I traind a model for 25 epochs and saved the model and optimizer like this:
checkpoint = {'model': trainer.model.state_dict(),
'optim': trainer.optimizer,
'epoch': epoch}
torch.save(checkpoint, PATH))
Now I want to load this checkpoint and continue to train the model for 50 epochs:
model.load_state_dict(checkpoint['model'])
optimizer = checkpoint['optim']
I didn’t change other parts of the code and the program runs good without any exception. But later I noticed that the arguments of the model won’t update, even when I use model.train()
and criterion.backward()
. Anybody knows why?