_dict
+
+### [torch.optim.Optimizer.state_dict](https://pytorch.org/docs/stable/generated/torch.optim.Optimizer.html#torch.optim.Optimizer.state_dict)
+
+```python
+torch.optim.Optimizer.state_dict()
+```
+
+### [paddle.optimizer.Optimizer.state_dict](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/optimizer/Optimizer/state_dict_cn.html#paddle/optimizer/Optimizer/state_dict_cn#cn-api-paddle-optimizer-Optimizer-state_dict)
+
+```python
+paddle.optimizer.Optimizer.state_dict()
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+optim = torch.optim.Optimizer([theta], defaults={"learning_rate": 1.0})
+result = optim.state_dict()
+
+# Paddle 写法
+optim = paddle.optimizer.Optimizer(parameters=[theta], **{"learning_rate": 1.0})
+result = optim.state_dict()
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.optim.Optimizer.step.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.optim.Optimizer.step.md
new file mode 100644
index 00000000000..f5fb40e2917
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.optim.Optimizer.step.md
@@ -0,0 +1,35 @@
+## [ 仅 API 调用方式不一致 ]torch.optim.Optimizer.step
+
+### [torch.optim.Optimizer.step](https://pytorch.org/docs/stable/generated/torch.optim.Optimizer.html#torch.optim.Optimizer.step)
+
+```python
+torch.optim.Optimizer.step(closure=None)
+```
+
+### [paddle.optimizer.Optimizer.step](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/optimizer/Optimizer/step_cn.html#paddle/optimizer/Optimizer/step_cn#cn-api-paddle-optimizer-Optimizer-step)
+
+```python
+paddle.optimizer.Optimizer.step()
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+sgd = torch.optim.SGD(
+    params=linear.parameters(),
+    lr=0.1,
+    weight_decay=0.01
+)
+sgd.step()
+
+# Paddle 写法
+sgd = paddle.optimizer.SGD(
+     learning_rate=0.1,
+     parameters=linear.parameters(),
+     weight_decay=0.01
+)
+sgd.step()
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.utils.data.ChainDataset.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.utils.data.ChainDataset.md
new file mode 100644
index 00000000000..43fca687c27
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.utils.data.ChainDataset.md
@@ -0,0 +1,29 @@
+## [ 仅 API 调用方式不一致 ]torch.utils.data.ChainDataset
+
+### [torch.utils.data.ChainDataset](https://pytorch.org/docs/stable/generated/torch.utils.data.ChainDataset.html#torch.utils.data.ChainDataset)
+
+```python
+torch.utils.data.ChainDataset(datasets)
+```
+
+### [paddle.io.ChainDataset](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/io/ChainDataset_cn.html#paddle/io/ChainDataset_cn#cn-api-paddle-io-ChainDataset)
+
+```python
+paddle.io.ChainDataset(datasets)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+dataset = torch.utils.data.ChainDataset(
+    [MyIterableDataset(start=3, end=7), MyIterableDataset(start=3, end=7)]
+)
+
+# Paddle 写法
+dataset = paddle.io.ChainDataset(
+    [MyIterableDataset(start=3, end=7), MyIterableDataset(start=3, end=7)]
+)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.utils.data.ConcatDataset.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.utils.data.ConcatDataset.md
new file mode 100644
index 00000000000..165bb7e8a2f
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.utils.data.ConcatDataset.md
@@ -0,0 +1,26 @@
+## [ 仅 API 调用方式不一致 ]torch.utils.data.ConcatDataset
+
+### [torch.utils.data.ConcatDataset](https://pytorch.org/docs/stable/generated/torch.utils.data.ConcatDataset.html#torch.utils.data.ConcatDataset)
+
+```python
+torch.utils.data.ConcatDataset(datasets)
+```
+
+### [paddle.io.ConcatDataset](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/io/ConcatDataset_cn.html#paddle/io/ConcatDataset_cn#cn-api-paddle-io-ConcatDataset)
+
+```python
+paddle.io.ConcatDataset(datasets)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+dataset = torch.utils.data.ConcatDataset([RandomDataset(2), RandomDataset(2)])
+
+# Paddle 写法
+dataset = paddle.io.ConcatDataset([RandomDataset(2), RandomDataset(2)])
+
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.utils.data.Dataset.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.utils.data.Dataset.md
new file mode 100644
index 00000000000..ebefc5954f6
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.utils.data.Dataset.md
@@ -0,0 +1,41 @@
+## [ 仅 API 调用方式不一致 ]torch.utils.data.Dataset
+
+### [torch.utils.data.Dataset](https://pytorch.org/docs/stable/generated/torch.utils.data.Dataset.html#torch.utils.data.Dataset)
+
+```python
+torch.utils.data.Dataset(*args, **kwargs)
+```
+
+### [paddle.io.Dataset](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/io/Dataset_cn.html#paddle/io/Dataset_cn#cn-api-paddle-io-Dataset)
+
+```python
+paddle.io.Dataset()
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+class Data(torch.utils.data.Dataset):
+    def __init__(self):
+        self.x = [1, 2, 3, 4]
+
+    def __getitem__(self, idx):
+        return self.x[idx]
+
+    def __len__(self):
+        return len(self.x)
+
+# Paddle 写法
+class Data(paddle.io.Dataset):
+    def __init__(self):
+        self.x = [1, 2, 3, 4]
+
+    def __getitem__(self, idx):
+        return self.x[idx]
+
+    def __len__(self):
+        return len(self.x)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.utils.data.IterableDataset.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.utils.data.IterableDataset.md
new file mode 100644
index 00000000000..372cde708ba
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.utils.data.IterableDataset.md
@@ -0,0 +1,39 @@
+## [ 仅 API 调用方式不一致 ]torch.utils.data.IterableDataset
+
+### [torch.utils.data.IterableDataset](https://pytorch.org/docs/stable/generated/torch.utils.data.IterableDataset.html#torch.utils.data.IterableDataset)
+
+```python
+torch.utils.data.IterableDataset(*args, **kwargs)
+```
+
+### [paddle.io.IterableDataset](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/io/IterableDataset_cn.html#paddle/io/IterableDataset_cn#cn-api-paddle-io-IterableDataset)
+
+```python
+paddle.io.IterableDataset()
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+class MyIterableDataset(torch.utils.data.IterableDataset):
+    def __init__(self, start, end):
+        super(MyIterableDataset).__init__()
+        self.start = start
+        self.end = end
+
+    def __iter__(self):
+        return iter(range(self.start, self.end))
+
+# Paddle 写法
+class MyIterableDataset(paddle.io.IterableDataset):
+    def __init__(self, start, end):
+        super(MyIterableDataset).__init__()
+        self.start = start
+        self.end = end
+
+    def __iter__(self):
+        return iter(range(self.start, self.end))
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.utils.data.Sampler.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.utils.data.Sampler.md
new file mode 100644
index 00000000000..066473e4f04
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.utils.data.Sampler.md
@@ -0,0 +1,41 @@
+## [ 仅 API 调用方式不一致 ]torch.utils.data.Sampler
+
+### [torch.utils.data.Sampler](https://pytorch.org/docs/stable/generated/torch.utils.data.Sampler.html#torch.utils.data.Sampler)
+
+```python
+torch.utils.data.Sampler(data_source)
+```
+
+### [paddle.io.Sampler](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/io/Sampler_cn.html#paddle/io/Sampler_cn#cn-api-paddle-io-Sampler)
+
+```python
+paddle.io.Sampler(data_source)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+class MySampler(torch.utils.data.Sampler):
+    def __init__(self, data_source):
+        self.data_source = data_source
+
+    def __iter__(self):
+        return iter(range(len(self.data_source)))
+
+    def __len__(self):
+        return len(self.data_source)
+
+# Paddle 写法
+class MySampler(paddle.io.Sampler):
+    def __init__(self, data_source):
+        super().__init__(data_source)
+
+    def __iter__(self):
+        return iter(range(len(self.data_source)))
+
+    def __len__(self):
+        return len(self.data_source)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.utils.data.SequentialSampler.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.utils.data.SequentialSampler.md
new file mode 100644
index 00000000000..9234427586d
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.utils.data.SequentialSampler.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.utils.data.SequentialSampler
+
+### [torch.utils.data.SequentialSampler](https://pytorch.org/docs/stable/generated/torch.utils.data.SequentialSampler.html#torch.utils.data.SequentialSampler)
+
+```python
+torch.utils.data.SequentialSampler(data_source)
+```
+
+### [paddle.io.SequenceSampler](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/io/SequenceSampler_cn.html#paddle/io/SequenceSampler_cn#cn-api-paddle-io-SequenceSampler)
+
+```python
+paddle.io.SequenceSampler(data_source)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+s = torch.utils.data.SequentialSampler(MyDataset())
+
+# Paddle 写法
+s = paddle.io.SequenceSampler(MyDataset())
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.utils.data.Subset.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.utils.data.Subset.md
new file mode 100644
index 00000000000..801d7052421
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.utils.data.Subset.md
@@ -0,0 +1,26 @@
+## [ 仅 API 调用方式不一致 ]torch.utils.data.Subset
+
+### [torch.utils.data.Subset](https://pytorch.org/docs/stable/generated/torch.utils.data.Subset.html#torch.utils.data.Subset)
+
+```python
+torch.utils.data.Subset(dataset, indices)
+```
+
+### [paddle.io.Subset](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/io/Subset_cn.html#paddle/io/Subset_cn#cn-api-paddle-io-Subset)
+
+```python
+paddle.io.Subset(dataset, indices)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+subset = torch.utils.data.Subset(full_dataset, indices)
+
+# Paddle 写法
+subset = paddle.io.Subset(full_dataset, indices)
+
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.utils.data.default_collate.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.utils.data.default_collate.md
new file mode 100644
index 00000000000..84a8356c7a5
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.utils.data.default_collate.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torch.utils.data.default_collate
+
+### [torch.utils.data.default_collate](https://pytorch.org/docs/stable/data.html#torch.utils.data.default_collate)
+
+```python
+torch.utils.data.default_collate(batch)
+```
+
+### [paddle.io.dataloader.collate.default_collate_fn](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/io/dataloader/collate/default_collate_fn_cn.html#paddle/io/dataloader/collate/default_collate_fn_cn#cn-api-paddle-io-dataloader-collate-default_collate_fn)
+
+```python
+paddle.io.dataloader.collate.default_collate_fn(batch)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = torch.tensor(torch.utils.data.default_collate([0, 1, 2, 3]))
+
+# Paddle 写法
+result = paddle.tensor(paddle.io.dataloader.collate.default_collate_fn([0, 1, 2, 3]))
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.utils.data.get_worker_info.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.utils.data.get_worker_info.md
similarity index 58%
rename from docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.utils.data.get_worker_info.md
rename to docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.utils.data.get_worker_info.md
index 56909bc0fc7..a695367ccdb 100644
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_diff_only/torch.utils.data.get_worker_info.md
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.utils.data.get_worker_info.md
@@ -1,12 +1,25 @@
 ## [ 仅 API 调用方式不一致 ]torch.utils.data.get_worker_info
+
 ### [torch.utils.data.get_worker_info](https://pytorch.org/docs/stable/data.html#torch.utils.data.get_worker_info)
+
 ```python
 torch.utils.data.get_worker_info()
 ```
 
-### [paddle.io.get_worker_info](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/io/get_worker_info_cn.html#get-worker-info)
+### [paddle.io.get_worker_info](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/io/get_worker_info_cn.html#paddle/io/get_worker_info_cn#cn-api-paddle-io-get_worker_info)
+
 ```python
 paddle.io.get_worker_info()
 ```
 
