Anthony Chen

I use the following code to implement adversarial classifier on cifar100 ``` transform_train_cifar = transforms.Compose([ transforms.RandomCrop(32, padding=4), transforms.RandomHorizontalFlip(), transforms.ToTensor(), transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)), ]) traindataset = datasets.CIFAR10(root, transform_train_cifar)...

which celebrities did you use in training?

1

Hi author, Thanks for the great work! After trying out the demo, I found that the model works better on non-asian faces, so I wonder how is the distribution like...

Checkpoint & Training Code Release

1

Thanks for the great work! I had seen that you said you will release the training code in the future, but I wonder if there is a estimated time for...

Greak work! But i have a problem when finetuning the model. I added the following code in `main/trainer.py` file, trying to inspect the gradients for the dynamicrafter model when fintuning...