From a389f81138da2904b00e63b98ecef02e19510a58 Mon Sep 17 00:00:00 2001 From: Phil Wang Date: Fri, 29 Apr 2022 15:40:51 -0700 Subject: [PATCH] todo --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 6b809e6..46e4161 100644 --- a/README.md +++ b/README.md @@ -741,6 +741,7 @@ Once built, images will be saved to the same directory the command is invoked - [ ] become an expert with unets, cleanup unet code, make it fully configurable, port all learnings over to https://github.com/lucidrains/x-unet - [ ] copy the cascading ddpm code to a separate repo (perhaps https://github.com/lucidrains/denoising-diffusion-pytorch) as the main contribution of dalle2 really is just the prior network - [ ] transcribe code to Jax, which lowers the activation energy for distributed training, given access to TPUs +- [ ] just take care of the training for the decoder in a wrapper class, as each unet in the cascade will need its own optimizer - [ ] train on a toy task, offer in colab - [ ] think about how best to design a declarative training config that handles preencoding for prior and training of multiple networks in decoder - [ ] extend diffusion head to use diffusion-gan (potentially using lightweight-gan) to speed up inference