GPU requirement for training One-class ImageNet-30

[gdwang08]

Thanks for the nice work! I have one question about the image size you used in one-class ImageNet-30 setting. I used four 3080ti gpus with a batch-size of 32 for each gpu, raising out of memory error. I assume the actual batch size for each gpu is 32 * 4 (four rotations) * 2 (2 views) = 256. So the input tensor has as size of (256, 3, 224, 224)?