Commit Graph

315 Commits

Author SHA1 Message Date
Phil Wang
ecf9e8027d make sure classifier free guidance is used only if conditional dropout is present on the DiffusionPrior and Decoder classes. also make sure prior can have a different conditional scale than decoder 0.2.38 2022-05-15 19:09:38 -07:00
Phil Wang
36c5079bd7 LazyLinear is not mature, make users pass in text_embed_dim if text conditioning is turned on 0.2.37 2022-05-15 18:56:52 -07:00
Phil Wang
4a4c7ac9e6 cond drop prob for diffusion prior network should default to 0 02.36 2022-05-15 18:47:45 -07:00
Phil Wang
fad7481479 todo 2022-05-15 17:00:25 -07:00
Phil Wang
123658d082 cite Ho et al, since cascading ddpm is now trainable 2022-05-15 16:56:53 -07:00
Phil Wang
11d4e11f10 allow for training unconditional ddpm or cascading ddpms 0.2.35 2022-05-15 16:54:56 -07:00
Phil Wang
99778e12de trainer classes now takes care of auto-casting numpy to torch tensors, and setting correct device based on model parameter devices 0.2.34 2022-05-15 15:25:45 -07:00
Phil Wang
0f0011caf0 todo 2022-05-15 14:28:35 -07:00
Phil Wang
7b7a62044a use eval vs training mode to determine whether to call backprop on trainer forward 0.2.32 2022-05-15 14:20:59 -07:00
Phil Wang
156fe5ed9f final cleanup for the day 2022-05-15 12:38:41 -07:00
Phil Wang
5ec34bebe1 cleanup readme 2022-05-15 12:29:26 -07:00
Phil Wang
8eaacf1ac1 remove indirection 2022-05-15 12:05:45 -07:00
Phil Wang
e66c7b0249 incorrect naming 2022-05-15 11:23:52 -07:00
Phil Wang
f7cd4a0992 product management 2022-05-15 11:21:12 -07:00
Phil Wang
68e7d2f241 make sure gradient accumulation feature works even if all arguments passed in are keyword arguments 0.2.31 2022-05-15 11:16:16 -07:00
Phil Wang
74f222596a remove todo 2022-05-15 11:01:35 -07:00
Phil Wang
aa6772dcff make sure optimizer and scaler is reloaded on resume for training diffusion prior script, move argparse to click 2022-05-15 10:48:10 -07:00
Phil Wang
71d0c4edae cleanup to use diffusion prior trainer 2022-05-15 10:16:05 -07:00
Phil Wang
f7eee09d8b 0.2.30 0.2.30 2022-05-15 09:56:59 -07:00
Phil Wang
89de5af63e experiment tracker agnostic 2022-05-15 09:56:40 -07:00
Phil Wang
4ec6d0ba81 backwards pass is not recommended under the autocast context, per pytorch docs 0.2.29 2022-05-14 18:26:19 -07:00
Phil Wang
aee92dba4a simplify more 2022-05-14 17:16:46 -07:00
Phil Wang
b0cd5f24b6 take care of gradient accumulation automatically for researchers, by passing in a max_batch_size on the decoder or diffusion prior trainer forward 0.2.26 2022-05-14 17:04:09 -07:00
Phil Wang
b494ed81d4 take care of backwards within trainer classes for diffusion prior and decoder, readying to take care of gradient accumulation as well (plus, unsure if loss should be backwards within autocast block) 0.2.24 2022-05-14 15:49:24 -07:00
Phil Wang
ff3474f05c normalize conditioning tokens outside of cross attention blocks 0.2.23 2022-05-14 14:23:52 -07:00
Phil Wang
d5293f19f1 lineup with paper 0.2.22 2022-05-14 13:57:00 -07:00
Phil Wang
e697183849 be able to customize adam eps 0.2.21 2022-05-14 13:55:04 -07:00
Phil Wang
591d37e266 lower default initial learning rate to what Jonathan Ho had in his original repo 0.2.20 2022-05-14 13:22:43 -07:00
Phil Wang
d1f02e8f49 always use sandwich norm for attention layer 0.2.19 2022-05-14 12:13:41 -07:00
Phil Wang
9faab59b23 use post-attn-branch layernorm in attempt to stabilize cross attention conditioning in decoder 0.2.18 2022-05-14 11:58:09 -07:00
Phil Wang
5d27029e98 make sure lowres conditioning image is properly normalized to -1 to 1 for cascading ddpm 0.2.17 2022-05-14 01:23:54 -07:00
Phil Wang
3115fa17b3 fix everything around normalizing images to -1 to 1 for ddpm training automatically 0.2.16 2022-05-14 01:17:11 -07:00
Phil Wang
124d8577c8 move the inverse normalization function called before image embeddings are derived from clip to within the diffusion prior and decoder classes 0.2.15 2022-05-14 00:37:52 -07:00
Phil Wang
2db0c9794c comments 2022-05-12 14:25:20 -07:00
Phil Wang
2277b47ffd make sure learned variance can work for any number of unets in the decoder, defaults to first unet, as suggested was used in the paper 0.2.14 2022-05-12 14:18:15 -07:00
Phil Wang
28b58e568c cleanup in preparation of option for learned variance 2022-05-12 12:04:52 -07:00
Phil Wang
924455d97d align the ema model device back after sampling from the cascading ddpm in the decoder 0.2.12 2022-05-11 19:56:54 -07:00
Phil Wang
6021945fc8 default to l2 loss 0.2.11 2022-05-11 19:24:51 -07:00
Light-V
6f76652d11 fix typo in README.md (#85)
The default config for clip from openai should be ViT-B/32
2022-05-11 13:38:16 -07:00
Phil Wang
3dda2570ed fix amp issue for https://github.com/lucidrains/DALLE2-pytorch/issues/82 0.2.10 2022-05-11 08:21:39 -07:00
Phil Wang
2f3c02dba8 numerical accuracy for noise schedule parameters 0.2.9 2022-05-10 15:28:46 -07:00
Phil Wang
908088cfea wrap up cross embed layer feature 0.2.8 2022-05-10 12:19:34 -07:00
Phil Wang
8dc8a3de0d product management 2022-05-10 11:51:38 -07:00
Phil Wang
35f89556ba bring in the cross embed layer from Crossformer paper for initial convolution in unet 0.2.7 2022-05-10 11:50:38 -07:00
Phil Wang
2b55f753b9 fix new issue with github actions and auto pypi package uploading 0.2.6a 2022-05-10 10:51:15 -07:00
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