-两者功能一致，无参数。
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = torch.utils.data.get_worker_info()
+
+# Paddle 写法
+result = paddle.io.get_worker_info()
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.utils.data.random_split.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.utils.data.random_split.md
new file mode 100644
index 00000000000..5fb5d3c2c87
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torch.utils.data.random_split.md
@@ -0,0 +1,47 @@
+## [ 仅 API 调用方式不一致 ]torch.utils.data.random_split
+
+### [torch.utils.data.random_split](https://pytorch.org/docs/stable/data.html#torch.utils.data.random_split)
+
+```python
+torch.utils.data.random_split(dataset, lengths, generator=<torch._C.Generator object>)
+```
+
+### [paddle.io.random_split](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/io/random_split_cn.html#paddle/io/random_split_cn#cn-api-paddle-io-random_split)
+
+```python
+paddle.io.random_split(dataset, lengths, generator=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+class Data(torch.utils.data.Dataset):
+    def __init__(self):
+        self.x = [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]
+
+    def __getitem__(self, idx):
+        return self.x[idx]
+
+    def __len__(self):
+        return len(self.x)
+
+data = Data()
+datasets = torch.utils.data.random_split(data, [3, 7])
+
+# Paddle 写法
+class Data(paddle.io.Dataset):
+    def __init__(self):
+        self.x = [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]
+
+    def __getitem__(self, idx):
+        return self.x[idx]
+
+    def __len__(self):
+        return len(self.x)
+
+data = Data()
+datasets = paddle.io.random_split(data, [3, 7])
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.ops.RoIPool.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.ops.RoIPool.md
new file mode 100644
index 00000000000..6f181526018
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.ops.RoIPool.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torchvision.ops.RoIPool
+
+### [torchvision.ops.RoIPool](https://pytorch.org/vision/stable/generated/torchvision.ops.RoIPool.html#torchvision.ops.RoIPool)
+
+```python
+torchvision.ops.RoIPool(output_size, spatial_scale)
+```
+
+### [paddle.vision.ops.RoIPool](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/ops/RoIPool_cn.html#paddle/vision/ops/RoIPool_cn#cn-api-paddle-vision-ops-RoIPool)
+
+```python
+paddle.vision.ops.RoIPool(output_size, spatial_scale)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+roi_pool = torchvision.ops.RoIPool(output_size=(7, 7), spatial_scale=1.0)
+
+# Paddle 写法
+roi_pool = paddle.vision.ops.RoIPool(output_size=(7, 7), spatial_scale=1.0)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.CenterCrop.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.CenterCrop.md
new file mode 100644
index 00000000000..5881987e631
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.CenterCrop.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torchvision.transforms.CenterCrop
+
+### [torchvision.transforms.CenterCrop](https://pytorch.org/vision/stable/generated/torchvision.transforms.CenterCrop.html#torchvision.transforms.CenterCrop)
+
+```python
+torchvision.transforms.CenterCrop(size)
+```
+
+### [paddle.vision.transforms.CenterCrop](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/CenterCrop_cn.html#paddle/vision/transforms/CenterCrop_cn#cn-api-paddle-vision-transforms-CenterCrop)
+
+```python
+paddle.vision.transforms.CenterCrop(size, keys=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+center_crop = torchvision.transforms.CenterCrop(size)
+
+# Paddle 写法
+center_crop = paddle.vision.transforms.CenterCrop(size)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.ColorJitter.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.ColorJitter.md
new file mode 100644
index 00000000000..994c551eb2b
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.ColorJitter.md
@@ -0,0 +1,29 @@
+## [ 仅 API 调用方式不一致 ]torchvision.transforms.ColorJitter
+
+### [torchvision.transforms.ColorJitter](https://pytorch.org/vision/stable/generated/torchvision.transforms.ColorJitter.html#torchvision.transforms.ColorJitter)
+
+```python
+torchvision.transforms.ColorJitter(brightness=0, contrast=0, saturation=0, hue=0)
+```
+
+### [paddle.vision.transforms.ColorJitter](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/ColorJitter_cn.html#paddle/vision/transforms/ColorJitter_cn#cn-api-paddle-vision-transforms-ColorJitter)
+
+```python
+paddle.vision.transforms.ColorJitter(brightness=0, contrast=0, saturation=0, hue=0, keys=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+jitter = torchvision.transforms.ColorJitter(
+    brightness=0.2, contrast=0.3, saturation=0.4, hue=0
+)
+
+# Paddle 写法
+jitter = paddle.vision.transforms.ColorJitter(
+    brightness=0.2, contrast=0.3, saturation=0.4, hue=0
+)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.Compose.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.Compose.md
new file mode 100644
index 00000000000..2c48df0ad73
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.Compose.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torchvision.transforms.Compose
+
+### [torchvision.transforms.Compose](https://pytorch.org/vision/stable/generated/torchvision.transforms.Compose.html#torchvision.transforms.Compose)
+
+```python
+torchvision.transforms.Compose(transforms)
+```
+
+### [paddle.vision.transforms.Compose](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/Compose_cn.html#paddle/vision/transforms/Compose_cn#cn-api-paddle-vision-transforms-Compose)
+
+```python
+paddle.vision.transforms.Compose(transforms)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+composed = torchvision.transforms.Compose(transforms=process)
+
+# Paddle 写法
+composed = paddle.vision.transforms.Compose(transforms=process)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.Grayscale.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.Grayscale.md
new file mode 100644
index 00000000000..cc5bc51ef2e
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.Grayscale.md
@@ -0,0 +1,34 @@
+## [ 仅 API 调用方式不一致 ]torchvision.transforms.Grayscale
+
+### [torchvision.transforms.Grayscale](https://pytorch.org/vision/stable/generated/torchvision.transforms.Grayscale.html#torchvision.transforms.Grayscale)
+
+```python
+torchvision.transforms.Grayscale(num_output_channels)
+```
+
+### [paddle.vision.transforms.Grayscale](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/Grayscale_cn.html#paddle/vision/transforms/Grayscale_cn#cn-api-paddle-vision-transforms-Grayscale)
+
+```python
+paddle.vision.transforms.Grayscale(num_output_channels, keys=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+grayscale = torchvision.transforms.Grayscale(num_output_channels=1)
+img = torch.tensor(
+    [[[0.2, 0.4], [0.6, 0.8]], [[0.1, 0.3], [0.5, 0.7]], [[0.0, 0.2], [0.4, 0.6]]]
+)
+result = grayscale(img)
+
+# Paddle 写法
+grayscale = paddle.vision.transforms.Grayscale(num_output_channels=1)
+img = paddle.tensor(
+    [[[0.2, 0.4], [0.6, 0.8]], [[0.1, 0.3], [0.5, 0.7]], [[0.0, 0.2], [0.4, 0.6]]]
+)
+result = grayscale(img)
+
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.Pad.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.Pad.md
new file mode 100644
index 00000000000..fe20efb57ec
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.Pad.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torchvision.transforms.Pad
+
+### [torchvision.transforms.Pad](https://pytorch.org/vision/stable/generated/torchvision.transforms.Pad.html#torchvision.transforms.Pad)
+
+```python
+torchvision.transforms.Pad(padding, fill=0, padding_mode='constant')
+```
+
+### [paddle.vision.transforms.Pad](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/Pad_cn.html#paddle/vision/transforms/Pad_cn#cn-api-paddle-vision-transforms-Pad)
+
+```python
+paddle.vision.transforms.Pad(padding, fill=0, padding_mode='constant', keys=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+pad = torchvision.transforms.Pad(padding=2, fill=0, padding_mode="constant")
+
+# Paddle 写法
+pad = paddle.vision.transforms.Pad(padding=2, fill=0, padding_mode="constant")
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.RandomAffine.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.RandomAffine.md
new file mode 100644
index 00000000000..b19b6652864
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.RandomAffine.md
@@ -0,0 +1,42 @@
+## [ 仅 API 调用方式不一致 ]torchvision.transforms.RandomAffine
+
+### [torchvision.transforms.RandomAffine](https://pytorch.org/vision/stable/generated/torchvision.transforms.RandomAffine.html#torchvision.transforms.RandomAffine)
+
+```python
+torchvision.transforms.RandomAffine(degrees, translate=None, scale=None, shear=None, interpolation=torchvision.transforms.InterpolationMode.InterpolationMode.NEAREST, fill=0, center=None)
+```
+
+### [paddle.vision.transforms.RandomAffine](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/RandomAffine_cn.html#paddle/vision/transforms/RandomAffine_cn#cn-api-paddle-vision-transforms-RandomAffine)
+
+```python
+paddle.vision.transforms.RandomAffine(degrees, translate=None, scale=None, shear=None, interpolation='nearest', fill=0, center=None, keys=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+transform = torchvision.transforms.RandomAffine(
+    45,
+    (0.1, 0.1),
+    (0.5, 1.5),
+    20,
+    torchvision.transforms.InterpolationMode.BILINEAR,
+    255,
+    (2, 2),
+)
+
+# Paddle 写法
+transform = paddle.vision.transforms.RandomAffine(
+    45,
+    (0.1, 0.1),
+    (0.5, 1.5),
+    20,
+    "bilinear",
+    255,
+    (2, 2)
+)
+
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.RandomCrop.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.RandomCrop.md
new file mode 100644
index 00000000000..d5b43068a85
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.RandomCrop.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torchvision.transforms.RandomCrop
+
+### [torchvision.transforms.RandomCrop](https://pytorch.org/vision/stable/generated/torchvision.transforms.RandomCrop.html#torchvision.transforms.RandomCrop)
+
+```python
+torchvision.transforms.RandomCrop(size, padding=None, pad_if_needed=False, fill=0, padding_mode='constant')
+```
+
+### [paddle.vision.transforms.RandomCrop](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/RandomCrop_cn.html#paddle/vision/transforms/RandomCrop_cn#cn-api-paddle-vision-transforms-RandomCrop)
+
+```python
+paddle.vision.transforms.RandomCrop(size, padding=None, pad_if_needed=False, fill=0, padding_mode='constant', keys=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+crop = torchvision.transforms.RandomCrop(size=size)
+
+# Paddle 写法
+crop = paddle.vision.transforms.RandomCrop(size=size)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.RandomRotation.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.RandomRotation.md
new file mode 100644
index 00000000000..129421d6a51
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.RandomRotation.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torchvision.transforms.RandomRotation
+
+### [torchvision.transforms.RandomRotation](https://pytorch.org/vision/stable/generated/torchvision.transforms.RandomRotation.html#torchvision.transforms.RandomRotation)
+
+```python
+torchvision.transforms.RandomRotation(degrees, interpolation=torchvision.transforms.InterpolationMode.NEAREST, expand=False, center=None, fill=0)
+```
+
+### [paddle.vision.transforms.RandomRotation](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/RandomRotation_cn.html#paddle/vision/transforms/RandomRotation_cn#cn-api-paddle-vision-transforms-RandomRotation)
+
+```python
+paddle.vision.transforms.RandomRotation(degrees, interpolation='nearest', expand=False, center=None, fill=0, keys=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+rotation = torchvision.transforms.RandomRotation(degrees=degrees)
+
+# Paddle 写法
+rotation = paddle.vision.transforms.RandomRotation(degrees=degrees)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.ToTensor.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.ToTensor.md
new file mode 100644
index 00000000000..9542515129e
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.ToTensor.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torchvision.transforms.ToTensor
+
+### [torchvision.transforms.ToTensor](https://pytorch.org/vision/stable/generated/torchvision.transforms.ToTensor.html#torchvision.transforms.ToTensor)
+
+```python
+torchvision.transforms.ToTensor()
+```
+
+### [paddle.vision.transforms.ToTensor](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/ToTensor_cn.html#paddle/vision/transforms/ToTensor_cn#cn-api-paddle-vision-transforms-ToTensor)
+
+```python
+paddle.vision.transforms.ToTensor(data_format='CHW', keys=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+transform = torchvision.transforms.ToTensor()
+
+# Paddle 写法
+transform = paddle.vision.transforms.ToTensor()
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.adjust_brightness.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.adjust_brightness.md
new file mode 100644
index 00000000000..43be4dddcaa
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.adjust_brightness.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torchvision.transforms.functional.adjust_brightness
+
+### [torchvision.transforms.functional.adjust_brightness](https://pytorch.org/vision/stable/generated/torchvision.transforms.functional.adjust_brightness.html#torchvision.transforms.functional.adjust_brightness)
+
+```python
+torchvision.transforms.functional.adjust_brightness(img, brightness_factor)
+```
+
+### [paddle.vision.transforms.adjust_brightness](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/adjust_brightness_cn.html#paddle/vision/transforms/adjust_brightness_cn#cn-api-paddle-vision-transforms-adjust_brightness)
+
+```python
+paddle.vision.transforms.adjust_brightness(img, brightness_factor)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = torchvision.transforms.functional.adjust_brightness(img, factor)
+
+# Paddle 写法
+result = paddle.vision.transforms.adjust_brightness(img, factor)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.adjust_contrast.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.adjust_contrast.md
new file mode 100644
index 00000000000..71b634033a2
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.adjust_contrast.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torchvision.transforms.functional.adjust_contrast
+
+### [torchvision.transforms.functional.adjust_contrast](https://pytorch.org/vision/stable/generated/torchvision.transforms.functional.adjust_contrast.html#torchvision.transforms.functional.adjust_contrast)
+
+```python
+torchvision.transforms.functional.adjust_contrast(img, contrast_factor)
+```
+
+### [paddle.vision.transforms.adjust_contrast](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/adjust_contrast_cn.html#paddle/vision/transforms/adjust_contrast_cn#cn-api-paddle-vision-transforms-adjust_contrast)
+
+```python
+paddle.vision.transforms.adjust_contrast(img, contrast_factor)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = torchvision.transforms.functional.adjust_contrast(img, contrast_factor)
+
+# Paddle 写法
+result = paddle.vision.transforms.adjust_contrast(img, contrast_factor)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.adjust_hue.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.adjust_hue.md
