Open yier2333 opened 3 years ago
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
I found the problem, your test_transform should use CenterCrop not RandomCrop
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?
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!
Try add
and
to see if you can get consistent results. If not then according to https://pytorch.org/docs/stable/notes/randomness.html