search

facebookresearch / DiT

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"
Other
6.37k stars 569 forks source link

DiT results on CIFAR10 #84

Open yuanzhi-zhu opened 6 months ago

yuanzhi-zhu commented 6 months ago

have you tried to run DiT on CIFAR10 dataset? I did some simple expr and found that DiT does not work well on CIFAR10.

tanghengjian commented 6 months ago

i also found sample.py script always give same result image under same label. In the workflow of DiTBlock, i wonder there is no cross attention , so i guess the variation ability may be a challange to DiT?

yuanzhi-zhu commented 6 months ago

i also found sample.py script always give same result image under same label. In the workflow of DiTBlock, i wonder there is no cross attention , so i guess the variation ability may be a challange to DiT?

Hi @tanghengjian, I do not know if your question is related to the cifar expr, but did you change the seed in the sample.py script? https://github.com/facebookresearch/DiT/blob/ed81ce2229091fd4ecc9a223645f95cf379d582b/sample.py#L23

tanghengjian commented 6 months ago

run with default value. by the way, i found cifar10 dataset is only 32*32 pixel with 10 classes, it means the y condition changes from 0 to 9. do you have tested the mscoco dataset in DiT model with label condition?

zhengyu-su commented 2 months ago

run with default value. by the way, i found cifar10 dataset is only 32*32 pixel with 10 classes, it means the y condition changes from 0 to 9. do you have tested the mscoco dataset in DiT model with label condition?

How do you link CIFAR10 classes to the ImageNet 1k classes?