michaelku1

Thanks for the quick reply, I will give it a try.

So I have tried lower discriminator loss weights but still got the same bug, I will look further into it.

just to double check, this is my current config param settings for clipart, which follows paper's numbers: 

> @michaelku1 Where did you set the discriminator weight? I don't see this parameter in your config? You manually edit it in the code? I passed it at the cmd...

So the error occured at iterations>14000 for clipart and >39000 for watercolor. I think my datasets are fine since I was able to train them on yjliu's unbiased teacher (by...

> I think it makes some sense for the iterations, yet I think I have to see if the current code is consistent as the version I run in Meta...

It's training well when I use 0.01 for domain loss weight, which makes sense as domain losses are high for source and target during mutual learning, will close this issue...

Performance is poor so far (e.g watercolor has AP around 29 for the best performance which is at iter=20k). Is it possible that the pre-trained weights be released?

So I was reporting the leftmost AP value (there are three) in the log file which shows “AP,” not [email protected].

I see. In that case the numbers are indeed close to the papers. I just realized for coco evaluator AP50 is the correct metric to look at for pascal voc...