目录
pb转tflite:
import tensorflow as tf
path="output_graph.pb"
inputs=["Placeholder"]
classes=["final_result"]
converter = tf.contrib.lite.TocoConverter.from_frozen_graph(path, inputs, classes)
tflite_model=converter.convert()
open("output_graph.tflite","wb").write(tflite_model)
获取 tflite 输入输出:
import numpy as np
import tensorflow as tf
# Load TFLite model and allocate tensors.
interpreter = tf.lite.Interpreter(model_path="converted_model.tflite")
interpreter.allocate_tensors()
# Get input and output tensors.
input_details = interpreter.get_input_details()
output_details = interpreter.get_output_details()
# Test model on random input data.
input_shape = input_details[0]['shape']
input_data = np.array(np.random.random_sample(input_shape), dtype=np.float32)
interpreter.set_tensor(input_details[0]['index'], input_data)
interpreter.invoke()
output_data = interpreter.get_tensor(output_details[0]['index'])
print(output_data)
获取模型 json文件:
def gen_model_json(flatc_path, model_output_path, jsonfile_path, schema_path, model_path):
if not os.path.exists(jsonfile_path):
cmd = (f'{flatc_path} -t --strict-json --defaults-json -o . {schema_path} -- {model_path}')
print(f'output json command = {cmd}')
os.system(cmd)
本文介绍了如何使用TensorFlow将protobuf (.pb)模型转换为TensorFlow Lite (tflite)格式,并提供了获取模型输入和输出的示例。此外,还展示了如何从模型json文件进行操作。
3960

被折叠的 条评论
为什么被折叠?



