Open vipul109 opened 3 years ago
Large gap between validation and test is somewhat strange. Anyway, I think there will be not many methods that can be applied to reduce such large overfitting.
Rosinality, Thanks for the reply. Could you point me to the public datasets which have worked for you? Did you experiment with FFHQ dataset?
I have tried to train on FFHQ.
Rosinality, For FFHQ, Did you follow the setting mentioned in the paper ? What is the best accuracy you achieved?
No, model in the paper is too large to use in my environments. In my cases I got 45% training accuracies for top level codes.
Hi,Thank you for your VQ-vae2 PyTorch version! If I want to achieve the results in the paper, what should I do? Just change the holistic architecture bottom+top to bottom+middle+top? Thank you for your reply!
@wwlCape If you want to try 1024 model then you need to use bottom + middle + top models, and larger pixelsnail model. But I don't know this repository can replicate the results in the paper.
OK, Thanks for your reply!
Hi , First of all thanks for the implementation.
I have tried to train PixelSNAIL-bottom/top prior for 256(imagenet) and 512(gaming) resolution images but I found that both the models are causing overfitting issue .
Bottom-prior (Average train accuracy = 0.77 , validation accuracy: 0.67, test accuracy: 0.37), where train and validation split(9:1) from same datset of 5k images of 512*512 , testing data is another dataset of same class.
Top-prior (Average train accuracy = 0.97180 , validation: 0.88 , testing accuracy: 0.4 ) rest of the settings are same as bottom prior.
I have tried to use l2 regularization, augmentation dataset along with existing dropout but no success. Any lead would be helpful. Thanks in advance.