Open hexiaoyi95 opened 1 year ago
Thanks for the question. We think input features of unet stay on the same scale will help network learning, but not verify that. You can try to see the impact on performance.
Thanks for your reply. Acctually I'm training your model with my own dataset from scratch. And find it's very hard to converge. Did you ever meet similar issues? Any experiences you can share?
You can try to adjust batchsize and learning rate, and consider training with Vimeo if the amount of data is small.
https://github.com/MCG-NJU/EMA-VFI/blob/75b6f6a889e695df875e103374040d47a4cfac7c/model/flow_estimation.py#L137C65-L137C65 this is a bug or not?