new file mode 100644
index 00000000000..83034082d2e
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.adjust_hue.md
@@ -0,0 +1,30 @@
+## [ 仅 API 调用方式不一致 ]torchvision.transforms.functional.adjust_hue
+
+### [torchvision.transforms.functional.adjust_hue](https://pytorch.org/vision/stable/generated/torchvision.transforms.functional.adjust_hue.html#torchvision.transforms.functional.adjust_hue)
+
+```python
+torchvision.transforms.functional.adjust_hue(img, hue_factor)
+```
+
+### [paddle.vision.transforms.adjust_hue](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/adjust_hue_cn.html#paddle/vision/transforms/adjust_hue_cn#cn-api-paddle-vision-transforms-adjust_hue)
+
+```python
+paddle.vision.transforms.adjust_hue(img, hue_factor)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = torchvision.transforms.functional.adjust_hue(
+    Image.new("RGB", (2, 2), color=(100, 100, 100)), 0.25
+)
+
+# Paddle 写法
+result = paddle.vision.transforms.adjust_hue(
+    Image.new("RGB", (2, 2), color=(100, 100, 100)), 0.25
+)
+
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.affine.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.affine.md
new file mode 100644
index 00000000000..2c8bdb2df53
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.affine.md
@@ -0,0 +1,30 @@
+## [ 仅 API 调用方式不一致 ]torchvision.transforms.functional.affine
+
+### [torchvision.transforms.functional.affine](https://pytorch.org/vision/stable/generated/torchvision.transforms.functional.affine.html#torchvision.transforms.functional.affine)
+
+```python
+torchvision.transforms.functional.affine(img, angle, translate, scale, shear, interpolation=torchvision.transforms.functional.NEREAST, fill=None, center=None)
+```
+
+### [paddle.vision.transforms.affine](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/affine_cn.html#paddle/vision/transforms/affine_cn#cn-api-paddle-vision-transforms-affine)
+
+```python
+paddle.vision.transforms.affine(img, angle, translate, scale, shear, interpolation='nearst', fill=0, center=None)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = torchvision.transforms.functional.affine(
+    img, 30, (1, 1), 1.0, 0, torchvision.transforms.InterpolationMode.NEAREST
+)
+
+# Paddle 写法
+result = paddle.vision.transforms.affine(
+    img, 30, (1, 1), 1.0, 0, torchvision.transforms.InterpolationMode.NEAREST
+)
+
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.center_crop.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.center_crop.md
new file mode 100644
index 00000000000..defca44d197
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.center_crop.md
@@ -0,0 +1,26 @@
+## [ 仅 API 调用方式不一致 ]torchvision.transforms.functional.center_crop
+
+### [torchvision.transforms.functional.center_crop](https://pytorch.org/vision/stable/generated/torchvision.transforms.functional.center_crop.html#torchvision.transforms.functional.center_crop)
+
+```python
+torchvision.transforms.functional.center_crop(img, output_size)
+```
+
+### [paddle.vision.transforms.center_crop](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/center_crop_cn.html#paddle/vision/transforms/center_crop_cn#cn-api-paddle-vision-transforms-center_crop)
+
+```python
+paddle.vision.transforms.center_crop(img, output_size)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = torchvision.transforms.functional.center_crop(img, output_size)
+
+# Paddle 写法
+result = paddle.vision.transforms.center_crop(img, output_size)
+
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.crop.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.crop.md
new file mode 100644
index 00000000000..082d5942475
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.crop.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torchvision.transforms.functional.crop
+
+### [torchvision.transforms.functional.crop](https://pytorch.org/vision/stable/generated/torchvision.transforms.functional.crop.html#torchvision.transforms.functional.crop)
+
+```python
+torchvision.transforms.functional.crop(img, top, left, height, width)
+```
+
+### [paddle.vision.transforms.crop](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/crop_cn.html#paddle/vision/transforms/crop_cn#cn-api-paddle-vision-transforms-crop)
+
+```python
+paddle.vision.transforms.crop(img, top, left, height, width)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = torchvision.transforms.functional.crop(img, top, left, height, width)
+
+# Paddle 写法
+result = paddle.vision.transforms.crop(img, top, left, height, width)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.erase.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.erase.md
new file mode 100644
index 00000000000..6969553c16e
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.erase.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torchvision.transforms.functional.erase
+
+### [torchvision.transforms.functional.erase](https://pytorch.org/vision/stable/generated/torchvision.transforms.functional.erase.html#torchvision.transforms.functional.erase)
+
+```python
+torchvision.transforms.functional.erase(img, i, j, h, w, v, inplace)
+```
+
+### [paddle.vision.transforms.erase](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/erase_cn.html#paddle/vision/transforms/erase_cn#cn-api-paddle-vision-transforms-erase)
+
+```python
+paddle.vision.transforms.erase(img, i, j, h, w, v, inplace)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = torchvision.transforms.functional.erase(img, i, j, h, w, v, inplace)
+
+# Paddle 写法
+result = paddle.vision.transforms.erase(img, i, j, h, w, v, inplace)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.hflip.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.hflip.md
new file mode 100644
index 00000000000..ab715c5b6aa
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.hflip.md
@@ -0,0 +1,26 @@
+## [ 仅 API 调用方式不一致 ]torchvision.transforms.functional.hflip
+
+### [torchvision.transforms.functional.hflip](https://pytorch.org/vision/stable/generated/torchvision.transforms.functional.hflip.html#torchvision.transforms.functional.hflip)
+
+```python
+torchvision.transforms.functional.hflip(img)
+```
+
+### [paddle.vision.transforms.hflip](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/hflip_cn.html#paddle/vision/transforms/hflip_cn#cn-api-paddle-vision-transforms-hflip)
+
+```python
+paddle.vision.transforms.hflip(img)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = torchvision.transforms.functional.hflip(img)
+
+# Paddle 写法
+result = paddle.vision.transforms.hflip(img)
+
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.pad.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.pad.md
new file mode 100644
index 00000000000..c376e431389
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.pad.md
@@ -0,0 +1,30 @@
+## [ 仅 API 调用方式不一致 ]torchvision.transforms.functional.pad
+
+### [torchvision.transforms.functional.pad](https://pytorch.org/vision/stable/generated/torchvision.transforms.functional.pad.html#torchvision.transforms.functional.pad)
+
+```python
+torchvision.transforms.functional.pad(img, padding, fill=0, padding_mode='constant')
+```
+
+### [paddle.vision.transforms.pad](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/pad_cn.html#paddle/vision/transforms/pad_cn#cn-api-paddle-vision-transforms-pad)
+
+```python
+paddle.vision.transforms.pad(img, padding, fill=0, padding_mode='constant')
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = torchvision.transforms.functional.pad(
+    img=img, padding=padding, fill=fill, padding_mode=padding_mode
+)
+
+# Paddle 写法
+result = paddle.vision.transforms.pad(
+    img=img, padding=padding, fill=fill, padding_mode=padding_mode
+)
+
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.perspective.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.perspective.md
new file mode 100644
index 00000000000..7dfc6a9dcac
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.perspective.md
@@ -0,0 +1,29 @@
+## [ 仅 API 调用方式不一致 ]torchvision.transforms.functional.perspective
+
+### [torchvision.transforms.functional.perspective](https://pytorch.org/vision/stable/generated/torchvision.transforms.functional.perspective.html#torchvision.transforms.functional.perspective)
+
+```python
+torchvision.transforms.functional.perspective(img, startpoints, endpoints, interpolation=torchvision.transforms.functional.InterpolationMode.BILINEAR, fill=None)
+```
+
+### [paddle.vision.transforms.perspective](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/perspective_cn.html#paddle/vision/transforms/perspective_cn#cn-api-paddle-vision-transforms-perspective)
+
+```python
+paddle.vision.transforms.perspective(img, startpoints, endpoints, interpolation='nearest', fill=0)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = torchvision.transforms.functional.perspective(
+    img, startpoints, endpoints, torchvision.transforms.InterpolationMode.BILINEAR, fill
+)
+
+# Paddle 写法
+result = paddle.vision.transforms.perspective(
+    img, startpoints, endpoints, torchvision.transforms.InterpolationMode.BILINEAR, fill
+)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.rotate.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.rotate.md
new file mode 100644
index 00000000000..b6f2bf7d43a
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.rotate.md
@@ -0,0 +1,40 @@
+## [ 仅 API 调用方式不一致 ]torchvision.transforms.functional.rotate
+
+### [torchvision.transforms.functional.rotate](https://pytorch.org/vision/stable/generated/torchvision.transforms.functional.rotate.html#torchvision.transforms.functional.rotate)
+
+```python
+torchvision.transforms.functional.rotate(img, angle, interpolation=torchvision.transforms.functional.InterpolationMode.NEAREST, expand=False, center=None, fill=None)
+```
+
+### [paddle.vision.transforms.rotate](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/rotate_cn.html#paddle/vision/transforms/rotate_cn#cn-api-paddle-vision-transforms-rotate)
+
+```python
+paddle.vision.transforms.rotate(img, angle, interpolation='nearest', expand=False, center=None, fill=0)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = torchvision.transforms.functional.rotate(
+    img=img,
+    angle=30,
+    interpolation=torchvision.transforms.InterpolationMode.BILINEAR,
+    expand=True,
+    center=(1, 1),
+    fill=[128, 128, 128],
+)
+
+
+# Paddle 写法
+result = paddle.vision.transforms.rotate(
+    img=img,
+    angle=30,
+    interpolation=torchvision.transforms.InterpolationMode.BILINEAR,
+    expand=True,
+    center=(1, 1),
+    fill=[128, 128, 128],
+)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.to_grayscale.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.to_grayscale.md
new file mode 100644
index 00000000000..24ec801aa20
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.to_grayscale.md
@@ -0,0 +1,25 @@
+## [ 仅 API 调用方式不一致 ]torchvision.transforms.functional.to_grayscale
+
+### [torchvision.transforms.functional.to_grayscale](https://pytorch.org/vision/stable/generated/torchvision.transforms.functional.to_grayscale.html#torchvision.transforms.functional.to_grayscale)
+
+```python
+torchvision.transforms.functional.to_grayscale(img, num_output_channels=1)
+```
+
+### [paddle.vision.transforms.to_grayscale](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/to_grayscale_cn.html#paddle/vision/transforms/to_grayscale_cn#cn-api-paddle-vision-transforms-to_grayscale)
+
+```python
+paddle.vision.transforms.to_grayscale(img, num_output_channels=1)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = torchvision.transforms.functional.to_grayscale(img, num_output_channels=1)
+
+# Paddle 写法
+result = paddle.vision.transforms.to_grayscale(img, num_output_channels=1)
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.to_tensor.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.to_tensor.md
new file mode 100644
index 00000000000..b0204fc2822
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.to_tensor.md
@@ -0,0 +1,26 @@
+## [ 仅 API 调用方式不一致 ]torchvision.transforms.functional.to_tensor
+
+### [torchvision.transforms.functional.to_tensor](https://pytorch.org/vision/stable/generated/torchvision.transforms.functional.to_tensor.html#torchvision.transforms.functional.to_tensor)
+
+```python
+torchvision.transforms.functional.to_tensor(pic)
+```
+
+### [paddle.vision.transforms.to_tensor](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/to_tensor_cn.html#paddle/vision/transforms/to_tensor_cn#cn-api-paddle-vision-transforms-to_tensor)
+
+```python
+paddle.vision.transforms.to_tensor(pic, data_format='CHW')
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = torchvision.transforms.functional.to_tensor(img)
+
+# Paddle 写法
+result = paddle.vision.transforms.to_tensor(img)
+
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.vflip.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.vflip.md
new file mode 100644
index 00000000000..e1a237fb794
--- /dev/null
+++ b/docs/guides/model_convert/convert_from_pytorch/api_difference/invok_only_diff/torchvision.transforms.functional.vflip.md
@@ -0,0 +1,26 @@
+## [ 仅 API 调用方式不一致 ]torchvision.transforms.functional.vflip
+
+### [torchvision.transforms.functional.vflip](https://pytorch.org/vision/stable/generated/torchvision.transforms.functional.vflip.html#torchvision.transforms.functional.vflip)
+
+```python
+torchvision.transforms.functional.vflip(img)
+```
+
+### [paddle.vision.transforms.vflip](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/vflip_cn.html#paddle/vision/transforms/vflip_cn#cn-api-paddle-vision-transforms-vflip)
+
+```python
+paddle.vision.transforms.vflip(img)
+```
+
+两者功能一致，但调用方式不一致，具体如下：
+
+### 转写示例
+
+```python
+# PyTorch 写法
+result = torchvision.transforms.functional.vflip(img)
+
+# Paddle 写法
+result = paddle.vision.transforms.vflip(img)
+
+```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/output_args_type_diff/torch.cuda.get_rng_state_all.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/output_args_type_diff/torch.cuda.get_rng_state_all.md
deleted file mode 100644
index c92088d86b5..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/output_args_type_diff/torch.cuda.get_rng_state_all.md
+++ /dev/null
@@ -1,29 +0,0 @@
-## [ 返回参数类型不一致 ]torch.cuda.get_rng_state_all
-### [torch.cuda.get_rng_state_all](https://pytorch.org/docs/stable/generated/torch.cuda.get_rng_state_all.html#torch.cuda.get_rng_state_all)
-```python
-torch.cuda.get_rng_state_all()
-```
-
-### [paddle.get_rng_state]()
-```python
-paddle.get_rng_state(device='gpu')
-```
-
-paddle 参数更多，并且 torch 与 paddle 的返回参数类型不一致，具体如下：
-
-### 参数映射
-
-| PyTorch | PaddlePaddle | 备注                                                                                               |
-| ------- | ------------ | -------------------------------------------------------------------------------------------------- |
-| -       | device       | 返回随机数生成器状态的设备，PyTorch 无此参数，Paddle 需设置为'gpu' 。           |
-| 返回值  | 返回值       | 返回参数类型不一致, PyTorch 返回 torch.ByteTensor，Paddle 返回 GeneratorState 对象。 |
-
-### 转写示例
-#### 返回参数类型不同
-```python
-# PyTorch 写法，返回 torch.ByteTensor
-x = torch.cuda.get_rng_state_all()
-
-# Paddle 写法，返回 GeneratorState 对象
-x = paddle.get_rng_state(device='gpu')
-```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/output_args_type_diff/torch.cuda.manual_seed.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/output_args_type_diff/torch.cuda.manual_seed.md
deleted file mode 100644
index 896d5c484a2..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/output_args_type_diff/torch.cuda.manual_seed.md
