Commit Graph

50 Commits

Author SHA1 Message Date
Phil Wang
a6cdbe0b9c relax learning rate constraint, as @rom1504 wants to try a higher one 2022-07-06 18:09:11 -07:00
Phil Wang
e928ae5c34 default the device to the device that the diffusion prior parameters are on, if the trainer was never given the accelerator nor device 2022-07-06 12:47:48 -07:00
Phil Wang
1bd8a7835a attempting to fix issue with deepspeed fp16 seeing overflowing gradient 2022-07-06 08:27:34 -07:00
Phil Wang
f33453df9f debugging with Aidan 2022-07-05 18:22:43 -07:00
Phil Wang
1e4bb2bafb cast long as float before deriving sinusoidal pos emb 2022-07-05 18:01:22 -07:00
Phil Wang
ee75515c7d remove forcing of softmax in f32, in case it is interfering with deepspeed 2022-07-05 16:53:58 -07:00
Phil Wang
ec68243479 set ability to do warmup steps for each unet during training 2022-07-05 16:24:16 -07:00
Phil Wang
3afdcdfe86 need to keep track of training steps separately for each unet in decoder trainer 2022-07-05 15:17:59 -07:00
Phil Wang
b9a908ff75 bring in two tricks from the cogview paper for reducing the chances of overflow, for attention and layernorm 2022-07-05 14:27:04 -07:00
Phil Wang
e1fe3089df do bias-less layernorm manually 2022-07-05 13:09:58 -07:00
Phil Wang
ec5a77fc55 0.15.4 2022-07-02 08:56:34 -07:00
Phil Wang
3d23ba4aa5 add ability to specify full self attention on specific stages in the unet 2022-07-01 10:22:07 -07:00
Phil Wang
282c35930f 0.15.2 2022-07-01 09:40:11 -07:00
Phil Wang
7b0edf9e42 allow for returning low resolution conditioning image on forward through decoder with return_lowres_cond_image flag 2022-07-01 09:35:39 -07:00
Phil Wang
a922a539de bring back convtranspose2d upsampling, allow for nearest upsample with hyperparam, change kernel size of last conv to 1, make configurable, cleanup 2022-07-01 09:21:47 -07:00
Phil Wang
8f2466f1cd blur sigma for upsampling training was 0.6 in the paper, make that the default value 2022-06-30 17:03:16 -07:00
Phil Wang
908ab83799 add skip connections for all intermediate resnet blocks, also add an extra resnet block for memory efficient version of unet, time condition for both initial resnet block and last one before output 2022-06-29 08:16:58 -07:00
Phil Wang
46a2558d53 bug in pydantic decoder config class 2022-06-29 07:17:35 -07:00
Phil Wang
6a11b9678b bring in the skip connection scaling factor, used by imagen in their unets, cite original paper using it 2022-06-26 21:59:55 -07:00
Phil Wang
b90364695d fix remaining issues with deriving cond_on_text_encodings from child unet settings 2022-06-26 21:07:42 -07:00
Phil Wang
032e83b0e0 nevermind, do not enforce text encodings on first unet 2022-06-26 12:45:05 -07:00
Phil Wang
2e85e736f3 remove unnecessary decoder setting, and if not unconditional, always make sure the first unet is condition-able on text 2022-06-26 12:32:17 -07:00
Phil Wang
4b994601ae just make sure decoder learning rate is reasonable and help out budding researchers 2022-06-23 11:29:28 -07:00
Phil Wang
c8422ffd5d fix EMA updating buffers with non-float tensors 2022-06-22 07:16:39 -07:00
Phil Wang
0021535c26 move ema to external repo 2022-06-20 11:48:32 -07:00
Phil Wang
f545ce18f4 be able to turn off p2 loss reweighting for upsamplers 2022-06-20 09:43:31 -07:00
Phil Wang
fc7abf624d in paper, blur sigma was 0.6 2022-06-20 09:05:08 -07:00
Phil Wang
138079ca83 allow for setting beta schedules of unets differently in the decoder, as what was used in the paper was cosine, cosine, linear 2022-06-20 08:56:37 -07:00
Phil Wang
461b91c5c1 also merge distributed training code for decoder, thanks to @Veldrovive 2022-06-19 09:26:44 -07:00
Phil Wang
e37072a48c 0.10.0 2022-06-19 08:50:53 -07:00
Phil Wang
6651eafa93 one more residual, after seeing good results on unconditional generation locally 2022-06-16 11:18:02 -07:00
Phil Wang
e6bb75e5ab fix missing residual for highest resolution of the unet 2022-06-15 20:09:43 -07:00
Phil Wang
b7f9607258 make memory efficient unet design from imagen toggle-able 2022-06-15 13:40:26 -07:00
Phil Wang
2219348a6e adopt similar unet architecture as imagen 2022-06-15 12:18:21 -07:00
Phil Wang
9eea9b9862 add p2 loss reweighting for decoder training as an option 2022-06-14 10:58:57 -07:00
Phil Wang
5d958713c0 fix classifier free guidance for image hiddens summed to time hiddens, thanks to @xvjiarui for finding this bug 2022-06-13 21:01:50 -07:00
Phil Wang
350a3d6045 0.6.16 2022-06-06 08:45:46 -07:00
Phil Wang
934c9728dc some cleanup 2022-06-04 16:54:15 -07:00
Phil Wang
ce4b0107c1 0.6.13 2022-06-04 13:26:57 -07:00
Phil Wang
22cc613278 ema fix from @nousr 2022-06-03 19:44:36 -07:00
Phil Wang
708809ed6c lower beta2 for adam down to 0.99, based on https://openreview.net/forum?id=2LdBqxc1Yv 2022-06-03 10:26:28 -07:00
Phil Wang
9cc475f6e7 fix update_every within EMA 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 2022-06-03 09:34:57 -07:00
Phil Wang
8cc278447e just cast to right types for blur sigma and kernel size augs 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) 2022-06-02 11:11:25 -07:00
Phil Wang
a851168633 make youtokentome optional package, due to reported installation difficulties 2022-06-01 09:25:35 -07:00
Phil Wang
1ffeecd0ca lower default ema beta value 2022-05-31 11:55:21 -07:00
Phil Wang
3df899f7a4 patch 2022-05-31 09:03:43 -07:00
Phil Wang
6f8b90d4d7 add packaging package 2022-05-30 11:45:00 -07:00
Phil Wang
b588286288 fix version 2022-05-30 11:06:34 -07:00