pytorch-neural-style-transfer-johnson icon indicating copy to clipboard operation
pytorch-neural-style-transfer-johnson copied to clipboard

Published 20 hours ago • verified publisher icon gordicaleksa

Is it possible to also load from the last saved checkpoint in case the training failed at some point?

Open tdbe opened this issue 4 years ago • 0 comments

I see you are saving checkpoints every x amount of batches. (I am new to this) Why exactly are you saving checkpoints if as far as I can see there isn't anything to load them later? Is it so that the anaconda TensorBoard has something to show?

tdbe avatar Jun 20 '21 10:06 tdbe