Closed cristyioan2000 closed 5 years ago
@cristyioan2000, I think you may need to add the structure file as the model.py, e.g. resnet.py and import the structure in the training file.
I was thinking that I can create a checkpoint file
checkpoint_file = {
'model': Some_Model_Class(),
'weights':model.state_dict()
}
torch.save(checkpoint_file,'architecture.pth')
I'm going to try both ways and post the result.
Hello,
I want to load the found architecture in a different script, is there a way to load the architecture structure(class) and the .weight file externally, just by importing using torch.load() ?
Thanks