shimazing

Results 6 comments of shimazing

Adaptation leads to lower precision.

I got a similar result to @Tianlin-Gao with office31 dataset. I freezed 1~4th conv blocks of ResNet50 and trained only the 5th block and the classifier, same config (for discriminator:...

Is the CNN version code trained well?

My conjecture is that the optimization step makes spectral norm larger than 1 and your code uses sigma calculated in the training phase to normalize it. It changes weight in...

Is the CNN version code trained well?

Thanks for updating!! :) However, I still have a problem and have a question. what is "weight_orig" parameter for? With assertion check, I've noticed that weight and weight_orig have different...

Is the CNN version code trained well?

@lingzenan Do you run the code with DataParallel??

Is the CNN version code trained well?

@jarrelscy I still have a problem even with the updated version. Have you run the code with DataParallel?

Is the CNN version code trained well?

I also found it runs correctly with a single gpu and net.train() under torch.no_grad().