Yue Wu 1096f88e2b sampling bug fix in diffusers tutorial "basic_training.md" (#8223) ...

sampling bug fix in basic_training.md

In the diffusers basic training tutorial, setting the manual seed argument (generator=torch.manual_seed(config.seed)) in the pipeline call inside evaluate() function rewinds the dataloader shuffling, leading to overfitting due to the model seeing same sequence of training examples after every evaluation call. Using generator=torch.Generator(device='cpu').manual_seed(config.seed) avoids this.

2024-05-24 11:14:32 -07:00

..

autopipeline.md

[docs] AutoPipeline (#7714)

2024-04-22 10:15:07 -07:00

basic_training.md

sampling bug fix in diffusers tutorial "basic_training.md" (#8223)

2024-05-24 11:14:32 -07:00

fast_diffusion.md

change to 2024 in the license (#6902)

2024-02-08 08:19:31 -10:00

tutorial_overview.md

change to 2024 in the license (#6902)

2024-02-08 08:19:31 -10:00

using_peft_for_inference.md

Implements Blockwise lora (#7352)

2024-03-29 21:15:57 +05:30