dynamic-soft-margin-pytorch Running the script multiple times, the results are different.

Hello, thank you! I get some questions when i run your script. detailed: Running the script multiple times, the results are different.

Looking forward to your reply! Thank you!

Dec 19 '19 12:12 lovekittynine

Do you mean training or inference? Inference results should not change unless your update PyTorch or cudnn. Training results are not guaranteed to be consistent (because it's SGD) but they should be close enough.

Dec 20 '19 17:12 lg-zhang

thanks for your reply!In training stage, even though i set random seed,the results are different each time!Other works,such as Hardnet,it can get same training results,when set identical random seed.

Dec 21 '19 05:12 lovekittynine

Could you specify what random seeds have you set? To make training deterministic, normally you need to fix seeds for pytorch, random, np.random and also set cudnn to deterministic mode.

Dec 23 '19 18:12 lg-zhang

np.random.seed(0) torch.cuda.manual_seed(0) torch.backends.cudnn.deterministic=True

Dec 24 '19 05:12 lovekittynine

Could you try: random.seed(0)?

Dec 24 '19 05:12 lg-zhang