search

tbepler / protein-sequence-embedding-iclr2019

Source code for "Learning protein sequence embeddings using information from structure" - ICLR 2019
Other
253 stars 75 forks source link

Warning in Pytorch 1.0.0 #17

Closed DaHaiHuha closed 4 years ago

DaHaiHuha commented 4 years ago

I used the code & model weights in original repo to reproduce the performance in the paper, using python3.7 and torch1.0.0, and I got following warnings.

/*/anaconda3/lib/python3.7/site-packages/torch/serialization.py:434: SourceChangeWarning: source code of class 'torch.nn.modules.sparse.Embedding' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
  warnings.warn(msg, SourceChangeWarning)
/*/anaconda3/lib/python3.7/site-packages/torch/serialization.py:434: SourceChangeWarning: source code of class 'torch.nn.modules.dropout.Dropout' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
  warnings.warn(msg, SourceChangeWarning)
/*/anaconda3/lib/python3.7/site-packages/torch/serialization.py:434: SourceChangeWarning: source code of class 'torch.nn.modules.container.ModuleList' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
  warnings.warn(msg, SourceChangeWarning)
/*/anaconda3/lib/python3.7/site-packages/torch/serialization.py:434: SourceChangeWarning: source code of class 'torch.nn.modules.rnn.LSTM' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
  warnings.warn(msg, SourceChangeWarning)
/*/anaconda3/lib/python3.7/site-packages/torch/serialization.py:434: SourceChangeWarning: source code of class 'torch.nn.modules.linear.Linear' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
  warnings.warn(msg, SourceChangeWarning)
/*/anaconda3/lib/python3.7/site-packages/torch/serialization.py:434: SourceChangeWarning: source code of class 'torch.nn.modules.activation.ReLU' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
  warnings.warn(msg, SourceChangeWarning)
/*/anaconda3/lib/python3.7/site-packages/torch/serialization.py:434: SourceChangeWarning: source code of class 'src.models.multitask.OrdinalRegression' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
  warnings.warn(msg, SourceChangeWarning)
/*/anaconda3/lib/python3.7/site-packages/torch/serialization.py:434: SourceChangeWarning: source code of class 'src.models.multitask.ConvContactMap' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
  warnings.warn(msg, SourceChangeWarning)
/*/anaconda3/lib/python3.7/site-packages/torch/serialization.py:434: SourceChangeWarning: source code of class 'torch.nn.modules.conv.Conv2d' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
  warnings.warn(msg, SourceChangeWarning)

However, I do not know whether this would cause a bad consequence, anyone has any ideas? Very appreciate!

tbepler commented 4 years ago

This shouldn't be a problem. AFAIK pytorch made some code changes between 0.4 and 1.0 that cause this warning to be raised when loading a model in 1.0 that was serialized with 0.4. If you want to get rid of this warning, you can resave the models with some code like:

model = torch.load(old_model_path)
torch.save(model, new_model_path)

Loading the resaved models won't give the warning.

DaHaiHuha commented 4 years ago

@tbepler Thanks for your kind reply, I'll close this issue.