Closed zjysteven closed 3 years ago
Thank you very much for pointing out this. This is a bug I made during code cleaning.
OK, thanks for the clarification!
@geekJZY Sorry to bother you again, but would you mind revealing a little bit about how the learning rate is chosen (the default value for LARS optimizer is 5.0 in the code)? Are you following something like linear scaling (e.g. a base learning rate * Batch Size / 256)? I'm having this question because most contrastive learning papers are taking ImageNet as the benchmark and don't tell much about the learning rate setup for CIFAR10. Any suggestions would be appreciated!
For CIFAR-10 learning rate, we grid search it under the standard training setting and choose the one yield the best linear eval accuracy.
Hi,
Thanks for releasing the code! I have a minor question on which some clarification would be appreciated. The code for
proj_head
seems to have an inconsistency. IftwoLayerProj
is True, thenself.fc3
andself.bn3
would not be initialized, while in the forward pass they would be called. Is it that I miss something? Thanks!https://github.com/VITA-Group/Adversarial-Contrastive-Learning/blob/a7e6d48686826b856a9f16dcc5cb8b2c70bd084a/models/resnet_multi_bn.py#L192-L194
https://github.com/VITA-Group/Adversarial-Contrastive-Learning/blob/a7e6d48686826b856a9f16dcc5cb8b2c70bd084a/models/resnet_multi_bn.py#L210-L214