Open YIBO-0805 opened 2 years ago
We didn't tune that hyper-parameter during the experiments. Perhaps a proper weight decay could further improve the performance.
But I get only 72.3% accuracy on cifar10 dataset. I run it in pytorch1.9.0+cuda11.4.
Maybe it is due to the different environment and random seed. The config we provided is exactly the one we used to produce the result reported in the paper. You may check the code again to make sure no additional modification is made and rerun the code with a different random seed.
We didn't tune that hyper-parameter during the experiments. Perhaps a proper weight decay could further improve the performance.
What might be an appropriate weight decay for CIFAR10?
We didn't tune that hyper-parameter in our experiments. You may try the commonly used 1e-3 or 1e-4.
Why the parameter 'weight_decay' set in code is 0.