James Betker
0eb1f4dd67
Revert "Get rid of CUDA_VISIBLE_DEVICES"
...
It is actually necessary for training in distributed mode. Only
do it then.
2020-12-31 10:31:40 -07:00
James Betker
8de5a02a48
byol_resnet_playground
...
Similar to the spinenet playground, but tinkers with resnet instead
2020-12-31 10:15:04 -07:00
James Betker
8f18b2709e
Get rid of CUDA_VISIBLE_DEVICES
...
It is not clear to me what the purpose of this is, but it has recently
started causing failures.
2020-12-31 10:13:58 -07:00
James Betker
1de1fa30ac
Disable refs and centers altogether in single_image_dataset
...
I suspect that this might be a cause of failures on parallel datasets.
Plus it is unnecessary computation.
2020-12-31 10:13:24 -07:00
James Betker
8f0984cacf
Add sr_fid evaluator
2020-12-30 20:18:58 -07:00
James Betker
b1fb82476b
Add gp debug (fix)
2020-12-30 15:26:54 -07:00
James Betker
9c53314ea2
Add gradient penalty visual debug
2020-12-30 09:51:59 -07:00
James Betker
63cf3d3126
Injector auto-registration
...
I love it!
2020-12-29 20:58:02 -07:00
James Betker
a777c1e4f9
Misc script fixes
2020-12-29 20:25:09 -07:00
James Betker
9dc3c8f0ff
Script updates
2020-12-29 20:24:41 -07:00
James Betker
ba543d1152
Glean mods
...
- Fixes fixed upscale factor issues
- Refines a few ops to decrease computation & parameterization
2020-12-27 12:25:06 -07:00
James Betker
5e2e605a50
Merge remote-tracking branch 'origin/gan_lab' into gan_lab
2020-12-26 13:51:19 -07:00
James Betker
f9be049adb
GLEAN mod to support custom initial strides
2020-12-26 13:51:14 -07:00
James Betker
2706a84f15
Merge remote-tracking branch 'origin/gan_lab' into gan_lab
2020-12-26 13:50:34 -07:00
James Betker
90e2362c00
Fix bug with full_image_dataset
2020-12-26 13:50:27 -07:00
James Betker
3fd627fc62
Mods to support image classification & filtering
2020-12-26 13:49:27 -07:00
James Betker
10fdfa1563
Migrate generators to dynamic model registration
2020-12-24 23:02:10 -07:00
James Betker
29db7c7a02
Further mods to BYOL
2020-12-24 09:28:41 -07:00
James Betker
036684893e
Add LARS optimizer & support for BYOL idiosyncrasies
...
- Added LARS and SGD optimizer variants that support turning off certain
features for BN and bias layers
- Added a variant of pytorch's resnet model that supports gradient checkpointing.
- Modify the trainer infrastructure to support above
- Fix bug with BYOL (should have been nonfunctional)
2020-12-23 20:33:43 -07:00
James Betker
1bbcb96ee8
Implement a few changes to support training BYOL networks
2020-12-23 10:50:23 -07:00
James Betker
2437b33e74
Fix srflow_latent_space_playground bug
2020-12-22 15:42:38 -07:00
James Betker
e7aeb17404
ImageFolder dataset: allow intermediary downscale before corrupt
...
For massive upscales (ex: 8x), corruption does almost nothing when applied
at the HQ level. This patch adds support to perform corruption at a specified
intermediary scale. The dataset downscales to this level, performs the corruption,
then downscales the rest of the way to get the LQ image.
2020-12-22 15:42:21 -07:00
James Betker
7938f9f50b
Fix bug with single_image_dataset which prevented working on multiple directories from working
2020-12-19 15:13:46 -07:00
James Betker
ae666dc520
Fix bugs with srflow after refactor
2020-12-19 10:28:23 -07:00
James Betker
4328c2f713
Change default ReLU slope to .2 BREAKS COMPATIBILITY
...
