tianyu0207 / igd Goto Github PK

In p32.ssim_main, there isreal_data = data_tmp.reshape(-1, 3, 32, 32). However, when computing the mssim the image size should be larger than 32. How to solve this problem?

Hello, amazing work!

I am currently trying to reimplement the paper and I stumbled upon a problem when computing the GSVDD classifier loss.

This is what I have:

• Latent/encoded vector of shape=(1, Z), the input from the current batch;
• Mean vector of shape=(1, Z), calculated in the E step from all samples;
• Standard deviation vector of shape=(1, Z), calculated in the E step from all samples.

Now when I calculate the GSVDD classifier loss I end up with a loss that is also (1, Z), should I average it to get a single value? I'm probably missing a key point here.

How to make a model's prediction on new images? Thanks

No such file or directory: './Encoder_lr_scheduler_ckpt'

unresolved reference from ssl_pretrain.resnet_cifar import * from ssl_pretrain.models import ContrastiveModel

Could you open source code about anomaly location? or give me some ideas about location of anomaly detction by IGD?