DengMiao55

@DavideA thank you，it‘s useful。 but I can't use the batch_size mentioned in the paper 。Do I need to use multiple GPUs？

@DavideA Hi，I try to recurring your result in cifar ，but I only get AUC 0.6. could you tell me more about the detail about training。 thanks

@samet-akcay python train.py --dataset cifar10 --abnormal_class ariplane when I print the net ,I also find the discriminator‘s structure is not same as the paper。 it lacks the fourth conv 。512。...

@samet-akcay ， I find the second question is in skipganomaly . And in skipganoamly,is the discriminator loss right? I think it shouldn't have err_g_lat