This conforms my ConvGnLelu implementation with the generally accepted negative_slope=.2. I have no idea where I got .1. This will break backwards compatibility with some older models but will likely improve their performance when freshly trained. I did some auditing to find what these models might be, and I am not actively using any of them, so probably OK.
2020-12-19 08:28:03 -07:00
James Betker
9377d34ac3
glean mods
2020-12-19 08:26:07 -07:00
James Betker
f35c034fa5
Add trainer readme
2020-12-18 16:52:16 -07:00
James Betker
e82f4552db
Update other docs with dumb config options
2020-12-18 16:21:28 -07:00
James Betker
92f9a129f7
GLEAN!
2020-12-18 16:04:19 -07:00
James Betker
c717765bcb
Notes for lucidrains converter.
2020-12-18 09:55:38 -07:00
James Betker
b4720ea377
Move stylegan to new location
2020-12-18 09:52:36 -07:00
James Betker
1708136b55
Commit my attempt at "conforming" the lucidrains stylegan implementation to the reference spec. Not working. will probably be abandoned.
2020-12-18 09:51:48 -07:00
James Betker
209332292a
Rosinality stylegan fix
2020-12-18 09:50:41 -07:00
James Betker
d875ca8342
More refactor changes
2020-12-18 09:24:31 -07:00
James Betker
5640e4efe4
More refactoring
2020-12-18 09:18:34 -07:00
James Betker
b905b108da
Large cleanup
...
Removed a lot of old code that I won't be touching again. Refactored some
code elements into more logical places.
2020-12-18 09:10:44 -07:00
James Betker
2f0a52b7db
misc changes
2020-12-18 08:53:45 -07:00
James Betker
a8179ff53c
Image label work
2020-12-18 08:53:18 -07:00
James Betker
3074f41877
Get rosinality model converter to work
...
Mostly, just needed to remove the custom cuda ops, not so bueno on Windows.
2020-12-17 16:03:39 -07:00
James Betker
e838c6e75b
Rosinality stylegan2 port
2020-12-17 14:18:46 -07:00
James Betker
12cf052889
Add an image patch labeling UI
2020-12-17 10:16:21 -07:00
James Betker
49327b99fe
SRFlow outputs RRDB output
2020-12-16 10:28:02 -07:00
James Betker
c25b49bb12
Clean up of SRFlowNet_arch
2020-12-16 10:27:38 -07:00
James Betker
42ac8e3eeb
Remove unnecessary comment from SRFlowNet
2020-12-16 09:43:07 -07:00
James Betker
fb2cfc795b
Update requirements, add image_patch_classifier tool
2020-12-16 09:42:50 -07:00
James Betker
09de3052ac
Add softmax to spinenet classification head
2020-12-16 09:42:15 -07:00
James Betker
4310e66848
Fix bug in 'corrupt_before_downsize=true'
2020-12-16 09:41:59 -07:00
James Betker
8661207d57
Merge branch 'gan_lab' of https://github.com/neonbjb/DL-Art-School into gan_lab
2020-12-15 17:16:48 -07:00
James Betker
fc376d34b2
Spinenet with logits head
2020-12-15 17:16:19 -07:00
James Betker
8e0e883050
Mods to support labeled datasets & random augs for those datasets
2020-12-15 17:15:56 -07:00
James Betker
e5a3e6b9b5
srflow latent space misc
2020-12-14 23:59:49 -07:00
James Betker
1e14635d88
Add exclusions to extract_subimages_with_ref
2020-12-14 23:59:41 -07:00
James Betker
0a19e53df0
BYOL mods
2020-12-14 23:59:11 -07:00
James Betker
ef7eabf457
Allow RRDB to upscale 8x
2020-12-14 23:58:52 -07:00
James Betker
087e9280ed
Add labeling feature to image_folder_dataset
2020-12-14 23:58:37 -07:00
James Betker
ec0ee25f4b
Structural latents checkpoint
2020-12-11 12:01:09 -07:00
James Betker
26ceca68c0
BYOL with structure!
