aljaz/DALLE2-pytorch
1
1
Fork 0
mirror of https://github.com/lucidrains/DALLE2-pytorch.git synced 2025-12-20 18:24:19 +01:00
Code Issues Packages Projects Releases Wiki Activity

product management

Browse Source
This commit is contained in:
Phil Wang
2022-05-05 07:39:51 -07:00
parent 8518684ae9
commit 93ba019069
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@@ -864,7 +864,7 @@ Once built, images will be saved to the same directory the command is invoked
- [x] add convnext backbone for vqgan-vae (in addition to vit [vit-vqgan] + resnet) - [x] add convnext backbone for vqgan-vae (in addition to vit [vit-vqgan] + resnet)
- [x] make sure DDPMs can be run with traditional resnet blocks (but leave convnext as an option for experimentation) - [x] make sure DDPMs can be run with traditional resnet blocks (but leave convnext as an option for experimentation)
- [x] make sure for the latter unets in the cascade, one can train on crops for learning super resolution (constrain the unet to be only convolutions in that case, or allow conv-like attention with rel pos bias) - [x] make sure for the latter unets in the cascade, one can train on crops for learning super resolution (constrain the unet to be only convolutions in that case, or allow conv-like attention with rel pos bias)
- [ ] become an expert with unets, cleanup unet code, make it fully configurable, port all learnings over to https://github.com/lucidrains/x-unet (test out unet² in ddpm repo) - [ ] become an expert with unets, cleanup unet code, make it fully configurable, port all learnings over to https://github.com/lucidrains/x-unet (test out unet² in ddpm repo) - consider https://github.com/lucidrains/uformer-pytorch attention-based 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 - [ ] 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 - [ ] transcribe code to Jax, which lowers the activation energy for distributed training, given access to TPUs
- [ ] pull logic for training diffusion prior into a class DiffusionPriorTrainer, for eventual script based + CLI based training - [ ] pull logic for training diffusion prior into a class DiffusionPriorTrainer, for eventual script based + CLI based training
@@ -877,7 +877,7 @@ Once built, images will be saved to the same directory the command is invoked
- [ ] use an experimental tracker agnostic setup, as done <a href="https://github.com/lucidrains/tf-bind-transformer#simple-trainer-class-for-fine-tuning">here</a> - [ ] use an experimental tracker agnostic setup, as done <a href="https://github.com/lucidrains/tf-bind-transformer#simple-trainer-class-for-fine-tuning">here</a>
- [ ] interface out the vqgan-vae so a pretrained one can be pulled off the shelf to validate latent diffusion + DALL-E2 - [ ] interface out the vqgan-vae so a pretrained one can be pulled off the shelf to validate latent diffusion + DALL-E2
- [ ] make sure FILIP works with DALL-E2 from x-clip https://arxiv.org/abs/2111.07783 - [ ] make sure FILIP works with DALL-E2 from x-clip https://arxiv.org/abs/2111.07783
- [ ] make sure resnet | convnext block hyperparameters can be configurable across unet depth (groups and expansion factor) - [ ] make sure resnet hyperparameters can be configurable across unet depth (groups and expansion factor)
## Citations ## Citations