+++ /dev/null
@@ -1,29 +0,0 @@
-## [ 返回参数类型不一致 ]torch.cuda.manual_seed
-### [torch.cuda.manual_seed](https://pytorch.org/docs/stable/generated/torch.cuda.manual_seed.html#torch.cuda.manual_seed)
-```python
-torch.cuda.manual_seed(seed)
-```
-
-### [paddle.seed](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/seed_cn.html)
-```python
-paddle.seed(seed)
-```
-
-功能一致，返回类型不一致，具体如下：
-
-### 参数映射
-
-| PyTorch | PaddlePaddle | 备注                                                 |
-|---------|--------------|----------------------------------------------------|
-| seed    | seed         | 表示设置的的随机种子(int)。                                   |
-| -       | 返回值          | PyTorch 无返回值，Paddle 返回 Generator(全局默认 generator 对象)。 |
-
-### 转写示例
-#### 返回值
-```python
-# torch 写法
-torch.cuda.manual_seed(100)
-
-# paddle 写法
-gen = paddle.seed(100)
-```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/output_args_type_diff/torch.max.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/output_args_type_diff/torch.max.md
deleted file mode 100644
index ec41a35a49b..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/output_args_type_diff/torch.max.md
+++ /dev/null
@@ -1,94 +0,0 @@
-## [ 返回参数类型不一致 ]torch.max
-输入一个 Tensor 对应 paddle.max，输入两个 Tensor 对应 paddle.maximum，因此有两组差异分析，分别如下：
-
--------------------------------------------------------------------------------------------------
-
-### [torch.max](https://pytorch.org/docs/stable/generated/torch.max.html?highlight=max#torch.max)
-```python
-torch.max(input,
-          dim=None,
-          keepdim=False,
-          *,
-          out=None)
-```
-
-### [paddle.max](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/max_cn.html#max)
-```python
-paddle.max(x,
-           axis=None,
-           keepdim=False,
-           name=None)
-```
-
-其中 PyTorch 与 Paddle 指定 `dim` 后返回值不一致，具体如下：
-### 参数映射
-
-| PyTorch       | PaddlePaddle | 备注                                                   |
-| ------------- | ------------ | ------------------------------------------------------ |
-| input         | x            | 输入的 Tensor ，仅参数名不一致。                                      |
-| dim           | axis         | 求最大值运算的维度， 仅参数名不一致。                                      |
-| keepdim       | keepdim      | 是否在输出 Tensor 中保留减小的维度。  |
-| out           | -            | 表示输出的 Tensor ， Paddle 无此参数，需要转写。               |
-| 返回值           | 返回值            | 表示返回结果，当指定 dim 后，PyTorch 会返回比较结果和元素索引， Paddle 不会返回元素索引，需要转写。               |
-
-
-### 转写示例
-#### out：指定输出
-```python
-# 对指定维度上的 Tensor 元素求最大值运算
-
-# PyTorch 写法
-torch.max(a, out=y)
-# torch 在输入 dim 时，返回 (values, indices)，返回参数类型不一致
-
-# Paddle 写法
-paddle.assign(paddle.max(a), y)
-```
-#### 指定 dim 后的返回值
-```python
-# PyTorch 写法
-result = torch.max(a, dim=1)
-
-# Paddle 写法
-result = paddle.max(a, axis=1), paddle.argmax(a, axis=1)
-```
-
---------------------------------------------------------------------------------------------------
-
-### [torch.max](https://pytorch.org/docs/stable/generated/torch.max.html?highlight=max#torch.max)
-```python
-torch.max(input,
-          other,
-          *,
-          out=None)
-```
-
-### [paddle.maximum](https://www.paddlepaddle.org.cn/documentation/docs/zh/api/paddle/minimum_cn.html#minimum)
-```python
-paddle.maximum(x,
-               y,
-               name=None)
-```
-
-PyTorch 相比 Paddle 支持更多其他参数，具体如下：
-### 参数映射
-
-| PyTorch       | PaddlePaddle | 备注                                                   |
-| ------------- | ------------ | ------------------------------------------------------ |
-| input         | x            | 输入的 Tensor ，仅参数名不一致。                                      |
-| other         | y            | 输入的 Tensor ， 仅参数名不一致。                                      |
-| out           | -            | 表示输出的 Tensor ， Paddle 无此参数，需要转写。               |
-
-
-### 转写示例
-#### out：指定输出
-```python
-# 逐元素对比输入的两个 Tensor
-
-# PyTorch 写法
-torch.max(a, b, out=y)
-# 在输入 other 时，比较 input 和 other 返回较大值
-
-# Paddle 写法
-paddle.assign(paddle.maximum(a, b), y)
-```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/output_args_type_diff/torch.min.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/output_args_type_diff/torch.min.md
deleted file mode 100644
index ee100fb0838..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/output_args_type_diff/torch.min.md
+++ /dev/null
@@ -1,92 +0,0 @@
-## [ 返回参数类型不一致 ]torch.min
-输入一个 Tensor 对应 paddle.min，输入两个 Tensor 对应 paddle.minimum，因此有两组差异分析，分别如下：
-
---------------------------------------------------------------------------------------------------
-### [torch.min](https://pytorch.org/docs/stable/generated/torch.min.html?highlight=min#torch.min)
-```python
-torch.min(input,
-          dim=None,
-          keepdim=False,
-          *,
-          out=None)
-```
-
-### [paddle.min](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/min_cn.html#min)
-```python
-paddle.min(x,
-           axis=None,
-           keepdim=False,
-           name=None)
-```
-
-其中 PyTorch 与 Paddle 指定 `dim` 后返回值不一致，具体如下：
-### 参数映射
-
-| PyTorch       | PaddlePaddle | 备注                                                   |
-| ------------- | ------------ | ------------------------------------------------------ |
-| input         | x            | 输入的 Tensor ，仅参数名不一致。                                      |
-| dim           | axis         | 求最小值运算的维度， 仅参数名不一致。                                      |
-| keepdim       | keepdim      | 是否在输出 Tensor 中保留减小的维度。  |
-| out           | -            | 表示输出的 Tensor ， Paddle 无此参数，需要转写。               |
-| 返回值           | 返回值            | 表示返回结果，当指定 dim 后，PyTorch 会返回比较结果和元素索引， Paddle 不会返回元素索引，需要转写。               |
-
-### 转写示例
-#### out：指定输出
-```python
-# 对指定维度上的 Tensor 元素求最大值运算
-
-# PyTorch 写法
-torch.min(a, out=y)
-# torch 在输入 dim 时，返回 (values, indices)，返回参数类型不一致
-
-# Paddle 写法
-paddle.assign(paddle.min(a), y)
-```
-#### 指定 dim 后的返回值
-```python
-# PyTorch 写法
-result = torch.min(a, dim=1)
-
-# Paddle 写法
-result = torch.min(a, dim=1), torch.argmin(a, dim=1)
-```
-
---------------------------------------------------------------------------------------------------
-
-### [torch.min](https://pytorch.org/docs/stable/generated/torch.min.html?highlight=min#torch.min)
-```python
-torch.min(input,
-          other,
-          *,
-          out=None)
-```
-
-### [paddle.minimum](https://www.paddlepaddle.org.cn/documentation/docs/zh/api/paddle/minimum_cn.html#minimum)
-```python
-paddle.minimum(x,
-               y,
-               name=None)
-```
-
-PyTorch 相比 Paddle 支持更多其他参数，具体如下：
-### 参数映射
-
-| PyTorch       | PaddlePaddle | 备注                                                   |
-| ------------- | ------------ | ------------------------------------------------------ |
-| input         | x            | 输入的 Tensor。                                      |
-| other         | y            | 输入的 Tensor。                                      |
-| out           | -            | 表示输出的 Tensor ， Paddle 无此参数，需要转写。               |
-
-
-### 转写示例
-#### out：指定输出
-```python
-# 逐元素对比输入的两个 Tensor
-
-# PyTorch 写法
-torch.min(a, b, out=y)
-# 在输入 other 时，比较 input 和 other 返回较大值
-
-# Paddle 写法
-paddle.assign(paddle.minimum(a, b), y)
-```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/output_args_type_diff/torch.sort.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/output_args_type_diff/torch.sort.md
deleted file mode 100644
index 31e14ce6669..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/output_args_type_diff/torch.sort.md
+++ /dev/null
@@ -1,45 +0,0 @@
-## [ 返回参数类型不一致 ]torch.sort
-### [torch.sort](https://pytorch.org/docs/stable/generated/torch.sort.html?highlight=sort#torch.sort)
-```python
-torch.sort(input,
-           dim=-1,
-           descending=False,
-           stable=False,
-           *,
-           out=None)
-```
-
-### [paddle.sort](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/sort_cn.html#paddle.sort)
-```python
-paddle.sort(x,
-            axis=-1,
-            descending=False,
-            stable=False,
-            name=None)
-```
-
-PyTorch 相比 Paddle 支持更多其他参数，同时两个 api 的返回参数类型不同，具体如下：
-
-### 参数映射
-
-| PyTorch       | PaddlePaddle | 备注                                                   |
-| ------------- | ------------ | ------------------------------------------------------ |
-| input         | x            | 输入的 Tensor ，仅参数名不一致。                           |
-| dim           | axis         | 指定对输入 Tensor 进行运算的轴。默认值为-1, 仅参数名不一致。 |
-| descending    |descending    | 指定算法排序的方向。如果设置为 True，算法按照降序排序。如果设置为 False 或者不设置，按照升序排序。默认值为 False，参数名相同。     |
-| stable        | stable        | 使排序程序更稳定，保证等价元素的顺序得以保留。            |
-| out           | -            | 表示以(Tensor, LongTensor)输出的元组，含义是排序后的返回值和对应元素索引。Paddle 无此参数，若返回排序后的元素，需要转写；若需要返回元素和元素索引，需要结合 argsort 进行转写。      |
-
-注：PyTorch 返回 (Tensor, LongTensor)，Paddle 返回 Tensor 。
-
-### 转写示例
-#### out：指定输出
-```python
-# 若要返回排序后的元素和元素索引，需要结合 argsort 进行转写
-# PyTorch 写法
-torch.sort(input, -1, True, out = (y, indices))
-
-# Paddle 写法
-paddle.assign(paddle.sort(input, -1, True), y)
-paddle.assign(paddle.argsort(input, -1, True), indices)
-```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/output_args_type_diff/torch.utils.data.default_collate.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/output_args_type_diff/torch.utils.data.default_collate.md
deleted file mode 100644
index 37964d72f29..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/output_args_type_diff/torch.utils.data.default_collate.md
+++ /dev/null
@@ -1,40 +0,0 @@
-## [ 返回参数类型不一致 ]torch.utils.data.default_collate
-### [torch.utils.data.default_collate](https://pytorch.org/docs/stable/data.html?highlight=default_collate#torch.utils.data.default_collate)
-```python
-torch.utils.data.default_collate(batch)
-```
-
-### [paddle.io.dataloader.collate.default_collate_fn]()
-```python
-paddle.io.dataloader.collate.default_collate_fn(batch)
-```
-
-返回参数类型不一致，需要转写。具体如下：
-### 参数映射
-
-| PyTorch       | PaddlePaddle | 备注                                                   |
-| ------------- | ------------ | ------------------------------------------------------ |
-| batch        | batch        | 输入的用于组 batch 的数据。                                    |
-| 返回值        | 返回值        | 返回参数类型不一致，当 batch 的元素为 numpy.ndarray 或 number 时， PyTorch 默认返回 torch.tensor, Paddle 默认返回 numpy.ndarray。                                    |
-
-
-### 转写示例
-#### 当 batch 的元素为 numpy.ndarray 或 number 时
-```python
-# PyTorch 写法
-y = torch.utils.data.default_collate(batch)
-
-# Paddle 写法
-y = paddle.to_tensor(paddle.io.dataloader.collate.default_collate_fn(batch))
-```
-
-#### 当 batch 的元素为字典且字典的 value 为 numpy.ndarray 或 number 时
-```python
-# PyTorch 写法
-y = torch.utils.data.default_collate(batch)
-
-# Paddle 写法
-y = paddle.io.dataloader.collate.default_collate_fn(batch)
-for k, v in y.items():
-    y[k] = paddle.to_tensor(v)
-```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torch.Tensor.argwhere.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torch.Tensor.argwhere.md
deleted file mode 100644
index 19c478d1a0e..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torch.Tensor.argwhere.md
+++ /dev/null
@@ -1,18 +0,0 @@
-## [ paddle 参数更多 ]torch.Tensor.argwhere
-### [torch.Tensor.argwhere](https://pytorch.org/docs/stable/generated/torch.Tensor.argwhere.html#torch.Tensor.argwhere)
-```python
-torch.Tensor.argwhere()
-```
-
-### [paddle.Tensor.nonzero](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/Tensor_cn.html#nonzero-as-tuple-false)
-```python
-paddle.Tensor.nonzero(as_tuple=False)
-```
-
-其中 Paddle 相比 PyTorch 支持更多其他参数，具体如下：
-
-### 参数映射
-
-| PyTorch       | PaddlePaddle | 备注                                                   |
-| ------------- | ------------ | ------------------------------------------------------ |
-| - | <font color='red'> as_tuple </font>   | 返回格式。是否以 1-D Tensor 构成的元组格式返回。 PyTorch 无此参数， Paddle 保持默认即可。  |
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torch.Tensor.pinverse.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torch.Tensor.pinverse.md
deleted file mode 100644
index 5bd373210cf..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torch.Tensor.pinverse.md
+++ /dev/null
@@ -1,22 +0,0 @@
-## [ paddle 参数更多 ]torch.Tensor.pinverse
-
-### [torch.Tensor.pinverse](https://pytorch.org/docs/stable/generated/torch.Tensor.pinverse.html#torch.Tensor.pinverse)
-```python
-torch.Tensor.pinverse()
-```
-
-### [paddle.Tensor.pinv]()
-```python
-paddle.Tensor.pinv(rcond=1e-15,
-                   hermitian=False,
-                   name=None)
-```
-
-其中 Paddle 相比 PyTorch 支持更多参数，具体如下：
-
-### 参数映射
-
-| PyTorch       | PaddlePaddle | 备注                                                   |
-| ------------- | ------------ | ------------------------------------------------------ |
-| -         | rcond        | 奇异值（特征值）被截断的阈值，PyTorch 无此参数，Paddle 保持默认即可。        |
-| -             | hermitian    | 是否为 hermitian 矩阵或者实对称矩阵，PyTorch 无此参数，Paddle 保持默认即可。|
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torch.nn.AdaptiveAvgPool2d.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torch.nn.AdaptiveAvgPool2d.md
deleted file mode 100644
index 40cd9cca297..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torch.nn.AdaptiveAvgPool2d.md
+++ /dev/null
@@ -1,18 +0,0 @@
-## [ paddle 参数更多 ]torch.nn.AdaptiveAvgPool2d
-### [torch.nn.AdaptiveAvgPool2d](https://pytorch.org/docs/stable/generated/torch.nn.AdaptiveAvgPool2d.html)
-```python
-torch.nn.AdaptiveAvgPool2d(output_size)
-```
-
-### [paddle.nn.AdaptiveAvgPool2D](https://www.paddlepaddle.org.cn/documentation/docs/zh/api/paddle/nn/AdaptiveAvgPool2D_cn.html#adaptiveavgpool2d)
-```python
-paddle.nn.AdaptiveAvgPool2D(output_size, data_format='NCHW', name=None)
-```
-
-其中 Paddle 相比 PyTorch 支持更多其他参数，具体如下：
-### 参数映射
-
-| PyTorch       | PaddlePaddle | 备注                                                   |
-| ------------- | ------------ | ------------------------------------------------------ |
-| output_size   | output_size  | 表示输出 Tensor 的 size 。                              |
-| -             | data_format  | 表示输入 Tensor 的数据格式， PyTorch 无此参数， Paddle 保持默认即可。 |
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torch.nn.AdaptiveAvgPool3d.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torch.nn.AdaptiveAvgPool3d.md
deleted file mode 100644
index 6a9f4e31acf..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torch.nn.AdaptiveAvgPool3d.md
+++ /dev/null
@@ -1,18 +0,0 @@
-## [ paddle 参数更多 ]torch.nn.AdaptiveAvgPool3d
-### [torch.nn.AdaptiveAvgPool3d](https://pytorch.org/docs/stable/generated/torch.nn.AdaptiveAvgPool3d.html)
-```python
-torch.nn.AdaptiveAvgPool3d(output_size)
-```
-
-### [paddle.nn.AdaptiveAvgPool3D](https://www.paddlepaddle.org.cn/documentation/docs/zh/api/paddle/nn/AdaptiveAvgPool3D_cn.html#adaptiveavgpool3d)
-```python
-paddle.nn.AdaptiveAvgPool3D(output_size, data_format='NCDHW', name=None)
-```
-
-其中 Paddle 相比 PyTorch 支持更多其他参数，具体如下：
-### 参数映射
-
-| PyTorch       | PaddlePaddle | 备注                                                   |
-| ------------- | ------------ | ------------------------------------------------------ |
-| output_size   | output_size  | 表示输出 Tensor 的 size 。                              |
-| -             | data_format  | 表示输入 Tensor 的数据格式， PyTorch 无此参数， Paddle 保持默认即可。 |
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torch.nn.MaxUnpool1d.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torch.nn.MaxUnpool1d.md
