 Phil Wang
|
a7f2d670bb
|
always set results_folder on Trainer
|
2022-12-21 08:34:34 -08:00 |
|
|
Phil Wang
|
6ab29d5cea
|
start saving version of library in the checkpoints, so in case of breaking changes, researchers can return to the right working version
|
2022-11-28 12:11:11 -08:00 |
|
|
Phil Wang
|
ddc31bc489
|
trust paper
|
2022-11-27 10:05:55 -08:00 |
|
|
Phil Wang
|
12079cadee
|
add the v-parameterization from Salimans et al for the discrete case, allow for distillation
|
2022-10-30 09:53:28 -07:00 |
|
|
Phil Wang
|
0ffff59ca0
|
add option for random fourier features, given misinterpretation of Katherine's code, thanks to @tmabraham for addressing this in https://github.com/lucidrains/denoising-diffusion-pytorch/issues/112
|
2022-10-30 09:32:06 -07:00 |
|
|
Phil Wang
|
23fd887a5f
|
switch back to regular attention, given @rromb results
|
2022-10-16 08:43:10 -07:00 |
|
|
Nicolas Pielawski
|
2ac3f94a80
|
Added gradient clipping.
|
2022-10-05 11:29:49 -07:00 |
|
|
Phil Wang
|
6e8a0f2082
|
fix auto-conversion of images to mode in dataset
|
2022-09-20 19:29:35 -07:00 |
|
|
Kashif Rasul
|
d85b8bbe2e
|
fix torch.cumprod
|
2022-09-16 17:19:00 +02:00 |
|
|
Ryan Burgert
|
7c0cd05c27
|
Trainer.load can use GPU's other than cuda:0
|
2022-09-04 22:11:35 -04:00 |
|
|
Phil Wang
|
6dda508ff6
|
in ddim, clip x0 before calculation of predicted noise, thanks to @lukovnikov again for pointing out this inconsistency with glides implementation
|
2022-09-01 09:34:50 -07:00 |
|
|
Phil Wang
|
9ec8d27217
|
0.27.7
|
2022-08-31 07:36:19 -07:00 |
|
|
lukovnikov
|
e4a4e4acaa
|
Revert "Revert "fix ddim sampling""
This reverts commit cd8329cdd7.
|
2022-08-31 15:28:35 +02:00 |
|
|
lukovnikov
|
cd8329cdd7
|
Revert "fix ddim sampling"
This reverts commit aec2a26984.
|
2022-08-31 15:25:51 +02:00 |
|
|
lukovnikov
|
aec2a26984
|
fix ddim sampling
|
2022-08-31 15:24:59 +02:00 |
|
|
TheDudeFromCI
|
e46a89e2bc
|
Update step before training checkpoint
|
2022-08-31 02:19:12 -07:00 |
|
|
Phil Wang
|
42158d6248
|
fix ddim, for issue https://github.com/lucidrains/denoising-diffusion-pytorch/issues/81
|
2022-08-30 20:30:29 -07:00 |
|
|
Phil Wang
|
d9275a744c
|
add weight standardization prior to groupnorm, lessen cosine sim attention scale to 10 for fp16
|
2022-08-17 11:42:54 -07:00 |
|
|
Phil Wang
|
f0d59acdfd
|
fix sampling ddpm tqdm
|
2022-08-10 12:02:56 -07:00 |
|
|
Phil Wang
|
689593a579
|
add the new self conditioning technique from hintons group from bit diffusion paper
0.27.0
|
2022-08-10 10:52:07 -07:00 |
|
|
Phil Wang
|
eba44498d1
|
higher epsilon for fp16 in layernorm
|
2022-07-29 13:29:52 -07:00 |
|
|
Phil Wang
|
12f95b33d8
|
rescale values to prevent linear attention from overflowing in fp16 setting
|
2022-07-27 12:25:40 -07:00 |
|
|
Phil Wang
|
6b504c4ae9
|
fix accelerator prepare bug for dataloader
|
2022-07-25 08:13:46 -07:00 |
|
|
Phil Wang
|
37334ae824
|
fix a bug with ddim and predict x0 objective
|
2022-07-18 19:04:57 -07:00 |
|
|
Phil Wang
|
555566c188
|
take a gamble on cosine sim attention
|
2022-07-18 11:29:20 -07:00 |
|
|
Phil Wang
|
2b742dd2cc
|
