By default, the best model and the last model are saved by catalyst as checkpoints. For example, I have the following files in thecheckpoints folder:

model.0049.pthmodel.best.pthmodel.last.pthmodel.storage.json

I then use the following code to read the checkpoint.

checkpoint=utils.load_checkpoint(path=os.path.join(model_dir,'model.best.pth'))checkpoint.keys()# the output is: odict_keys(['model.0.weight', 'model.0.bias', 'model.2.weight', 'model.2.bias', 'model.4.weight', 'model.4.bias'])

The obtainedcheckpoint contains weights and bias values for each linear layer (the underlying net is just a MLP).

Now the question is how I can restore the network model withcheckpoint. I can't work withutils.unpack_checkpoint(checkpoint, best_model) since it depends on the 'model_state_dict' key but ourcheckpoint above does not have it.

Is there any method inutils handling this task? Or do I have to make it manually with PyTorch methods?