deleted file mode 100644
index af8892885d9..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torch.nn.MaxUnpool1d.md
+++ /dev/null
@@ -1,28 +0,0 @@
-## [ paddle 参数更多 ]torch.nn.MaxUnpool1d
-### [torch.nn.MaxUnpool1d](https://pytorch.org/docs/stable/generated/torch.nn.MaxUnpool1d.html?highlight=maxunpool1d#torch.nn.MaxUnpool1d)
-```python
-torch.nn.MaxUnpool1d(kernel_size,
-                     stride=None,
-                     padding=0)
-```
-
-### [paddle.nn.MaxUnPool1D](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/nn/MaxUnPool1D_cn.html)
-```python
-paddle.nn.MaxUnPool1D(kernel_size,
-                      stride=None,
-                      padding=0,
-                      data_format='NCL',
-                      output_size=None,
-                      name=None)
-```
-
-其中 Paddle 相比 PyTorch 支持更多其他参数，具体如下：
-### 参数映射
-
-| PyTorch       | PaddlePaddle | 备注                                                   |
-| ------------- | ------------ | ------------------------------------------------------ |
-| kernel_size          | kernel_size            | 表示反池化核大小。                           |
-| stride          | stride            | 表示反池化核步长。                           |
-| padding          | padding            | 表示填充大小。                           |
-| -             | data_format  | 输入和输出的数据格式，PyTorch 无此参数，Paddle 保持默认即可。  |
-| -             | output_size  | 目标输出尺寸，PyTorch 无此参数，Paddle 保持默认即可。        |
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torch.nn.MaxUnpool2d.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torch.nn.MaxUnpool2d.md
deleted file mode 100644
index b01d53b1cca..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torch.nn.MaxUnpool2d.md
+++ /dev/null
@@ -1,28 +0,0 @@
-## [ paddle 参数更多 ]torch.nn.MaxUnpool2d
-### [torch.nn.MaxUnpool2d](https://pytorch.org/docs/stable/generated/torch.nn.MaxUnpool2d.html?highlight=maxunpool2d#torch.nn.MaxUnpool2d)
-```python
-torch.nn.MaxUnpool2d(kernel_size,
-                     stride=None,
-                     padding=0)
-```
-
-### [paddle.nn.MaxUnPool2D](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/nn/MaxUnPool2D_cn.html)
-```python
-paddle.nn.MaxUnPool2D(kernel_size,
-                      stride=None,
-                      padding=0,
-                      data_format='NCHW',
-                      output_size=None,
-                      name=None)
-```
-
-其中 Paddle 相比 PyTorch 支持更多其他参数，具体如下：
-### 参数映射
-
-| PyTorch       | PaddlePaddle | 备注                                                   |
-| ------------- | ------------ | ------------------------------------------------------ |
-| kernel_size          | kernel_size            | 表示反池化核大小。                           |
-| stride          | stride            | 表示反池化核步长。                           |
-| padding          | padding            | 表示填充大小。                           |
-| -             | data_format  | 输入和输出的数据格式，PyTorch 无此参数，Paddle 保持默认即可。  |
-| -             | output_size  | 目标输出尺寸，PyTorch 无此参数，Paddle 保持默认即可。        |
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torch.nn.MaxUnpool3d.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torch.nn.MaxUnpool3d.md
deleted file mode 100644
index 1ec4ca953e5..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torch.nn.MaxUnpool3d.md
+++ /dev/null
@@ -1,28 +0,0 @@
-## [ paddle 参数更多 ]torch.nn.MaxUnpool3d
-### [torch.nn.MaxUnpool3d](https://pytorch.org/docs/stable/generated/torch.nn.MaxUnpool3d.html?highlight=maxunpool3d#torch.nn.MaxUnpool3d)
-```python
-torch.nn.MaxUnpool3d(kernel_size,
-                     stride=None,
-                     padding=0)
-```
-
-### [paddle.nn.MaxUnPool3D](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/nn/MaxUnPool3D_cn.html)
-```python
-paddle.nn.MaxUnPool3D(kernel_size,
-                      stride=None,
-                      padding=0,
-                      data_format='NCDHW',
-                      output_size=None,
-                      name=None)
-```
-
-其中 Paddle 相比 PyTorch 支持更多其他参数，具体如下：
-### 参数映射
-
-| PyTorch       | PaddlePaddle | 备注                                                   |
-| ------------- | ------------ | ------------------------------------------------------ |
-| kernel_size          | kernel_size            | 表示反池化核大小。                           |
-| stride          | stride            | 表示反池化核步长。                           |
-| padding          | padding            | 表示填充大小。                           |
-| -             | data_format  | 输入和输出的数据格式，PyTorch 无此参数，Paddle 保持默认即可。  |
-| -             | output_size  | 目标输出尺寸，PyTorch 无此参数，Paddle 保持默认即可。        |
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torch.nn.Module.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torch.nn.Module.md
deleted file mode 100644
index a24fc14503e..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torch.nn.Module.md
+++ /dev/null
@@ -1,20 +0,0 @@
-## [ paddle 参数更多 ]torch.nn.Module
-
-### [torch.nn.Module](https://pytorch.org/docs/stable/generated/torch.nn.Module.html?highlight=torch+nn+module#torch.nn.Module)
-```python
-torch.nn.Module(*args, **kwargs)
-```
-
-### [paddle.nn.Layer](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/nn/Layer_cn.html)
-```python
-paddle.nn.Layer(name_scope=None, dtype='float32')
-```
-
-其中 Paddle 相比 PyTorch 支持更多其他参数，具体如下：
-
-### 参数映射
-
-| PyTorch | PaddlePaddle |                  备注                  |
-|  -----  |  ----------  |  ------------------------------------ |
-|    -    |  name_scope  | PyTorch 无此参数，Paddle 保持默认即可。 |
-|    -    |    dtype     | PyTorch 无此参数，Paddle 保持默认即可。 |
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torch.nn.Module.modules.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torch.nn.Module.modules.md
deleted file mode 100644
index 8054091e7ca..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torch.nn.Module.modules.md
+++ /dev/null
@@ -1,18 +0,0 @@
-## [ paddle 参数更多 ]torch.nn.Module.modules
-### [torch.nn.Module.modules](https://pytorch.org/docs/stable/generated/torch.nn.Module.html#torch.nn.Module.modules)
-```python
-torch.nn.Module.modules()
-```
-
-### [paddle.nn.Layer.sublayers](https://www.paddlepaddle.org.cn/documentation/docs/zh/api/paddle/nn/Layer_cn.html#sublayers-include-self-false)
-```python
-paddle.nn.Layer.sublayers(include_self=False)
-```
-
-其中 Paddle 相比 PyTorch 支持更多其他参数，具体如下：
-
-### 参数映射
-
-| PyTorch | PaddlePaddle | 备注 |
-| ------- | ------------ | -- |
-| -       | include_self | 是否包含本层。PyTorch 无此参数，Paddle 保持默认即可。 |
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torch.nn.UpsamplingBilinear2d.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torch.nn.UpsamplingBilinear2d.md
deleted file mode 100644
index fcdf6ba071b..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torch.nn.UpsamplingBilinear2d.md
+++ /dev/null
@@ -1,19 +0,0 @@
-## [ paddle 参数更多 ]torch.nn.UpsamplingBilinear2d
-### [torch.nn.UpsamplingBilinear2d](https://pytorch.org/docs/stable/generated/torch.nn.UpsamplingBilinear2d.html?highlight=upsamplingbilinear2d#torch.nn.UpsamplingBilinear2d)
-```python
-torch.nn.UpsamplingBilinear2d(size=None, scale_factor=None)
-```
-
-### [paddle.nn.UpsamplingBilinear2D](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/nn/UpsamplingBilinear2D_cn.html)
-```python
-paddle.nn.UpsamplingBilinear2D(size=None,scale_factor=None, data_format='NCHW',name=None)
-```
-
-其中 Paddle 相比 PyTorch 支持更多其他参数，具体如下：
-### 参数映射
-
-| PyTorch       | PaddlePaddle | 备注                                                   |
-| ------------- | ------------ | ------------------------------------------------------ |
-| size          | size         | 表示输出 Tensor 的 size 。                                     |
-| scale_factor           | scale_factor            | 表示输入 Tensor 的高度或宽度的乘数因子。               |
-| -           | data_format           | 表示输入 Tensor 的数据格式， PyTorch 无此参数， Paddle 保持默认即可。               |
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torch.nn.UpsamplingNearest2d.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torch.nn.UpsamplingNearest2d.md
deleted file mode 100644
index f262c3f9c77..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torch.nn.UpsamplingNearest2d.md
+++ /dev/null
@@ -1,19 +0,0 @@
-## [ paddle 参数更多 ]torch.nn.UpsamplingNearest2d
-### [torch.nn.UpsamplingNearest2d](https://pytorch.org/docs/stable/generated/torch.nn.UpsamplingNearest2d.html?highlight=upsampl#torch.nn.UpsamplingNearest2d)
-```python
-torch.nn.UpsamplingNearest2d(size=None, scale_factor=None)
-```
-
-### [paddle.nn.UpsamplingNearest2D](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/nn/UpsamplingNearest2D_cn.html)
-```python
-paddle.nn.UpsamplingNearest2D(size=None, scale_factor=None, data_format='NCHW',name=None)
-```
-
-其中 Paddle 相比 PyTorch 支持更多其他参数，具体如下：
-### 参数映射
-
-| PyTorch       | PaddlePaddle | 备注                                                   |
-| ------------- | ------------ | ------------------------------------------------------ |
-| size          | size         | 表示输出 Tensor 的 size 。                                     |
-| scale_factor           | scale_factor            | 表示输入 Tensor 的高度或宽度的乘数因子。               |
-| -           | data_format           | 表示输入 Tensor 的数据格式， PyTorch 无此参数， Paddle 保持默认即可。               |
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torch.nn.ZeroPad2d.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torch.nn.ZeroPad2d.md
deleted file mode 100644
index 8367e4f43b0..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torch.nn.ZeroPad2d.md
+++ /dev/null
@@ -1,21 +0,0 @@
-## [ paddle 参数更多 ]torch.nn.ZeroPad2d
-
-### [torch.nn.ZeroPad2d](https://pytorch.org/docs/stable/generated/torch.nn.ZeroPad2d.html?highlight=zeropad#torch.nn.ZeroPad2d)
-```python
-torch.nn.ZeroPad2d(padding)
-```
-
-### [paddle.nn.ZeroPad2D](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/nn/ZeroPad2D_cn.html)
-```python
-paddle.nn.ZeroPad2D(padding,
-                    data_format='NCHW',
-                    name=None)
-```
-
-其中 Paddle 相比 PyTorch 支持更多其他参数，具体如下：
-### 参数映射
-
-| PyTorch       | PaddlePaddle | 备注                                                   |
-| ------------- | ------------ | ------------------------------------------------------ |
-| padding   | padding | 表示填充大小。                   |
-| -   | data_format | 指定输入的 format， PyTorch 无此参数， Paddle 保持默认即可。                  |
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torch.nn.functional.pad.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torch.nn.functional.pad.md
deleted file mode 100644
index 79c7ff869e9..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torch.nn.functional.pad.md
+++ /dev/null
@@ -1,34 +0,0 @@
-## [ paddle 参数更多 ]torch.nn.functional.pad
-### [torch.nn.functional.pad](https://pytorch.org/docs/stable/generated/torch.nn.functional.pad.html)
-```python
-torch.nn.functional.pad(input,
-                            pad,
-                            mode='constant',
-                            value=None)
-```
-
-### [paddle.nn.functional.pad](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/nn/functional/pad_cn.html#pad)
-```python
-paddle.nn.functional.pad(x,
-                            pad,
-                            mode='constant',
-                            value=0.0,
-                            data_format=None,
-                            pad_from_left_axis=True,
-                            name=None)
-```
-
-两者功能一致，其中 Paddle 相比 PyTorch 支持更多其他参数，具体如下：
-
-### 参数映射
-
-| PyTorch       | PaddlePaddle | 备注                                                   |
-| ------------- | ------------ | ------------------------------------------------------ |
-| input          | x         | 表示输入的 Tensor，仅参数名不一致。                                     |
-| pad          | pad         | 表示一个 one-hot 向量的长度 。                                     |
-| mode          | mode         | 表示填充的模式。                                     |
-| value          | value         | 表示填充的值，mode 为'constant'时有效 。                |
-| -        | data_format |  指定输入的数据格式, PyTorch 无此参数， Paddle 保持默认即可。 |
-| -        | pad_from_left_axis | 只有当 mode 为 'constant' ，且 pad 是长度为 2N 的列表时有效，设置 pad 与 x 的轴左对齐或右对齐， PyTorch 无此参数， Paddle 需设置为 False 结果才与 PyTorch 一致。                |
-
-在实际使用过程中，`data_format` 参数需要根据输入参数进行指定
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torchvision.transforms.CenterCrop.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torchvision.transforms.CenterCrop.md
deleted file mode 100644
index 9a2d06182e3..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torchvision.transforms.CenterCrop.md
+++ /dev/null
@@ -1,24 +0,0 @@
-## [ paddle 参数更多 ]torchvision.transforms.CenterCrop
-### [torchvision.transforms.CenterCrop](https://pytorch.org/vision/main/generated/torchvision.transforms.CenterCrop.html)
-```python
-torchvision.transforms.CenterCrop(
-    size: Union[int, List[int], Tuple[int, ...]]
-)
-```
-
-### [paddle.vision.transforms.CenterCrop](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/CenterCrop_cn.html)
-```python
-paddle.vision.transforms.CenterCrop(
-    size: Union[int, List[int], Tuple[int, ...]],
-    keys: Optional[Union[List[str], Tuple[str, ...]]] = None
-)
-```
-
-两者功能一致，但 Paddle 相比 torchvision 支持更多参数，具体如下：
-
-### 参数映射
-
-| torchvision  | PaddlePaddle | 备注                   |
-| ------------ | ------------ | ---------------------- |
-| size         | size         | 输出图像的形状大小。     |
-| -            | keys         | 输入的类型，PyTorch 无此参数，Paddle 保持默认即可。             |
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torchvision.transforms.ColorJitter.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torchvision.transforms.ColorJitter.md
deleted file mode 100644
index e8b48417e18..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torchvision.transforms.ColorJitter.md
+++ /dev/null
@@ -1,22 +0,0 @@
-## [ paddle 参数更多 ]torchvision.transforms.ColorJitter
-### [torchvision.transforms.ColorJitter](https://pytorch.org/vision/main/generated/torchvision.transforms.ColorJitter.html)
-```python
-torchvision.transforms.ColorJitter(brightness: Union[float, Tuple[float, float]] = 0, contrast: Union[float, Tuple[float, float]] = 0, saturation: Union[float, Tuple[float, float]] = 0, hue: Union[float, Tuple[float, float]] = 0)
-```
-
-### [paddle.vision.transforms.ColorJitter](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/ColorJitter_cn.html)
-```python
-paddle.vision.transforms.ColorJitter(brightness=0, contrast=0, saturation=0, hue=0, keys=None)
-```
-
-其中 Paddle 相比 PyTorch 支持更多其他参数，具体如下：
-
-### 参数映射
-
-| torchvision | PaddlePaddle | 备注    |
-| --------------------------- | ------------------------------ | --------------------- |
-| brightness     | brightness     | 亮度调整范围大小。       |
-| contrast       | contrast       | 对比度调整范围大小。       |
-| saturation     | saturation     | 饱和度调整范围大小。       |
-| hue            | hue            | 色调调整范围大小。       |
-| -              | keys           | 输入的类型，PyTorch 无此参数，Paddle 保持默认即可。             |
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torchvision.transforms.Grayscale.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torchvision.transforms.Grayscale.md
deleted file mode 100644
index 75cda0d305a..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torchvision.transforms.Grayscale.md
+++ /dev/null
@@ -1,23 +0,0 @@
-## [ paddle 参数更多 ]torchvision.transforms.Grayscale
-
-### [torchvision.transforms.Grayscale](https://pytorch.org/vision/main/generated/torchvision.transforms.Grayscale.html)
