slala2121

No but the issue can be closed since I found a workaround. On Wed, Oct 21, 2020 at 1:22 AM zzb112233 wrote: > Platform (like ubuntu 16.04/win10): ubuntu 16.04 >...

I just loaded the weights using the tf graph. Then I wrote a script to map those weights to a corresponding pytorch graph. You can do this by inspecting the...

Using the ensemble of pretrained models, I get AUC of 0.91 on the test dataset rather than 0.95. I followed the instructions in downloading the dataset. Should I be getting...

Could you explain how the contrastive accuracy is computed? I could understand the potential for overfitting if it's measured on samples different from the those used to compute the training...

Okay. Then I'm not sure why overfitting would occur since the accuracy is measured over the same samples as the training dataset.

Thanks. Also the paper mentions it uses EMA of 0.99 and memory buffer of 64. What do these hyperparameters correspond to and how can they be set in the code?