Adrian744

I would like to know that as well.

This looks like a overfitting problem. Try to increase/decrease your learning rate and batch sizes. There is no "perfect" answer, it is always trial and error.

1. No, diffusion.sample(X) will simply generate X outputs based on the trained model. 2. No. The objective is simply a learning strategy which will be used in the training process....

The Trainer Class has the attribute "train_batch_size". You can simply pass the batch_size you want.

> @modantailleur Hi thanks for your answer. I wonder what I can do instead of sampling if I wanna transport a new image(not consisted in the train set). That means...

Did you double check your data ?(Make sure that all your data does not contain nan values)