-```python
-torchvision.transforms.Grayscale(num_output_channels: int = 1)
-```
-
-### [paddle.vision.transforms.Grayscale](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/Grayscale_cn.html)
-```python
-paddle.vision.transforms.Grayscale(
-    num_output_channels: int = 1,
-    keys: Optional[Union[List[str], Tuple[str, ...]]] = None
-)
-```
-
-其中 Paddle 相比 PyTorch 支持更多其他参数，具体如下：
-
-### 参数映射
-
-| torchvision | PaddlePaddle | 备注    |
-| --------------------------- | ------------------------------ | --------------------- |
-| num_output_channels         | num_output_channels            | 输出图像的通道数。       |
-| -                           | keys                           | 输入的类型，PyTorch 无此参数，Paddle 保持默认即可。             |
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torchvision.transforms.Pad.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torchvision.transforms.Pad.md
deleted file mode 100644
index b3a484fa6a7..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torchvision.transforms.Pad.md
+++ /dev/null
@@ -1,32 +0,0 @@
-## [ paddle 参数更多 ]torchvision.transforms.Pad
-
-### [torchvision.transforms.Pad](https://pytorch.org/vision/main/generated/torchvision.transforms.Pad.html)
-
-```python
-torchvision.transforms.Pad(
-    padding: Union[int, List[int], Tuple[int, ...]],
-    fill: Union[int, List[int], Tuple[int, ...]] = 0,
-    padding_mode: str = 'constant'
-)
-```
-
-### [paddle.vision.transforms.Pad](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/Pad__upper_cn.html#pad)
-```python
-paddle.vision.transforms.Pad(
-    padding: Union[int, List[int], Tuple[int, ...]],
-    fill: Union[int, List[int], Tuple[int, ...]] = 0,
-    padding_mode: str = 'constant',
-    keys: Optional[Union[List[str], Tuple[str, ...]]] = None
-)
-```
-
-两者功能一致，但 Paddle 相比 torchvision 支持更多参数，具体如下：
-
-### 参数映射
-
-| torchvision   | PaddlePaddle  | 备注                           |
-| ------------- | ------------- | ----------------------------- |
-| padding       | padding       | 在图像边界上进行填充的范围。     |
-| fill          | fill          | 多通道图像填充。                |
-| padding_mode  | padding_mode  | 填充模式。|
-| -             | keys          | 输入的类型，PyTorch 无此参数，Paddle 保持默认即可。     |
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torchvision.transforms.RandomCrop.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torchvision.transforms.RandomCrop.md
deleted file mode 100644
index fea93a59d71..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torchvision.transforms.RandomCrop.md
+++ /dev/null
@@ -1,36 +0,0 @@
-## [ paddle 参数更多 ]torchvision.transforms.RandomCrop
-### [torchvision.transforms.RandomCrop](https://pytorch.org/vision/main/generated/torchvision.transforms.RandomCrop.html)
-```python
-torchvision.transforms.RandomCrop(
-    size: Union[int, List[int], Tuple[int, ...]],
-    padding: Optional[Union[int, List[int], Tuple[int, ...]]] = None,
-    pad_if_needed: bool = False,
-    fill: Union[float, Tuple[float, ...]] = 0,
-    padding_mode: str = 'constant'
-)
-```
-
-### [paddle.vision.transforms.RandomCrop](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/RandomCrop_cn.html)
-```python
-paddle.vision.transforms.RandomCrop(
-    size: Union[int, List[int], Tuple[int, ...]],
-    padding: Optional[Union[int, List[int], Tuple[int, ...]]] = None,
-    pad_if_needed: bool = False,
-    fill: Union[float, Tuple[float, ...]] = 0,
-    padding_mode: str = 'constant',
-    keys: Optional[Union[List[str], Tuple[str, ...]]] = None
-)
-```
-
-两者功能一致，但 Paddle 相比 torchvision 支持更多参数，具体如下：
-
-### 参数映射
-
-| torchvision | PaddlePaddle | 备注                                                         |
-| ------------- | -------------- | -------------------------------------------------------- |
-| size          | size          | 裁剪后的图片大小。                                           |
-| padding       | padding       | 对图像四周外边进行填充。                                  |
-| pad_if_needed | pad_if_needed | 是否在裁剪前进行填充以满足大小要求。                         |
-| fill          | fill          | 用于填充的像素值。                                        |
-| padding_mode  | padding_mode  | 填充模式。 |
-| -             | keys          | 输入的类型，PyTorch 无此参数，Paddle 保持默认即可。     |
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torchvision.transforms.ToTensor.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torchvision.transforms.ToTensor.md
deleted file mode 100644
index e4486c9d788..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torchvision.transforms.ToTensor.md
+++ /dev/null
@@ -1,19 +0,0 @@
-## [ paddle 参数更多 ]torchvision.transforms.ToTensor
-### [torchvision.transforms.ToTensor](https://pytorch.org/vision/main/generated/torchvision.transforms.ToTensor.html?highlight=totensor#torchvision.transforms.ToTensor)
-```python
-torchvision.transforms.ToTensor()
-```
-
-### [paddle.vision.transforms.ToTensor](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/ToTensor_cn.html#totensor)
-```python
-paddle.vision.transforms.ToTensor(data_format: str = 'CHW', keys: List[str] | Tuple[str] = None)
-```
-
-两者功能基本一致，但 Paddle 相比 torchvision 支持更多参数，具体如下：
-
-### 参数映射
-
-| torchvision | PaddlePaddle          | 备注                                   |
-|-------------- |-------------------- |----------------------------------- |
-| -              | data_format         | 返回 Tensor 的格式，PyTorch 无此参数，Paddle 保持默认即可。 |
-| -              | keys             | 输入的类型，PyTorch 无此参数，Paddle 保持默认即可。     |
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torchvision.transforms.functional.to_tensor.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torchvision.transforms.functional.to_tensor.md
deleted file mode 100644
index 03c0eeeeae6..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/paddle_more_args/torchvision.transforms.functional.to_tensor.md
+++ /dev/null
@@ -1,22 +0,0 @@
-## [ paddle 参数更多 ]torchvision.transforms.functional.to_tensor
-### [torchvision.transforms.functional.to_tensor](https://pytorch.org/vision/main/generated/torchvision.transforms.functional.to_tensor.html)
-```python
-torchvision.transforms.functional.to_tensor(pic: Union[PIL.Image.Image, numpy.ndarray])
-```
-
-### [paddle.vision.transforms.to_tensor](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/vision/transforms/to_tensor_cn.html)
-```python
-paddle.vision.transforms.to_tensor(
-    pic: Union[PIL.Image.Image, np.ndarray],
-    data_format: str = 'CHW'
-)
-```
-
-其中 Paddle 相比 PyTorch 支持更多其他参数，具体如下：
-
-### 参数映射
-
-| torchvision | PaddlePaddle | 备注                          |
-| --------- | ------------- | ------------------------------ |
-| pic       | pic           | 输入图像。                       |
-| -         | data_format   | 返回的 Tensor 的格式，PyTorch 无此参数，Paddle 保持默认即可。 |
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/torch_more_args/torch.Tensor.bernoulli.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/torch_more_args/torch.Tensor.bernoulli.md
deleted file mode 100644
index 75547c5ed61..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/torch_more_args/torch.Tensor.bernoulli.md
+++ /dev/null
@@ -1,32 +0,0 @@
-## [ torch 参数更多 ]torch.Tensor.bernoulli
-### [torch.Tensor.bernoulli](https://pytorch.org/docs/stable/generated/torch.Tensor.bernoulli.html#torch.Tensor.bernoulli)
-```python
-torch.Tensor.bernoulli(p=None, *, generator=None)
-```
-
-### [paddle.bernoulli](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/bernoulli_cn.html#bernoulli)
-```python
-paddle.bernoulli(x, p=None, name=None)
-```
-
-Pytorch 为 Tensor 类方法，Paddle 为普通函数，另外 PyTorch 相比 Paddle 支持更多其他参数。具体如下：
-
-
-### 参数映射
-
-| PyTorch       | PaddlePaddle | 备注                    |
-| ------------- | ------------ | ----------------------------------------------------------------------------- |
-| self      | x  | 伯努利参数 Tensor，将调用 torch.Tensor 类方法的 self Tensor 传入。  |
-| p         | p  | 可选，伯努利参数 p。 |
-| generator | -  | 用于采样的伪随机数生成器， Paddle 无此参数，一般对网络训练结果影响不大，可直接删除。    |
-
-
-### 转写示例
-#### self：调用类方法的 Tensor
-```python
-# PyTorch 写法
-x.bernoulli()
-
-# Paddle 写法
-paddle.bernoulli(x)
-```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/torch_more_args/torch.distributed.ReduceOp.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/torch_more_args/torch.distributed.ReduceOp.md
deleted file mode 100644
index 2d7a675e375..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/torch_more_args/torch.distributed.ReduceOp.md
+++ /dev/null
@@ -1,27 +0,0 @@
-## [ torch 参数更多 ]torch.distributed.ReduceOp
-### [torch.distributed.ReduceOp](https://pytorch.org/docs/stable/distributed.html?highlight=torch+distributed+reduceop#torch.distributed.ReduceOp)
-```python
-torch.distributed.ReduceOp
-```
-
-### [paddle.distributed.ReduceOp](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/distributed/ReduceOp_cn.html)
-```python
-paddle.distributed.ReduceOp
-```
-
-两者功能一致。
-
-其中，规约操作对应如下：
-
-### 参数映射
-
-|  PyTorch   | PaddlePaddle  | 备注 |
-|  ----  | ----  | --- |
-| SUM  | SUM | |
-| PRODUCT  | PROD | |
-| MIN | MIN | |
-| MAX | MAX | |
-| BAND | - | |
-| BOR | - | |
-| BXOR | - | |
-| PREMUL_SUM | -  | |
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/torch_more_args/torch.median.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/torch_more_args/torch.median.md
deleted file mode 100644
index 35e6f3ed736..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/torch_more_args/torch.median.md
+++ /dev/null
@@ -1,37 +0,0 @@
-## [ torch 参数更多 ]torch.median
-### [torch.median](https://pytorch.org/docs/stable/generated/torch.median.html?highlight=median#torch.median)
-```python
-torch.median(input,
-             dim=-1,
-             keepdim=False,
-             *,
-             out=None)
-```
-
-### [paddle.median](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/median_cn.html#median)
-```python
-paddle.median(x, axis=None, keepdim=False, mode='avg', name=None)
-```
-
-PyTorch 相比 Paddle 支持更多其他参数，具体如下：
-
-### 参数映射
-
-| PyTorch       | PaddlePaddle | 备注                                                   |
-| ------------- | ------------ | ------------------------------------------------------ |
-| <font color='red'> input </font> | <font color='red'> x </font> | 表示输入的 Tensor ，仅参数名不一致。  |
-| <font color='red'> dim </font> | <font color='red'> axis </font> | 表示进行运算的轴，仅参数名不一致。  |
-| keepdim       | keepdim      | 是否在输出 Tensor 中保留减小的维度。  |
-| -             | mode         | 当 x 在所需要计算的轴上有偶数个非 NaN 元素时，选择使用平均值或最小值确定非 NaN 中位数的值， PyTorch 无此参数，Paddle 需设置为 'min'。 |
-| <font color='red'> out </font> | -  | 表示输出的 Tensor ， Paddle 无此参数，需要转写。    |
-
-
-### 转写示例
-#### out：指定输出
-```python
-# PyTorch 写法
-torch.median([3, 5], out=y)
-
-# Paddle 写法
-paddle.assign(paddle.median([3, 5], mode='min'), y)
-```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/torch_more_args/torch.nanmedian.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/torch_more_args/torch.nanmedian.md
deleted file mode 100644
index 28203bf6177..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/torch_more_args/torch.nanmedian.md
+++ /dev/null
@@ -1,37 +0,0 @@
-## [ torch 参数更多 ]torch.nanmedian
-### [torch.nanmedian](https://pytorch.org/docs/stable/generated/torch.nanmedian.html?highlight=nanmedian#torch.nanmedian)
-```python
-torch.nanmedian(input,
-                dim=-1,
-                keepdim=False,
-                *,
-                out=None)
-```
-
-### [paddle.nanmedian](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/nanmedian_cn.html#nanmedian)
-```python
-paddle.nanmedian(x, axis=None, keepdim=False, mode='avg', name=None)
-```
-
-PyTorch 相比 Paddle 支持更多其他参数，具体如下：
-
-### 参数映射
-
-| PyTorch       | PaddlePaddle | 备注                                                   |
-| ------------- | ------------ | ------------------------------------------------------ |
-| <font color='red'> input </font> | <font color='red'> x </font> | 表示输入的 Tensor ，仅参数名不一致。  |
-| <font color='red'> dim </font> | <font color='red'> axis </font> | 表示进行运算的轴，仅参数名不一致。  |
-| keepdim       | keepdim         | 表示是否在输出 Tensor 中保留减小的维度。               |
-| -             | mode         | 当 x 在所需要计算的轴上有偶数个非 NaN 元素时，选择使用平均值或最小值确定非 NaN 中位数的值， PyTorch 无此参数，Paddle 需设置为 'min'。 |
-| <font color='red'> out </font> | -  | 表示输出的 Tensor ， Paddle 无此参数，需要转写。    |
-
-
-### 转写示例
-#### out：指定输出
-```python
-# PyTorch 写法
-torch.nanmedian(a, -1, out=y)
-
-# Paddle 写法
-paddle.assign(paddle.nanmedian(a, -1, mode='min'), y)
-```
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/torch_more_args/torch.nn.functional.softmax.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/torch_more_args/torch.nn.functional.softmax.md
deleted file mode 100644
index 0287897cb35..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/torch_more_args/torch.nn.functional.softmax.md
+++ /dev/null
@@ -1,21 +0,0 @@
-## [ torch 参数更多 ]torch.nn.functional.softmax
-### [torch.nn.functional.softmax](https://pytorch.org/docs/stable/generated/torch.nn.functional.softmax.html#torch.nn.functional.softmax)
-```python
-torch.nn.functional.softmax(input, dim=None, _stacklevel=3, dtype=None)
-```
-
-### [paddle.nn.functional.softmax](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/nn/functional/softmax_cn.html#softmax)
-```python
-paddle.nn.functional.softmax(x, axis=-1, dtype=None, name=None)
-```
-
-PyTorch 相比 Paddle 支持更多其他参数，具体如下：
-
-### 参数映射
-
-| PyTorch | PaddlePaddle | 备注                                                  |
-| --------- | -------------- | ----------------------------------------------------- |
-| input   |   x           |  表示输入张量，仅参数名不一致。           |
-| dim     | axis         |  表示对输入 Tensor 进行运算的轴，仅参数名不一致。            |
-| dtype   |   dtype      |  表示返回张量所需的数据类型。  |
-| _stacklevel | - | Paddle 无此参数，一般对网络训练结果影响不大，可直接删除。 |
diff --git a/docs/guides/model_convert/convert_from_pytorch/api_difference/torch_more_args/torch.optim.Optimizer.step.md b/docs/guides/model_convert/convert_from_pytorch/api_difference/torch_more_args/torch.optim.Optimizer.step.md
deleted file mode 100644
index d56ee5207fa..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/api_difference/torch_more_args/torch.optim.Optimizer.step.md
+++ /dev/null
@@ -1,18 +0,0 @@
-## [ torch 参数更多 ]torch.optim.Optimizer.step
-### [torch.optim.Optimizer.step](https://pytorch.org/docs/stable/generated/torch.optim.Optimizer.step.html#torch-optim-optimizer-step)
-```python
-torch.optim.Optimizer.step(closure)
-```
-
-### [paddle.optimizer.Optimizer.step](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/optimizer/Optimizer_cn.html#step)
-```python
-paddle.optimizer.Optimizer.step()
-```
-
-PyTorch 相比 Paddle 支持更多其他参数，具体如下：
-
-### 参数映射
-
-|  PyTorch   | PaddlePaddle |        备注        |
-|  --------  |  ----------  |  ----------------  |
-| closure |  -  | 重新评估模型并返回损失的闭包, Paddle 无此参数，暂无转写方式。 |
diff --git a/docs/guides/model_convert/convert_from_pytorch/tools/README.md b/docs/guides/model_convert/convert_from_pytorch/tools/README.md
index 6b0dccc91c5..6db38878bc1 100644
--- a/docs/guides/model_convert/convert_from_pytorch/tools/README.md
+++ b/docs/guides/model_convert/convert_from_pytorch/tools/README.md
@@ -81,8 +81,8 @@ paddle.Tensor.atan2(y, name=None)
 - `paddle API` 中 `paddle api` 和 `paddle signature` 解析结果是否一致；
 - `参数映射` 表格是否成功解析（表格每行 3 列）
 - 状态机结束状态：
-    - `无参数` 或 `组合替代实现`：允许无参数映射表
-    - `组合替代实现` 或更靠后的映射类型：允许无 **paddle API** 部分
+    - `仅 API 调用方式不一致` 或 `组合替代实现`：允许无参数映射表
+    - `仅 API 调用方式不一致` 或 `组合替代实现`：允许无 **paddle API** 部分
     - 其他类型：必须有所有结构
 
