Pytorch1.1版本pytorch模型转onnx的bug

最新推荐文章于 2026-05-18 08:12:28 发布

原创

最新推荐文章于 2026-05-18 08:12:28 发布 · 6.9k 阅读

收录于

当前文章被以下社区和专栏收录：

在Pytorch 1.1版本中，尝试将模型转换为ONNX格式时遇到一个错误，具体是由于默认的upsampling行为改变导致。错误提示建议在upsample操作中指定align_corners=True。解决此问题的方法是回退到Pytorch 1.0版本。通过直接安装指定版本的Pytorch和torchvision，可以避免因版本不兼容而重新安装高版本Pytorch的问题。

Bug in pytorch 1.1:

/usr/local/lib/python3.5/dist-packages/torch/nn/functional.py:2539: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details.
"See the documentation of nn.Upsample for details.".format(mode))
Traceback (most recent call last):
File "/usr/local/lib/python3.5/dist-packages/torch/onnx/__init__.py", line 19, in _export
    result = utils._export(*args, **kwargs)
File "/usr/local/lib/python3.5/dist-packages/torch/onnx/utils.py", line 363, in _export
    _retain_param_name, do_constant_folding)
File "/usr/local/lib/python3.5/dist-packages/torch/onnx/utils.py", line 278, in _model_to_graph
    _disable_torch_constant_prop=_disable_torch_constant_prop)
File "/usr/local/lib