How to load saved model in google colab?

1

I saved my model like this:

torch.save({
            'epoch': all_epochs,
            'Gmodel_state_dict': gen.state_dict(),
            'Dmodel_state_dict': crit.state_dict(),
            'G_optimizer':gen_opt.state_dict(),
            'D_optimizer':crit_opt.state_dict()
            }, 'WGAN-GP-lr1-0.0002.pt')

For loading the model I wrote these lines of code:

checkpoint = torch.load('WGAN-GP-lr1-0.0002.pt')
gen.load_state_dict(checkpoint['Gmodel_state_dict']) # Load Generator model
crit.load_state_dict(checkpoint['Dmodel_state_dict']) # load Discriminator model
gen_opt.load_state_dict(checkpoint['G_optimizer']) # Load Generator's optimizer
crit_opt.load_state_dict(checkpoint['D_optimizer']) # Load Discriminator's optimizer
previous_epochs = checkpoint['epoch']
epoch_flag = True
print("Number of Epochs after training:",previous_epochs)

During loading the model I am getting this error:

RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory

I don’t have any idea why this error is occurring and how would I resolve it. Kindly guide me. Any help shall be highly appreciated.

Note: I am loading and saving the model in google colab.

2

I have question in this regard
If we save model on gpu machine and then want to load that model on google colab why it throws “PytorchStreamReader failed reading zip archive: failed finding central directory” error?

3

This error could be raised if the checkpoint file is corrupt and thus the reading fails. Could you check the file size of the stored checkpoint and the one used in Colab? Also, try to save a new checkpoint and load it in your other setup.