 通过设计这一系列约束，可以检查映射文档中粗心疏漏导致的错误，从而降低检查成本；此外，通过将文档解析得到结构化的元数据（`docs_mapping.json`），能为后续流程提供数据支持。
diff --git a/docs/guides/model_convert/convert_from_pytorch/tools/generate_api_difference.py b/docs/guides/model_convert/convert_from_pytorch/tools/generate_api_difference.py
deleted file mode 100644
index bc2897d96c2..00000000000
--- a/docs/guides/model_convert/convert_from_pytorch/tools/generate_api_difference.py
+++ /dev/null
@@ -1,608 +0,0 @@
-from __future__ import annotations
-
-import argparse
-import ast
-import contextlib
-import inspect
-import io
-import os
-import re
-import subprocess
-import sys
-import textwrap
-
-from utils import (
-    extract_no_need_convert_list,
-    get_paddle_url,
-    get_pytorch_url,
-    load_mapping_json,
-)
-
-
-class APIConversionError(Exception):
-    """自定义异常类，用于API转换过程中的错误"""
-
-    def __init__(self, message, api_name=None):
-        self.message = message
-        self.api_name = api_name
-        super().__init__(self.message)
-
-    def __str__(self):
-        return f"API Conversion Error for {self.api_name}: {self.message}"
-
-
-def get_function_signature(api_name: str, framework: str) -> str:
-    """
-    获取API的函数签名，支持普通函数、类方法、内置方法等
-
-    Args:
-        api_name: API的全限定名
-        framework: 框架名称
-
-    Returns:
-        函数签名字符串
-    """
-    # 导入框架
-    if framework == "torch":
-        import torch
-
-        module = torch
-    elif framework == "paddle":
-        import paddle
-
-        module = paddle
-    elif framework == "fairscale":
-        import fairscale
-
-        module = fairscale
-    elif framework == "transformers":
-        import transformers
-
-        module = transformers
-    elif framework == "torchvision":
-        import torchvision
-
-        module = torchvision
-    elif framework == "flash_attn":
-        import flash_attn
-
-        module = flash_attn
-    else:
-        raise ValueError("Invalid framework.")
-
-    # 解析API路径
-    parts = api_name.split(".")[1:]
-    api_obj = module
-
-    try:
-        for part in parts:
-            api_obj = getattr(api_obj, part)
-    except Exception as e:
-        raise ValueError(f"Failed to parse API path: {e}") from e
-
-    # 优先尝试inspect.signature（适用于普通函数和方法）
-    try:
-        # 处理类的情况（获取__init__方法）
-        if inspect.isclass(api_obj):
-            sig = inspect.signature(api_obj.__init__)
-            # 移除self参数
-            params = []
-            first_param = True
-            for name, param in sig.parameters.items():
-                if first_param and name == "self":
-                    first_param = False
-                    continue
-                first_param = False
-                params.append(format_param(param))
-
-            return f"{api_name}({', '.join(params)})"
-
-        # 处理普通函数和方法
-        sig = inspect.signature(api_obj)
-        params = [format_param(param) for param in sig.parameters.values()]
-        return f"{api_name}({', '.join(params)})"
-
-    except (ValueError, TypeError):
-        # 如果inspect失败，使用help信息解析
-        return parse_signature_from_help(api_obj, api_name)
-
-
-def format_param(param: inspect.Parameter) -> str:
-    """格式化参数，保留*和**符号"""
-    if param.kind == param.VAR_POSITIONAL:
-        return f"*{param.name}"
-    elif param.kind == param.VAR_KEYWORD:
-        return f"**{param.name}"
-    else:
-        return param.name
-
-
-def parse_signature_from_help(api_obj, api_name: str) -> str:
-    """从help信息中解析函数签名"""
-
-    # 捕获help输出
-    help_output = get_help_output(api_obj, api_name)
-    if not help_output:
-        return f"{api_name}(...)"
-
-    # 解析函数签名行
-    signature_line = extract_signature_line(help_output, api_name)
-    if signature_line:
-        return normalize_signature(signature_line, api_name)
-
-    return f"{api_name}(...)"
-
-
-def get_help_output(api_obj, api_name: str) -> str | None:
-    """获取API对象的help输出"""
-    try:
-        with io.StringIO() as buffer:
-            with contextlib.redirect_stdout(buffer):
-                help(api_obj)
-            return buffer.getvalue()
-    except:
-        raise APIConversionError(f"Failed to get help output for {api_name}")
-
-
-def extract_signature_line(help_text: str, api_name: str) -> str | None:
-    """从help文本中提取签名行"""
-    lines = help_text.split("\n")
-    base_name = api_name.split(".")[-1]
-
-    # 匹配模式：函数名后跟括号
-    patterns = [
-        # 匹配: numel(...) 或 forward(*args: Any, **kwargs: Any) -> Any
-        rf"^{re.escape(base_name)}\s*\([^)]*\)",
-        # 匹配: |  ZeroPad2d(padding: Union[int, tuple[int, int, int, int]]) -> None
-        rf"^\s*[\| ]*\w+\s+{re.escape(base_name)}\s*\([^)]*\)",
-        # 匹配类定义中的签名
-        rf"^class\s+\w+\(.*\):\s*\n\s*[\| ]*{re.escape(base_name)}\s*\([^)]*\)",
-    ]
-
-    for i, line in enumerate(lines):
-        for pattern in patterns:
-            if re.search(pattern, line.strip()):
-                # 对于多行签名，合并后续行直到遇到空行或缩进减少
-                signature = line.strip()
-                j = i + 1
-                while (
-                    j < len(lines)
-                    and lines[j].strip()
-                    and not lines[j].strip().startswith(("def ", "class "))
-                ):
-                    signature += " " + lines[j].strip()
-                    j += 1
-                return signature
-
-    raise APIConversionError(f"Failed to extract signature line for {api_name}")
-
-
-def normalize_signature(signature_line: str, api_name: str) -> str:
-    """规范化签名格式"""
-    # 提取括号内的内容
-    match = re.search(r"\(([^)]*)\)", signature_line)
-    if not match:
-        return f"{api_name}()"
-
-    params_str = match.group(1)
-
-    # 处理不同的参数格式
-    if params_str == "...":  # 如: numel(...)
-        return f"{api_name}()"
-
-    # 解析参数，移除类型注解和默认值
-    params = []
-    current_param = []
-    depth = 0  # 处理嵌套括号
-
-    for char in params_str + ",":  # 添加逗号确保处理最后一个参数
-        if char == "," and depth == 0:
-            param = "".join(current_param).strip()
-            if param:
-                # 提取参数名（移除类型注解）
-                param_name = extract_param_name(param)
-                if param_name:
-                    params.append(param_name)
-            current_param = []
-        else:
-            if char == "(":
-                depth += 1
-            elif char == ")":
-                depth -= 1
-            current_param.append(char)
-
-    # 处理特殊参数格式
-    final_params = []
-    for param in params:
-        if param.startswith("*") and param.endswith(": Any"):
-            # 处理 *args: Any, **kwargs: Any
-            param = param.replace(": Any", "")
-        elif "=" in param and not param.startswith("*"):
-            # 移除默认值，保留参数名
-            param = param.split("=")[0].strip()
-
-        final_params.append(param)
-
-    return f"{api_name}({', '.join(final_params)})"
-
-
-def extract_param_name(param_str: str) -> str | None:
-    """从参数字符串中提取参数名"""
-    param_str = param_str.strip()
-
-    if not param_str:
-        return None
-
-    # 处理可变参数 *args, **kwargs
-    if param_str.startswith("*") and param_str.endswith(": Any"):
-        return param_str.replace(": Any", "")
-
-    # 移除类型注解
-    if ":" in param_str:
-        # 找到第一个冒号（类型注解开始）
-        colon_pos = param_str.find(":")
-        param_name = param_str[:colon_pos].strip()
-
-        # 检查是否是可变参数
-        if param_name.startswith("*"):
-            return param_name
-        else:
-            return param_name
-    else:
-        # 没有类型注解，直接返回
-        return (
-            param_str.split("=")[0].strip() if "=" in param_str else param_str
-        )
-
-
-def find_test_file(torch_api: str, paconvert_dir: str) -> str:
-    """
-    在paconvert的tests目录中递归查找测试文件
-
-    Args:
-        torch_api: Torch API名称
-        paconvert_dir: paconvert目录路径
-
-    Returns:
-        测试文件路径
-    """
-    # 生成测试文件名（如：test_nn_functional_elu.py）
-    head = torch_api.split(".")[0]
-    if head == "flash_attn":
-        parts = torch_api.split(".")
-    else:
-        parts = torch_api.split(".")[1:]
-    file_name = "test_" + "_".join(parts) + ".py"
-
-    # 在tests目录中递归查找
-    test_dir = os.path.join(paconvert_dir, "tests")
-    for root, _, files in os.walk(test_dir):
-        if file_name in files:
-            return os.path.join(root, file_name)
-
-    raise APIConversionError(f"Test file not found for {torch_api}", torch_api)
-
-
-def extract_test_case_code(test_file: str) -> str:
-    """
-    从测试文件中提取第一个测试用例的pytorch代码
-
-    Args:
-        test_file: 测试文件路径
-
-    Returns:
-        提取的pytorch代码字符串
-    """
-    with open(test_file, "r", encoding="utf-8") as f:
-        content = f.read()
-
-    # 解析AST找到第一个测试函数
-    module = ast.parse(content)
-
-    for node in module.body:
-        if isinstance(node, ast.FunctionDef) and node.name.startswith("test_"):
-            # 在测试函数中查找pytorch_code的赋值语句
-            for item in node.body:
-                if isinstance(item, ast.Assign):
-                    for target in item.targets:
-                        if (
-                            isinstance(target, ast.Name)
-                            and target.id == "pytorch_code"
-                        ):
-                            # 检查赋值语句的值是否是函数调用
-                            if isinstance(item.value, ast.Call):
-                                call_func = item.value.func
-                                # 检查是否是textwrap.dedent调用
-                                if (
-                                    isinstance(call_func, ast.Attribute)
-                                    and isinstance(call_func.value, ast.Name)
-                                    and call_func.value.id == "textwrap"
-                                    and call_func.attr == "dedent"
-                                ):
-                                    # 获取dedent的第一个参数（应该是字符串）
-                                    if item.value.args and isinstance(
-                                        item.value.args[0], ast.Str
-                                    ):
-                                        # 返回字符串内容，去除首尾的三引号
-                                        code_str = item.value.args[0].s
-                                        return textwrap.dedent(code_str)
-
-                                    # 处理Python 3.8+的ast.Constant节点
-                                    elif (
-                                        item.value.args
-                                        and isinstance(
-                                            item.value.args[0], ast.Constant
-                                        )
-                                        and isinstance(
-                                            item.value.args[0].value, str
-                                        )
-                                    ):
-                                        code_str = item.value.args[0].value
-                                        return textwrap.dedent(code_str)
-
-    raise APIConversionError(f"Test case not found in {test_file}", test_file)
-
-
-def get_torch_example(torch_api: str, paconvert_dir: str) -> str:
-    """
-    获取Torch API的示例代码
-
-    Args:
-        torch_api: Torch API名称
-        paconvert_dir: paconvert目录路径
-
-    Returns:
-        Torch API调用代码
-    """
-    # 1. 查找测试文件
-    test_file = find_test_file(torch_api, paconvert_dir)
-
-    # 2. 提取测试用例代码
-    test_code = extract_test_case_code(test_file)
-
-    # 3. 写入临时文件
-    torch_temp_file = f"temp_generate_api_difference_{torch_api.replace('.', '_')}_torch_code.py"
-    with open(torch_temp_file, "w") as f:
-        f.write(test_code)
-
-    # 4. 使用paconvert补全代码
-    complete_file = f"temp_generate_api_difference_{torch_api.replace('.', '_')}_torch_code_complete.py"
-    try:
-        subprocess.run(
-            [
-                "python3.10",
-                os.path.join(paconvert_dir, "paconvert", "main.py"),
-                "-i",
-                torch_temp_file,
-                "-o",
-                complete_file,
-                "--only_complete",
-            ],
-            check=True,
-            capture_output=True,
-        )
-
-        # 5. 替换import paddle为import torch
-        with open(complete_file, "r") as f:
-            lines = f.readlines()
-
-        if lines and "import paddle" in lines[0]:
-            lines[0] = "import torch\n"
-
-        with open(complete_file, "w") as f:
-            f.writelines(lines)
-
-        # 6. 查找包含API调用的行
-        with open(complete_file, "r") as f:
-            for line in f:
-                if torch_api.split(".")[-1] in line:
-                    return line.strip()
-
-    except subprocess.CalledProcessError as e:
-        raise APIConversionError(
-            f"paconvert failed: {e.stderr.decode().strip()}", torch_api
-        ) from e
-
-    # 如果执行到这里，说明没有找到API调用
-    raise APIConversionError(
-        f"torch API call not found in converted code for {torch_api}", torch_api
-    )
-
-
-def get_conversion_example(
-    torch_code: str, torch_api: str, paddle_api: str, paconvert_dir: str
-) -> str:
-    """
-    使用paconvert转换Torch代码为Paddle代码
-
-    Args:
-        torch_code: Torch代码
-        torch_api: Torch API名称（用于临时文件命名）
-        paddle_api: Paddle API名称
-        paconvert_dir: paconvert目录路径
-
-    Returns:
-        Paddle API调用代码
-    """
-    # 1. 创建临时文件
-    temp_file = f"temp_generate_api_difference_{torch_api.replace('.', '_')}_torch_code_complete.py"
-    # with open(temp_file, "w") as f:
-    #     f.write(torch_code)
-
-    # 2. 运行paconvert转换
-    paddle_file = f"temp_generate_api_difference_{torch_api.replace('.', '_')}_paddle_code.py"
-    try:
-        subprocess.run(
-            [
-                "python3.10",
-                os.path.join(paconvert_dir, "paconvert", "main.py"),
-                "-i",
-                temp_file,
-                "-o",
-                paddle_file,
-            ],
-            check=True,
-            capture_output=True,
-        )
-
-        # 3. 查找包含API调用的行
-        with open(paddle_file, "r") as f:
-            for line in f:
-                if paddle_api.split(".")[-1] in line:
-                    return line.strip()
-
-    except subprocess.CalledProcessError as e:
-        raise APIConversionError(
-            f"paconvert conversion failed: {e.stderr.decode().strip()}",
-            torch_api,
-        ) from e
-
-    # 如果执行到这里，说明没有找到API调用
-    raise APIConversionError(
-        f"paddle API call not found in converted code for {torch_api}",
-        torch_api,
-    )
-
-
-def generate_invok_diff_only_docs(
-    output_dir: str, paconvert_dir: str, overwrite: bool = False
-):
-    """
-    生成"仅 API 调用方式不一致"类别的API差异文档
-
-    Args:
-        output_dir: 输出目录
-        paconvert_dir: PaConvert目录路径
-        overwrite: 是否覆盖已有文件
-    """
-    script_dir = os.path.dirname(os.path.abspath(__file__))
-
-    api_mapping_path = os.path.join(script_dir, "api_mapping.json")
-    attribute_mapping_path = os.path.join(script_dir, "attribute_mapping.json")
-    global_var_path = os.path.join(script_dir, "global_var.py")
-    no_need_list = extract_no_need_convert_list(global_var_path)
-
-    output_dir = os.path.join(script_dir, output_dir)
-
-    whitelist_api = [
-        "fairscale.nn.model_parallel.initialize.get_model_parallel_rank",
-        "fairscale.nn.model_parallel.initialize.get_model_parallel_world_size",
-        "flash_attn.__version__.split",
-    ]
-
-    # 读取API映射
-    api_mapping = load_mapping_json(api_mapping_path)
-    attribute_mapping = load_mapping_json(attribute_mapping_path)
-    api_mapping = api_mapping | attribute_mapping
-
-    # 定义属于invok_diff_only类别的Matcher
-    invok_diff_matchers = [
-        "ChangeAPIMatcher",
-        "TensorFunc2PaddleFunc",
-        "Func2Attribute",
-        "Attribute2Func",
-        "NumelMatcher",
-        "Is_InferenceMatcher",
-    ]
-
-    # 创建输出目录
-    test_output_dir = os.path.join(output_dir, "invok_diff_only")
-    actually_output_dir = os.path.join(
-        output_dir, "../../api_difference/invok_diff_only"
-    )
-    os.makedirs(test_output_dir, exist_ok=True)
-
-    # 生成文档
-    for torch_api, mapping in api_mapping.items():
-        if (
-            mapping.get("Matcher") in invok_diff_matchers
-            and torch_api not in whitelist_api
-            and torch_api not in no_need_list
-        ):
-            paddle_api = mapping["paddle_api"]
-            print(f"Processing: {torch_api} -> {paddle_api}")
-            # 生成文件名
-            file_name = f"{torch_api}.md"
-            file_path = os.path.join(test_output_dir, file_name)
-            if overwrite:
-                file_path = os.path.join(actually_output_dir, file_name)
-
-            try:
-                # 获取URL
-                torch_url = get_pytorch_url(https://github.com/torch_api)
-                paddle_url = get_paddle_url(https://github.com/paddle_api)
-
-                # 获取函数签名
-                module = torch_api.split(".")[0]
-                torch_signature = get_function_signature(torch_api, module)
-                paddle_signature = get_function_signature(paddle_api, "paddle")
-
-                # 生成转写示例
-                torch_example = get_torch_example(torch_api, paconvert_dir)
-                paddle_example = get_conversion_example(
-                    torch_example, torch_api, paddle_api, paconvert_dir
-                )
-
-                # 生成文档内容
-                content = f"## [ 仅 API 调用方式不一致 ]{torch_api}\n\n"
-                content += f"### [{torch_api}]({torch_url})\n\n"
-                content += "```python\n"
-                content += f"{torch_signature}\n"
-                content += "```\n\n"
-                content += f"### [{paddle_api}]({paddle_url})\n\n"
-                content += "```python\n"
-                content += f"{paddle_signature}\n"
-                content += "```\n\n"
-                content += "两者功能一致，但调用方式不一致，具体如下：\n\n"
-                content += "### 转写示例\n\n"
-                content += "```python\n"
-                content += f"# PyTorch 写法\n{torch_example}\n\n"
-                content += f"# Paddle 写法\n{paddle_example}\n"
-                content += "```\n"
-
-                # 保存文件
-                with open(file_path, "w", encoding="utf-8") as f:
-                    f.write(content)
-
-                print(f"Generated: {file_path}")
-
-            except APIConversionError as e:
-                print(f"ERROR: {e}", file=sys.stderr)
-                continue
-            except Exception as e:
-                print(f"UNEXPECTED ERROR: {e} for {torch_api}", file=sys.stderr)
-                continue
-
-
-def main():
-    parser = argparse.ArgumentParser(
-        description="Generate API difference documents for invok_diff_only category"
-    )
-    parser.add_argument(
-        "--output_dir",
-        type=str,
-        default="test",
-        help="Output directory for generated docs",
-    )
-    parser.add_argument(
-        "--paconvert_dir",
-        type=str,
-        default="/workspace/PaConvert",
-        help="Path to PaConvert directory",
-    )
-    parser.add_argument(
-        "--overwrite", action="https://github.com/store_true", help="Overwrite existing files"
-    )
-
-    args = parser.parse_args()
-
-    # 生成文档
-    generate_invok_diff_only_docs(
-        output_dir=args.output_dir,
-        paconvert_dir=args.paconvert_dir,
-        overwrite=args.overwrite,
-    )
-
-
-if __name__ == "__main__":
-    main()
diff --git a/docs/guides/model_convert/convert_from_pytorch/tools/generate_pytorch_api_mapping.py b/docs/guides/model_convert/convert_from_pytorch/tools/generate_pytorch_api_mapping.py
index 8d0a2088ba2..ff4b039c8f2 100644
--- a/docs/guides/model_convert/convert_from_pytorch/tools/generate_pytorch_api_mapping.py
+++ b/docs/guides/model_convert/convert_from_pytorch/tools/generate_pytorch_api_mapping.py
@@ -122,6 +122,7 @@ def generate_category1_table(
         rows.append((torch_api, col2, col3, mapping_category, "-"))
 
