Zhang Mingkun

Why use zero_module?

2

Thanks for your code for the project! It is a really nice work! I am confused about why using zero_module, may lead to the zero_grad between the input and the...

The grad of training loss with respect to z_{sem} is zero

2

First, thanks for your excellent work! I've reproduced the model training process outlined in your project. However, during my inspection of the GaussianDiffusionBeatGans.training_losses method (defined in diffusion/base.py), I noticed that...

Hi! Thank you for your intresting work! Is there lack of the implementation code for ATRO_loss which is required in train_cifar.py ? It would be appreciated that adding the code...

Convert the checkpoint saved by flax to .pth

1

Thanks for your excellent work and published code! About the checkpoint trained by the Score SDE (published by song yang), how can we transfer the checkpoint save by flax.training.checkpoints.save_checkpoint to...