2020-12-10 15:07:35 -07:00
James Betker
9c5e272a22
Script to extract models from a wrapped BYOL model
2020-12-10 09:57:52 -07:00
James Betker
a5630d282f
Get rid of 2nd trainer
2020-12-10 09:57:38 -07:00
James Betker
8e4b9f42fd
New BYOL dataset which uses a form of RandomCrop that lends itself to
...
structural guidance to the latents.
2020-12-10 09:57:18 -07:00
James Betker
c203cee31e
Allow swapping to torch DDP as needed in code
2020-12-09 15:03:59 -07:00
James Betker
66cbae8731
Add random_dataset for testing
2020-12-09 14:55:05 -07:00
James Betker
97ff25a086
BYOL!
...
Man, is there anything ExtensibleTrainer can't train? :)
2020-12-08 13:07:53 -07:00
James Betker
5369cba8ed
Stage
2020-12-08 00:33:07 -07:00
James Betker
bca59ed98a
Merge remote-tracking branch 'origin/gan_lab' into gan_lab
2020-12-07 12:51:04 -07:00
James Betker
ea56eb61f0
Fix DDP errors for discriminator
...
- Don't define training_net in define_optimizers - this drops the shell and leads to problems downstream
- Get rid of support for multiple training nets per opt. This was half baked and needs a better solution if needed
downstream.
2020-12-07 12:50:57 -07:00
James Betker
c0aeaabc31
Spinenet playground
2020-12-07 12:49:32 -07:00
James Betker
88fc049c8d
spinenet latent playground!
2020-12-05 20:30:36 -07:00
James Betker
11155aead4
Directly use dataset keys
...
This has been a long time coming. Cleans up messy "GT" nomenclature and simplifies ExtensibleTraner.feed_data
2020-12-04 20:14:53 -07:00
James Betker
8a83b1c716
Go back to apex DDP, fix distributed bugs
2020-12-04 16:39:21 -07:00
James Betker
7a81d4e2f4
Revert gaussian loss changes
2020-12-04 12:49:20 -07:00
James Betker
711780126e
Cleanup
2020-12-03 23:42:51 -07:00
James Betker
ac7256d4a3
Do tqdm reporting when calculating flow_gaussian_nll
2020-12-03 23:42:29 -07:00
James Betker
dc9ff8e05b
Allow the majority of the srflow steps to checkpoint
2020-12-03 23:41:57 -07:00
James Betker
06d1c62c5a
iGPT support!
...
Sweeeeet
2020-12-03 15:32:21 -07:00
James Betker
c18adbd606
Delete mdcn & panet
...
Garbage, all of it.
2020-12-02 22:25:57 -07:00
James Betker
f2880b33c9
Get rid of mean shift from MDCN
2020-12-02 14:18:33 -07:00
James Betker
8a00f15746
Implement FlowGaussianNll evaluator
2020-12-02 14:09:54 -07:00
James Betker
edf408508c
Fix discriminator
2020-12-01 17:45:56 -07:00
James Betker
c963e5f2ce
Add ImageFolderDataset
...
This one has been a long time coming.. How does torch not have something like this?
2020-12-01 17:45:37 -07:00
James Betker
9a421a41f4
SRFlow: accomodate mismatches between global scale and flow_scale
2020-12-01 11:11:51 -07:00
James Betker
8f65f81ddb
Adjustments to subimage extractor
2020-12-01 11:11:30 -07:00
James Betker
e343722d37
Add stepped rrdb
2020-12-01 11:11:15 -07:00
James Betker
2e0bbda640
Remove unused archs
2020-12-01 11:10:48 -07:00
James Betker
a1c8300052
Add mdcn
2020-11-30 16:14:21 -07:00
James Betker
1e0f69e34b
extra_conv in gn discriminator, multiframe support in rrdb.
