Commit Graph

450 Commits

Author SHA1 Message Date
zion
64c2f9c4eb implement ema warmup from @crowsonkb (#140) 2022-06-04 13:26:34 -07:00
Phil Wang
22cc613278 ema fix from @nousr v0.6.12 2022-06-03 19:44:36 -07:00
zion
83517849e5 ema module fixes (#139) 2022-06-03 19:43:51 -07:00
Phil Wang
708809ed6c lower beta2 for adam down to 0.99, based on https://openreview.net/forum?id=2LdBqxc1Yv v0.6.11 2022-06-03 10:26:28 -07:00
Phil Wang
9cc475f6e7 fix update_every within EMA v0.6.10 2022-06-03 10:21:05 -07:00
Phil Wang
ffd342e9d0 allow for an option to constrain the variance interpolation fraction coming out from the unet for learned variance, if it is turned on v0.6.9 2022-06-03 09:34:57 -07:00
Phil Wang
f8bfd3493a make destructuring datum length agnostic when validating in training decoder script, for @YUHANG-Ma 2022-06-02 13:54:57 -07:00
Phil Wang
9025345e29 take a stab at fixing generate_grid_samples when real images have a greater image size than generated 2022-06-02 11:33:15 -07:00
Phil Wang
8cc278447e just cast to right types for blur sigma and kernel size augs v0.6.8 2022-06-02 11:21:58 -07:00
Phil Wang
38cd62010c allow for random blur sigma and kernel size augmentations on low res conditioning (need to reread paper to see if the augmentation value needs to be fed into the unet for conditioning as well) v0.6.7 2022-06-02 11:11:25 -07:00
Ryan Russell
1cc288af39 Improve Readability (#133)
Signed-off-by: Ryan Russell <git@ryanrussell.org>
2022-06-01 13:28:02 -07:00
Phil Wang
a851168633 make youtokentome optional package, due to reported installation difficulties v0.6.6 2022-06-01 09:25:35 -07:00
Phil Wang
1ffeecd0ca lower default ema beta value v0.6.5 2022-05-31 11:55:21 -07:00
Phil Wang
3df899f7a4 patch v0.6.4 2022-05-31 09:03:43 -07:00
Aidan Dempster
09534119a1 Fixed non deterministic optimizer creation (#130) 2022-05-31 09:03:20 -07:00
Phil Wang
6f8b90d4d7 add packaging package v0.6.3 2022-05-30 11:45:00 -07:00
Phil Wang
b588286288 fix version v0.6.2 2022-05-30 11:06:34 -07:00
Phil Wang
b693e0be03 default number of resnet blocks per layer in unet to 2 (in imagen it was 3 for base 64x64) v0.6.1 2022-05-30 10:06:48 -07:00
Phil Wang
a0bed30a84 additional conditioning on image embedding by summing to time embeddings (for FiLM like conditioning in subsequent layers), from passage found in paper by @mhh0318 v0.6.0 2022-05-30 09:26:51 -07:00
zion
387c5bf774 quick patch for new prior loader (#123) 2022-05-29 16:25:53 -07:00
Phil Wang
a13d2d89c5 0.5.7 v0.5.7 2022-05-29 07:40:25 -07:00
zion
44d4b1bba9 overhaul prior dataloader (#122)
add readme for loader
2022-05-29 07:39:59 -07:00
Phil Wang
f12a7589c5 commit to trying out grid attention 2022-05-26 12:56:10 -07:00
Phil Wang
b8af2210df make sure diffusion prior can be instantiated from pydantic class without clip v0.5.6 2022-05-26 08:47:30 -07:00
Phil Wang
f4fe6c570d allow for full customization of number of resnet blocks per down or upsampling layers in unet, as in imagen v0.5.5 2022-05-26 08:33:31 -07:00
Phil Wang
645e207441 credit assignment 2022-05-26 08:16:03 -07:00
Phil Wang
00743b3a0b update 2022-05-26 08:12:25 -07:00
Phil Wang
01589aff6a cite maxvit properly 2022-05-26 07:12:25 -07:00
Phil Wang
7ecfd76cc0 fix evaluation config splat in training decoder script 2022-05-26 07:11:31 -07:00
Phil Wang
6161b61c55 0.5.4 v0.5.4 2022-05-25 09:32:17 -07:00
zion
1ed0f9d80b use deterministic optimizer params (#116) 2022-05-25 09:31:43 -07:00
Phil Wang
f326a95e26 0.5.3 v0.5.3 2022-05-25 09:07:28 -07:00
zion
d7a0a2ce4b add more support for configuring prior (#113) 2022-05-25 09:06:50 -07:00
Phil Wang
f23fab7ef7 switch over to scale shift conditioning, as it seems like Imagen and Glide used it and it may be important v0.5.2 2022-05-24 21:46:12 -07:00
Phil Wang
857b9fbf1e allow for one to stop grouping out weight decayable parameters, to debug optimizer state dict problem v0.5.1 2022-05-24 21:42:32 -07:00
Phil Wang
8864fd0aa7 bring in the dynamic thresholding technique from the Imagen paper, which purportedly improves classifier free guidance for the cascading ddpm 0.5.0a 2022-05-24 18:15:14 -07:00
Phil Wang
72bf159331 update v0.5.0 2022-05-24 08:25:40 -07:00
Phil Wang
e5e47cfecb link to aidan's test run 2022-05-23 12:41:46 -07:00
Phil Wang
fa533962bd just use an assert to make sure clip image channels is never different than the channels of the diffusion prior and decoder, if clip is given v0.4.14 2022-05-22 22:43:14 -07:00
Phil Wang
276abf337b fix and cleanup image size determination logic in decoder 0.4.11 2022-05-22 22:28:45 -07:00
Phil Wang
ae42d03006 allow for saving of additional fields on save method in trainers, and return loaded objects from the load method 0.4.10 2022-05-22 22:14:25 -07:00
Phil Wang
4d346e98d9 allow for config driven creation of clip-less diffusion prior 2022-05-22 20:36:20 -07:00
Phil Wang
2b1fd1ad2e product management 2022-05-22 19:23:40 -07:00
zion
82a2ef37d9 Update README.md (#109)
block in a section that links to available pre-trained models for those who are interested
2022-05-22 19:22:30 -07:00
Phil Wang
5c397c9d66 move neural network creations off the configuration file into the pydantic classes 0.4.8 2022-05-22 19:18:18 -07:00
Phil Wang
0f4edff214 derived value for image preprocessing belongs to the data config class 0.4.7 2022-05-22 18:42:40 -07:00
Phil Wang
501a8c7c46 small cleanup 0.4.6 2022-05-22 15:39:38 -07:00
Phil Wang
4e49373fc5 project management 2022-05-22 15:27:40 -07:00
Phil Wang
49de72040c fix decoder trainer optimizer loading (since there are multiple for each unet), also save and load step number correctly 0.4.5 2022-05-22 15:21:00 -07:00
Phil Wang
271a376eaf 0.4.3 0.4.3 2022-05-22 15:10:28 -07:00