New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
The model collapse when use moco loss #50
Comments
I notice in the paths_config.py, you are using
However, in the README, google drive link download the pretrained_models/moco_v2_800ep_pretrain.pt |
Using the MoCo model that was uploaded to the Google Drive should be the correct version. It is possible that the config is incorrect and the correct path should be |
OK. Thanks. |
Sorry. it seems the pt version of Moco still has the same problem. |
Can you please provide the error you're getting with the MoCo model? |
Oh. I don't think your problem is the MoCo loss then. You should be able to disable it completely by setting the lambda value to 0. But I don't think this will necessarily solve your problem. |
I've been using pixel2style2pixel for few times with the model, and it works well. The only unsatisfaction is the inversion details are not as good as the optimization method(The optim method can perfectly invert the real image). |
It is interesting that the results you got with pSp are better than ReStyle. Did you use the same loss weights in both cases? |
I just use l2 and lpips loss. And I've tried using id loss, which shows a comparable result. But when I add moco loss, the synthetic image starts to become worse. I'm not sure why, but I'll keep my eyes on the problem. Thank you. |
It does make some sense that the moco loss may lead to unsatisfactory results because MoCo was pretrained on ImageNet which is quite different from your data. Have you tried disabling the moco loss by setting the lambda value to 0? |
Yes, I'm trying to disable Moco loss and right now the training goes well. |
Hi Yuval,
When I train my datasets with the configuration you recommended, the model seems to collapse after just a few iterations(As shown below). However, when I set the moco lambda as 0.0001, there is no problem so far. So do you have any clue why that happens? Is there a way to disable the moco loss totally? (when I set the moco loss as 0, it seems you bind the id_logs with the moco_loss calculation)
The text was updated successfully, but these errors were encountered: