The score for the same picture varies about neural-image-assessment

[yunxiaoshi]

Try add

torch.backends.cudnn.deterministic = True

and

torch.cuda.manual_seed_all(seed)

to see if you can get consistent results. If not then according to https://pytorch.org/docs/stable/notes/randomness.html

Completely reproducible results are not guaranteed across PyTorch releases, individual commits, or different platforms. Furthermore, results may not be reproducible between CPU and GPU executions, even when using identical seeds.

[yier2333]

Try add

torch.backends.cudnn.deterministic = True

and

torch.cuda.manual_seed_all(seed)

to see if you can get consistent results. If not then according to https://pytorch.org/docs/stable/notes/randomness.html

Completely reproducible results are not guaranteed across PyTorch releases, individual commits, or different platforms. Furthermore, results may not be reproducible between CPU and GPU executions, even when using identical seeds.

not train model, I use your pretrained model to infer my image many times, but get different value

[yier2333]

I found the problem, your test_transform should use CenterCrop not RandomCrop

[wcc17864158993]

Try add

torch.backends.cudnn.deterministic = True

and

torch.cuda.manual_seed_all(seed)

to see if you can get consistent results. If not then according to https://pytorch.org/docs/stable/notes/randomness.html

Completely reproducible results are not guaranteed across PyTorch releases, individual commits, or different platforms. Furthermore, results may not be reproducible between CPU and GPU executions, even when using identical seeds.

Can you tell me how you downloaded the dataset and decompress it?

[cherryolg]

Hello, when I want to test my image, how does test_labels.csv get generated? What does test_labels.csv mean? Looking forward to your answer!