FeatherNets_Face-Anti-spoofing-Attack-Detection-Challenge-CVPR2019 icon indicating copy to clipboard operation
FeatherNets_Face-Anti-spoofing-Attack-Detection-Challenge-CVPR2019 copied to clipboard

Published 20 hours ago • verified publisher icon SoftwareGift

train_dataset and val_dataset processing is different? why?

Open Melonia-H opened this issue 5 years ago • 0 comments 

train_dataset = CASIA(
        transforms.Compose([
            transforms.RandomResizedCrop(img_size),
            transforms.RandomHorizontalFlip(),
            transforms.ToTensor(),
            ColorAugmentation(),
            normalize,
        ]),phase_train=True)
    val_dataset = CASIA( transforms.Compose([
        transforms.Resize(int(256 * ratio)),
        transforms.CenterCrop(img_size),
        transforms.ToTensor(),
        normalize,
    ]),phase_train=False,phase_test=args.phase_test)

Melonia-H avatar Oct 24 '19 07:10 Melonia-H