I am trying to deploy my flask application using Docker, but before running it in a container, I would like to verify that it works in a linux environment.
After installing all the packages in the right versions (pytorch 1.6, torchtext 0.7.0) as I did in windows, I get the following error for my exported model:
untimeError: Error(s) in loading state_dict for RNN:
size mismatch for embedding.weight: copying a param with shape torch.Size([101616, 100]) from checkpoint, the shape in current model is torch.Size([100944, 100]).
How can i fix this?