You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi, I am current test linknet on pytorch 0.41, but the model trained can not load to test:
ile "demo.py", line 95, in predict
model.load_state_dict(m['state_dict'])
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 719, in load_state_dict
self.__class__.__name__, "\n\t".join(error_msgs)))
RuntimeError: Error(s) in loading state_dict for LinkNet:
Missing key(s) in state_dict: "in_block.0.weight", "in_block.1.weight", "in_block.1.bias", "in_block.1.running_mean", "in_block.1.running_var", "encoder1.0.conv1.weight",
Many thanks if any clue can be provide!
BTW, the model can be resume which is really wierd.....
The text was updated successfully, but these errors were encountered:
This model was trained an older version of PyTorch (may be 0.2x). Most likely you will have to create a new dictionary and copy the weights one by one for each layer with updated keys.
Hi, I am current test linknet on pytorch 0.41, but the model trained can not load to test:
Many thanks if any clue can be provide!
BTW, the model can be resume which is really wierd.....
The text was updated successfully, but these errors were encountered: