aljaz/DALLE2-pytorch
1
1
Fork 0
mirror of https://github.com/lucidrains/DALLE2-pytorch.git synced 2026-01-09 11:34:20 +01:00
Code Issues Packages Projects Releases Wiki Activity
270 Commits 2 Branches 353 Tags
fc8fce38fbf323154e74788ed9d3d27960af5c09
Commit Graph

270 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Phil Wang
fc8fce38fb make sure cascading DDPM can be trained unconditionally, to ready for CLI one command training for the public 0.2.6 2022-05-10 10:48:10 -07:00
Phil Wang
a1bfb03ba4 project management 2022-05-10 10:13:51 -07:00
Phil Wang
b1e7b5f6bb make sure resnet groups in unet is finely customizable 0.2.5 2022-05-10 10:12:50 -07:00
z
10b905b445 smol typo (#81) 2022-05-10 09:52:50 -07:00
Phil Wang
9b322ea634 patch 0.2.4 2022-05-09 19:46:19 -07:00
Phil Wang
ba64ea45cc 0.2.3 0.2.3 2022-05-09 16:50:31 -07:00
Phil Wang
64f7be1926 some cleanup 2022-05-09 16:50:21 -07:00
Phil Wang
db805e73e1 fix a bug with numerical stability in attention, sorry! 🐛 0.2.2a 2022-05-09 16:23:37 -07:00
z
cb07b37970 Ensure Eval Mode In Metric Functions (#79) 
* add eval/train toggles

* train/eval flags

* shift train toggle

Co-authored-by: nousr <z@localhost.com>
0.2.2 		2022-05-09 16:05:40 -07:00
Phil Wang
a774bfefe2 add attention and feedforward dropouts to train_diffusion_prior script 2022-05-09 13:57:15 -07:00
Phil Wang
2ae57f0cf5 cleanup 2022-05-09 13:51:26 -07:00
Phil Wang
e46eaec817 deal the diffusion prior problem yet another blow 0.2.1 2022-05-09 11:08:52 -07:00
Kumar R
8647cb5e76 Val loss changes, with quite a few other changes. This is in place of the earlier PR(https://github.com/lucidrains/DALLE2-pytorch/pull/67) (#77) 
* Val_loss changes - no rebased with lucidrains' master.

* Val Loss changes - now rebased with lucidrains' master

* train_diffusion_prior.py updates

* dalle2_pytorch.py updates

* __init__.py changes

* Update train_diffusion_prior.py

* Update dalle2_pytorch.py

* Update train_diffusion_prior.py

* Update train_diffusion_prior.py

* Update dalle2_pytorch.py

* Update train_diffusion_prior.py

* Update train_diffusion_prior.py

* Update train_diffusion_prior.py

* Update train_diffusion_prior.py

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md
 2022-05-09 08:53:29 -07:00
Phil Wang
53c189e46a give more surface area for attention in diffusion prior 0.2.0 2022-05-09 08:08:11 -07:00
Phil Wang
dde51fd362 revert restriction for classifier free guidance for diffusion prior, given @crowsonkb advice 0.1.10 2022-05-07 20:55:41 -07:00
Nasir Khalid
2eac7996fa Additional image_embed metric (#75) 
Added metric to track image_embed vs predicted_image_embed
 2022-05-07 14:32:33 -07:00
Phil Wang
4010aec033 turn off classifier free guidance if predicting x_start for diffusion prior 0.1.9 2022-05-07 09:38:17 -07:00
Phil Wang
c87b84a259 todo 2022-05-07 09:21:08 -07:00
Phil Wang
8b05468653 todo 2022-05-07 08:33:45 -07:00
Phil Wang
830afd3c15 sinusoidal embed time embeddings for diffusion prior as well, for continuous version 0.1.8 2022-05-07 08:32:43 -07:00
Phil Wang
8f93729d19 when in doubt, make it a hyperparameter 0.1.7a 2022-05-07 07:52:17 -07:00
z
cd5f2c1de4 simulate unrelated captions as a training metric (#66) 
* add unrelated embedding metric

* change to torch.roll

Co-authored-by: nousr <z@localhost.com>
Co-authored-by: nousr <>
0.1.7 		2022-05-07 05:34:59 -07:00
Phil Wang
85ed77d512 fix a potentially huge bug thanks to @CiaoHe https://github.com/lucidrains/DALLE2-pytorch/issues/71 0.1.6 2022-05-07 05:05:54 -07:00
Piero Rolando
fd53fa17db Fix a typo in README (#70) 
Change "pyhon" for "python" (correct)
 2022-05-06 16:53:36 -07:00
Phil Wang
3676ef4d49 make sure vqgan-vae trainer supports mixed precision 0.1.5 2022-05-06 10:44:16 -07:00
Phil Wang
28e944f328 make sure openai clip adapter outputs l2normed embeddings 0.1.4 2022-05-06 10:12:03 -07:00
Phil Wang
14e63a3f67 also offer l2norm clamping in diffusion prior during training, if one were using predict x0 objective 0.1.2 2022-05-06 10:05:14 -07:00
Phil Wang
09e9eaa5a6 project management 2022-05-06 09:00:22 -07:00
Phil Wang
e6d752cf4a reprioritize 2022-05-06 08:55:26 -07:00
Phil Wang
ad20a14a4d bring in rotary embeddings for diffusion prior causal transformer (the most powerful relative positional encoding, used in PaLM) - 0.1.0 because of breaking change 0.1.1 2022-05-06 08:45:30 -07:00
Phil Wang
0be1e0d64c support CoCa, which seems to be better than CLIP (has an autoregressive text encoder) https://arxiv.org/abs/2205.01917 0.0.109 2022-05-06 08:27:12 -07:00
Phil Wang
98df1ba51e add diffusion prior trainer, which automatically takes care of the exponential moving average (training and sampling), as well as mixed precision, gradient clipping 2022-05-06 08:11:09 -07:00
Phil Wang
878b555ef7 fix training with clip 0.0.107 2022-05-06 07:37:57 -07:00
Phil Wang
63029f7388 remove l2norm output from train_diffusion_prior.py 2022-05-05 19:07:58 -07:00
Phil Wang
c76a964fd6 allow for CLIP to be optional in Decoder, and allow DecoderTrainer to work off training pre-encoded image embeddings 0.0.106 2022-05-05 08:11:01 -07:00
Phil Wang
79fabc4341 reorg readme 2022-05-05 07:54:12 -07:00
Kumar R
f7ef4bde38 Added some documentation for the diffusion prior in README.md (#62) 
* Delete README.md

* Create README.md

* Update README.md

* Update README.md
 2022-05-05 07:51:31 -07:00
Phil Wang
93ba019069 product management 2022-05-05 07:39:51 -07:00
Phil Wang
8518684ae9 does not make much sense, as researchers may want to try predicting noise with diffusionprior instead of predicting x0 0.0.105 2022-05-05 07:37:00 -07:00
Phil Wang
1d5dc08810 take @crowsonkb 's suggestion at https://github.com/lucidrains/DALLE2-pytorch/issues/60#issue-1226116132 0.0.104 2022-05-05 07:28:53 -07:00
Phil Wang
d8d8b6caf1 dataloaders for decoder training, from @Veldrovive 0.0.102 2022-05-05 07:09:45 -07:00
Aidan Dempster
15acc03bd4 Add a dataloader for training the decoder (#57) 
* Added dataloader and updated requirements

* Added option to set embedding shard width separately from webdataset shard length.
There must be a better way to do this.

* Changed embedding loader to read using fsspec

* Moved the loader into a more compatible location

* Removed unnecessary package

* Fixed typo (Embeding -> Embedding)

* Simplified example embedding finder code to remove unnecessary get_file_list function

* Added example usage of ImageEmbeddingDataset

* Changed the name of create_dataloader to be more verbose
Added a dataloaders __init__.py
 2022-05-05 07:08:45 -07:00
Phil Wang
896f19786d remove convnext blocks, they are illsuited for generative work, validated by early experimental results at https://github.com/lucidrains/video-diffusion-pytorch 0.0.101 2022-05-05 07:07:21 -07:00
Phil Wang
aec5575d09 take a bet on resize right, given Katherine is using it 0.0.100 2022-05-04 19:26:45 -07:00
Phil Wang
9773f10d6c use inference mode whenever possible, cleanup 0.0.99 2022-05-04 15:25:05 -07:00
Phil Wang
a6bf8ddef6 advertise laion 2022-05-04 15:04:05 -07:00
Phil Wang
86e692d24f fix random crop probability 0.0.98 2022-05-04 11:52:24 -07:00
Phil Wang
97b751209f allow for last unet in the cascade to be trained on crops, if it is convolution-only 0.0.97 2022-05-04 11:48:48 -07:00
Phil Wang
74103fd8d6 product management 2022-05-04 11:20:50 -07:00
Phil Wang
1992d25cad project management 0.0.96 2022-05-04 11:18:54 -07:00