2020-11-29 15:39:50 -07:00
James Betker
da604752e6
Misc RRDB changes
2020-11-29 12:21:31 -07:00
James Betker
f2422f1d75
Latent space playground
2020-11-29 09:33:29 -07:00
James Betker
a1d4c9f83c
multires rrdb work
2020-11-28 14:35:46 -07:00
James Betker
929cd45c05
Fix for RRDB scale
2020-11-27 21:37:10 -07:00
James Betker
71fa532356
Adjustments to how flow networks set size and scale
2020-11-27 21:37:00 -07:00
James Betker
6f958bb150
Maybe this is necessary after all?
2020-11-27 15:21:13 -07:00
James Betker
ef8d5f88c1
Bring split gaussian nll out of split so it can be computed accurately with the rest of the nll component
2020-11-27 13:30:21 -07:00
James Betker
11d2b70bdd
Latent space playground work
2020-11-27 12:03:16 -07:00
James Betker
4ab49b0d69
RRDB disc work
2020-11-27 12:03:08 -07:00
James Betker
6de4dabb73
Remove srflow (modified version)
...
Starting from orig and re-working from there.
2020-11-27 12:02:06 -07:00
James Betker
5f5420ff4a
Update to srflow_latent_space_playground
2020-11-26 20:31:21 -07:00
James Betker
fd356580c0
Play with lambdas
2020-11-26 20:30:55 -07:00
James Betker
0c6d7971b9
Dataset documentation
2020-11-26 11:58:39 -07:00
James Betker
45a489110f
Fix datasets
2020-11-26 11:50:38 -07:00
James Betker
5edaf085e0
Adjustments to latent_space_playground
2020-11-25 15:52:36 -07:00
James Betker
205c9a5335
Learn how to functionally use srflow networks
2020-11-25 13:59:06 -07:00
James Betker
cb045121b3
Expose srflow rrdb
2020-11-24 13:20:20 -07:00
James Betker
f3c1fc1bcd
Dataset modifications
2020-11-24 13:20:12 -07:00
James Betker
f6098155cd
Mods to tecogan to allow use of embeddings as input
2020-11-24 09:24:02 -07:00
James Betker
b10bcf6436
Rework stylegan_for_sr to incorporate structure as an adain block
2020-11-23 11:31:11 -07:00
James Betker
519ba6f10c
Support 2x RRDB with 4x srflow
2020-11-21 14:46:15 -07:00
James Betker
cad92bada8
Report logp and logdet for srflow
2020-11-21 10:13:05 -07:00
James Betker
c37d3faa58
More adjustments to srflow_orig
2020-11-20 19:38:33 -07:00
James Betker
d51d12a41a
Adjustments to srflow to (maybe?) fix training
2020-11-20 14:44:24 -07:00
James Betker
6c8c35ac47
Support training RRDB encoder [srflow]
2020-11-20 10:03:06 -07:00
James Betker
5ccdbcefe3
srflow_orig integration
2020-11-19 23:47:24 -07:00
James Betker
f80acfcab6
Throw if dataset isn't going to work with force_multiple setting
2020-11-19 23:47:00 -07:00
James Betker
2b2d754d8e
Bring in an original SRFlow implementation for reference
2020-11-19 21:42:39 -07:00
James Betker
1e0d7be3ce
"Clean up" SRFlow
2020-11-19 21:42:24 -07:00
James Betker
d7877d0a36
Fixes to teco losses and translational losses
2020-11-19 11:35:05 -07:00
James Betker
b2a05465fc
Fix missing requirements
2020-11-18 10:16:39 -07:00
James Betker
5c10264538
Remove pyramid_disc hard dependencies
2020-11-17 18:34:11 -07:00
James Betker
6b679e2b51
Make grad_penalty available to classical discs
2020-11-17 18:31:40 -07:00
James Betker
8a19c9ae15
Add additive mode to rrdb
2020-11-16 20:45:09 -07:00
James Betker
2a507987df
Merge remote-tracking branch 'origin/gan_lab' into gan_lab
2020-11-15 16:16:30 -07:00
James Betker
931ed903c1
Allow combined additive loss
2020-11-15 16:16:18 -07:00
James Betker
4b68116977
import fix
2020-11-15 16:15:42 -07:00
James Betker
98eada1e4c
More circular dependency fixes + unet fixes
2020-11-15 11:53:35 -07:00
James Betker
e587d549f7
Fix circular imports
2020-11-15 11:32:35 -07:00
James Betker
99f0cfaab5
Rework stylegan2 divergence losses
...