move accelerator backward outside of autocast context, also calculate total loss correctly across gradient accumulated steps
|
2022-07-11 21:02:06 -07:00 |
|
|
Phil Wang
|
1345a8a41d
|
do not noise at the last timestep for ddim
|
2022-07-09 18:36:45 -07:00 |
|
|
Phil Wang
|
931a5af2c3
|
bring in ddim sampling
|
2022-07-09 16:10:23 -07:00 |
|
|
Phil Wang
|
a0c3443eaa
|
optimizer should be saved and loaded
|
2022-07-08 17:43:41 -07:00 |
|
|
Phil Wang
|
662172851b
|
add convert_image_to keyword argument, for forcing images being loaded to be converted to some format, greyscale, rgb, rgba, whatever
|
2022-07-08 09:22:59 -07:00 |
|
|
Phil Wang
|
0248b5e4d3
|
also make sure grad scaler actually exists in the saved pt file
|
2022-07-06 11:48:04 -07:00 |
|
|
Phil Wang
|
6b56af08a2
|
support multi-gpu training using huggingface accelerate, addressing https://github.com/lucidrains/denoising-diffusion-pytorch/pull/54
|
2022-07-06 11:45:56 -07:00 |
|
|
Phil Wang
|
d4420248f1
|
tqdm auto instead
|
2022-06-29 19:48:49 -07:00 |
|
|
Arya Aftab
|
d97bc0278c
|
Solve issue #26
|
2022-06-29 11:42:54 +04:30 |
|
|
Phil Wang
|
d26acbcae6
|
more skip connections, as in guided diffusion
|
2022-06-27 13:23:32 -07:00 |
|
|
Phil Wang
|
9939a48139
|
make sure all versions of torch supported
|
2022-06-23 12:28:09 -07:00 |
|
|
Phil Wang
|
75ea49a7ef
|
pass parameter for Trainer to EMA properly
|
2022-06-21 07:37:43 -07:00 |
|
|
Phil Wang
|
8c3609a6e3
|
move EMA logic out of the repository for clarity
|
2022-06-20 13:17:51 -07:00 |
|
|
Phil Wang
|
1586d1a8a0
|
just pluck the image size off the gaussian diffusion class
|
2022-06-17 13:54:41 -07:00 |
|
|
Phil Wang
|
b4fb8804d2
|
conditioning on final resnet block
|
2022-06-17 10:38:17 -07:00 |
|
|
Phil Wang
|
9fd05f1b1f
|
switch to learned sinsuoidal pos emb for the continuous case
|
2022-06-17 09:24:51 -07:00 |
|
|
Phil Wang
|
ec2397f0ba
|
add one more residual
|
2022-06-16 11:08:42 -07:00 |
|
|
Phil Wang
|
844e557dfb
|
fix a missing residual needed at the top most resolution in the unet
|
2022-06-15 19:10:05 -07:00 |
|
|
Phil Wang
|
8b30be8042
|
add p2 loss reweighting for default ddpm as an option
|
2022-06-14 10:49:13 -07:00 |
|
|
Phil Wang
|
ecc6f30901
|
for https://github.com/lucidrains/denoising-diffusion-pytorch/issues/36
|
2022-06-11 10:51:13 -07:00 |
|
|
Phil Wang
|
f900f40f14
|
allow for turning off horizontal flip augmentation
|
2022-06-09 20:59:59 -07:00 |
|
|
Phil Wang
|
3bf5e768c2
|
use a non-sinusoidal embedded condition for continuous time gaussian diffusion conditioned on log(snr)
|
2022-06-07 21:15:27 -07:00 |
|
|
Phil Wang
|
3bbb6ebf16
|
get working version of gaussian diffusion with continuous time (only beta linear schedule for now, but will eventually contain alpha cosine schedule as well as parameterized, learned monotonic MLP)
|
2022-06-07 15:59:29 -07:00 |
|
|
Phil Wang
|
a291da5098
|
bring back linear noise schedule, but default to cosine
|
2022-05-27 19:13:05 -07:00 |
|
|
Phil Wang
|
e5a18bb25c
|
switch over to film like conditioning, used by both openai and google at this point
|
2022-05-24 23:47:34 -07:00 |
|