     # 生成Markdown表格字符串
+    rows = sorted(rows, key=lambda x: x[1].replace(r"\_", "_"))
     table_lines = TABLE_HEADER_LINES.copy()
 
     for idx, (_, col2, col3, mapping_category, remark) in enumerate(
@@ -242,6 +243,7 @@ def generate_category2_table(
             existing_apis.add(src_api)
 
     # 生成Markdown表格字符串
+    rows = sorted(rows, key=lambda x: x[1].replace(r"\_", "_"))
     table_lines = TABLE_HEADER_LINES.copy()
 
     for idx, (_, col2, col3, mapping_category, remark) in enumerate(
@@ -269,7 +271,7 @@ def generate_api_alias_table(
     # 遍历api_alias_data，为每个别名映射生成表格行
     for torch_api, torch_api_alias in api_alias_data.items():
         # 检查API是否已经在前面的类别中处理过
-        if torch_api in existing_apis or torch_api_alias in existing_apis:
+        if torch_api in existing_apis:
             continue
 
         # 在docs_mapping中查找torch_api_alias对应的Paddle API
@@ -309,9 +311,9 @@ def generate_api_alias_table(
         used_apis.add(torch_api)
         used_apis.add(torch_api_alias)
         existing_apis.add(torch_api)
-        existing_apis.add(torch_api_alias)
 
     # 生成Markdown表格字符串
+    rows = sorted(rows, key=lambda x: x[1].replace(r"\_", "_"))
     table_lines = TABLE_HEADER_LINES.copy()
 
     for idx, (_, col2, col3, mapping_category, remark) in enumerate(
@@ -370,6 +372,7 @@ def generate_no_implement_table(
         )
 
         # 检查API是否已经在前面的类别中处理过
+        torch_api = torch_api.replace(r"\_", "_")
         if torch_api in existing_apis:
             continue
 
@@ -409,9 +412,10 @@ def generate_no_implement_table(
         existing_apis.add(torch_api)
 
     # 生成Markdown表格字符串
+    rows = sorted(rows, key=lambda x: x[1].replace(r"\_", "_"))
     table_lines = TABLE_HEADER_LINES.copy()
 
-    for idx, (_, col2, col3, mapping_category, remark) in enumerate(
+    for idx, (torch_api, col2, col3, mapping_category, remark) in enumerate(
         rows, start=1
     ):
         table_lines.append(
@@ -449,6 +453,7 @@ def update_mapping_table(
         if api_name in existing_apis:
             continue
 
+        existing_apis.add(api_name)
         mapping_info = api_mapping_dict.get(api_name, {})
         dst_api = mapping_info.get("dst_api", "-")
 
diff --git a/docs/guides/model_convert/convert_from_pytorch/tools/get_api_difference_info.py b/docs/guides/model_convert/convert_from_pytorch/tools/get_api_difference_info.py
index d9f05fe029c..13f0f919a4e 100644
--- a/docs/guides/model_convert/convert_from_pytorch/tools/get_api_difference_info.py
+++ b/docs/guides/model_convert/convert_from_pytorch/tools/get_api_difference_info.py
@@ -15,47 +15,17 @@
 validate_whitelist = []
 
 mapping_type_levels = [
-    # type 0
-    ["UNDEFINED_MAPPING_TYPE_0"],
-    # type 1
     [
-        "无参数",
-        "参数完全一致",
         "仅 API 调用方式不一致",
         "仅参数名不一致",
         "paddle 参数更多",
         "参数默认值不一致",
-    ],
-    # type 2
-    [
-        "torch 参数更多",
-    ],
-    # type 3
-    [
         "返回参数类型不一致",
         "输入参数类型不一致",
         "输入参数用法不一致",
-    ],
-    # type 4
-    [
+        "torch 参数更多",
         "组合替代实现",
     ],
-    # type 5
-    [
-        "涉及上下文修改",
-    ],
-    # type 6
-    [
-        "对应 API 不在主框架",
-    ],
-    # type 7
-    [
-        "功能缺失",
-    ],
-    # delete
-    [
-        "可删除",
-    ],
 ]
 
 mapping_type_set = {t for ts in mapping_type_levels for t in ts}
@@ -477,7 +447,7 @@ def get_meta_from_diff_file(
                 )
 
     # 允许没有参数映射列表
-    if mapping_type in ["无参数", "组合替代实现", "仅 API 调用方式不一致"]:
+    if mapping_type in ["组合替代实现", "仅 API 调用方式不一致"]:
         if state == ParserState.wait_for_args:
             state = ParserState.end
     # 必须有参数映射列表，但是可以随时停止
@@ -491,8 +461,8 @@ def get_meta_from_diff_file(
         )
 
     # 允许的终止状态，解析完了 dst_api 或者只有 src_api
-    # 映射类型前三个级别必须要有对应的 dst_api
-    if mapping_type_to_level[mapping_type] <= 3:
+    # 映射类型除了 "组合替代实现" 和 "仅 API 调用方式不一致" 之外，其他的都必须有 dst_api
+    if mapping_type not in ["组合替代实现", "仅 API 调用方式不一致"]:
         if state != ParserState.end:
             print(state)
             raise Exception(
diff --git a/docs/guides/model_convert/convert_from_pytorch/tools/utils.py b/docs/guides/model_convert/convert_from_pytorch/tools/utils.py
index a54de7bcc04..ae6c83f5ee1 100644
--- a/docs/guides/model_convert/convert_from_pytorch/tools/utils.py
+++ b/docs/guides/model_convert/convert_from_pytorch/tools/utils.py
@@ -252,6 +252,11 @@ def parse_md_files(directories):
                     except Exception as e:
                         print(f"错误: 读取文件 {md_path} 时出错: {e!s}")
 
+    for category, apis in category_api_map.items():
+        category_api_map[category] = sorted(
+            apis, key=lambda x: x["api_name"].replace(r"\_", "_")
+        )
+
     return category_api_map
 
 
diff --git a/docs/install/compile/arm-compile.md b/docs/install/compile/arm-compile.md
index 37c800edd71..d65cd4702c3 100644
--- a/docs/install/compile/arm-compile.md
+++ b/docs/install/compile/arm-compile.md
@@ -52,7 +52,7 @@
     sudo make install
     ```
 
-3. 根据[requirments.txt](https://github.com/PaddlePaddle/Paddle/blob/develop/python/requirements.txt)安装 Python 依赖库，在飞腾加国产化操作系统环境中，pip 安装可能失败或不能正常工作，主要依赖通过源或源码安装的方式安装依赖库，建议使用系统提供源的方式安装依赖库。
+3. 根据[requirements.txt](https://github.com/PaddlePaddle/Paddle/blob/develop/python/requirements.txt)安装 Python 依赖库，在飞腾加国产化操作系统环境中，pip 安装可能失败或不能正常工作，主要依赖通过源或源码安装的方式安装依赖库，建议使用系统提供源的方式安装依赖库。
 
 4. 将 Paddle 的源代码克隆到当下目录下的 Paddle 文件夹中，并进入 Paddle 目录
 
diff --git a/docs/install/compile/mips-compile.md b/docs/install/compile/mips-compile.md
index 97b04492c98..47736d5a23d 100644
--- a/docs/install/compile/mips-compile.md
+++ b/docs/install/compile/mips-compile.md
@@ -76,7 +76,7 @@
     cd Paddle
     ```
 
-6. 根据[requirments.txt](https://github.com/PaddlePaddle/Paddle/blob/develop/python/requirements.txt)安装 Python 依赖库。
+6. 根据[requirements.txt](https://github.com/PaddlePaddle/Paddle/blob/develop/python/requirements.txt)安装 Python 依赖库。
 
 
 7. 切换到`develop`分支下进行编译：
diff --git a/docs/install/compile/sw-compile.md b/docs/install/compile/sw-compile.md
index 20e2cf161a5..04efcc8f4ec 100644
--- a/docs/install/compile/sw-compile.md
+++ b/docs/install/compile/sw-compile.md
@@ -48,7 +48,7 @@
    -- Found lapack in OpenBLAS (include: /usr/include)
    ```
 
-5. 根据[requirments.txt](https://github.com/PaddlePaddle/Paddle/blob/develop/python/requirements.txt)安装 Python 依赖库，注意在申威系统中一般无法直接使用 pip 或源码编译安装 python 依赖包，建议使用源的方式安装，如果遇到部分依赖包无法安装的情况，请联系操作系统服务商提供支持。此外也可以通过 pip 安装的时候加--no-deps 的方式来避免依赖包的安装，但该种方式可能导致包由于缺少依赖不可用。
+5. 根据[requirements.txt](https://github.com/PaddlePaddle/Paddle/blob/develop/python/requirements.txt)安装 Python 依赖库，注意在申威系统中一般无法直接使用 pip 或源码编译安装 python 依赖包，建议使用源的方式安装，如果遇到部分依赖包无法安装的情况，请联系操作系统服务商提供支持。此外也可以通过 pip 安装的时候加--no-deps 的方式来避免依赖包的安装，但该种方式可能导致包由于缺少依赖不可用。
 
 6. 请创建并进入一个叫 build 的目录下：