Notably: include unet loss
2020-11-15 11:26:44 -07:00
James Betker
ea94b93a37
Fixes for unet
2020-11-15 10:38:33 -07:00
James Betker
89f56b2091
Fix another import
2020-11-14 22:10:45 -07:00
James Betker
9af049c671
Import fix for unet
2020-11-14 22:09:18 -07:00
James Betker
5cade6b874
Move stylegan2 around, bring in unet
2020-11-14 22:04:48 -07:00
James Betker
4c6b14a3f8
Allow extract_square_images to work on multiple images
2020-11-14 20:24:05 -07:00
James Betker
125cb16dce
Add a FID evaluator for stylegan with structural guidance
2020-11-14 20:16:07 -07:00
James Betker
c9258e2da3
Alter how structural guidance is given to stylegan
2020-11-14 20:15:48 -07:00
James Betker
3397c83447
Merge remote-tracking branch 'origin/gan_lab' into gan_lab
2020-11-14 09:30:09 -07:00
James Betker
423ee7cb90
Allow attention to be specified for stylegan2
2020-11-14 09:29:53 -07:00
James Betker
ec621c69b5
Fix train bug
2020-11-14 09:29:08 -07:00
James Betker
cdc5ac30e9
oddity
2020-11-13 20:11:57 -07:00
James Betker
f406a5dd4c
Mods to support stylegan2 in SR mode
2020-11-13 20:11:50 -07:00
James Betker
9c3d0b7560
Merge remote-tracking branch 'origin/gan_lab' into gan_lab
2020-11-13 20:10:47 -07:00
James Betker
67bf55495b
Allow hq_batched_key to be specified
2020-11-13 20:10:12 -07:00
James Betker
0b96811611
Fix another issue with gpu ids getting thrown all over hte place
2020-11-13 20:05:52 -07:00
James Betker
c47925ae34
New image extractor utility
2020-11-13 11:04:03 -07:00
James Betker
a07e1a7292
Add separate Evaluator module and FID evaluator
2020-11-13 11:03:54 -07:00
James Betker
080ad61be4
Add option to work with nonrandom latents
2020-11-12 21:23:50 -07:00
James Betker
566b99ca75
GP adjustments for stylegan2
2020-11-12 16:44:51 -07:00
James Betker
fc55bdb24e
Mods to how wandb are integrated
2020-11-12 15:45:25 -07:00
James Betker
44a19cd37c
ExtensibleTrainer mods to support advanced checkpointing for stylegan2
...
Basically: stylegan2 makes use of gradient-based normalizers. These
make it so that I cannot use gradient checkpointing. But I love gradient
checkpointing. It makes things really, really fast and memory conscious.
So - only don't checkpoint when we run the regularizer loss. This is a
bit messy, but speeds up training by at least 20%.
Also: pytorch: please make checkpointing a first class citizen.
2020-11-12 15:45:07 -07:00
James Betker
db9e9e28a0
Fix an issue where GPU0 was always being used in non-ddp
...
Frankly, I don't understand how this has ever worked. WTF.
2020-11-12 15:43:01 -07:00
James Betker
2d3449d7a5
stylegan2 in ml art school!
2020-11-12 15:42:05 -07:00
James Betker
fd97573085
Fixes
2020-11-11 21:49:06 -07:00