XIANG Weilai

Thank you for your response! I compare the FID results on classifier-free guidance conditional CIFAR-10 with `attn = attn.softmax(dim=1)` and `attn = attn.softmax(dim=2)`, following the settings in the original DDPM...

> You can absolutely add new custom objects to a scene. You can check out our recent ECCV tutorials (https://aihabitat.org/tutorial/2020/) for more information. Specifically, I would suggest **Habitat-Sim for Interaction**,...

Hi Kecheng, Thanks for your interest in this work, and I'm sorry for the delayed response. The current state of this repo does not contain official configurations for Tiny-ImageNet training,...

Paper name: Denoising Diffusion Autoencoders are Unified Self-supervised Learners Paper link: https://arxiv.org/abs/2303.09769 Code link: https://github.com/FutureXiang/ddae Related area: Diffusion, Self-supervised representation learning Selected for *Oral* presentation at ICCV 23. @amusi Thank...

Hi, I am also confused about the weight initialization in different implementations. ## Each implementation has its own initialization style In the [official DDPM repo](https://github.com/hojonathanho/diffusion), the convs before residual connections...

Hi, I'm using `pytorch=2.0.0` with `python=3.8`. The `environment.yaml` file can be found at https://pastebin.com/DCuA0us6. Please note that the actual error outputs will always come after the `ChildFailedError` or before `ERROR:torch.distributed.elastic.multiprocessing.api:failed...