mrq/DL-Art-School
1
3
Fork 5
Code Issues Pull Requests Packages Projects Releases Wiki Activity
1,776 Commits 1 Branch 0 Tags 5.6 MiB
88ec0512f7
Commit Graph

1742 Commits

Author SHA1 Message Date
James Betker
0005c56cd4 dbg 2020-08-23 17:43:03 -06:00
James Betker
4bb5b3c981 corfea debugging 2020-08-23 17:39:02 -06:00
James Betker
7713cb8df5 Corrupted features in srgan 2020-08-23 17:32:03 -06:00
James Betker
dffc15184d More ExtensibleTrainer work 
It runs now, just need to debug it to reach performance parity with SRGAN. Sweet.
 2020-08-23 17:22:45 -06:00
James Betker
afdd93fbe9 Grey feature 2020-08-22 13:41:38 -06:00
James Betker
e59e712e39 More ExtensibleTrainer work 2020-08-22 13:08:33 -06:00
James Betker
f40545f235 ExtensibleTrainer work 2020-08-22 08:24:34 -06:00
James Betker
a498d7b1b3 Report l_g_gan_grad before weight multiplication 2020-08-20 11:57:53 -06:00
James Betker
9d77a4db2e Allow initial temperature to be specified to SPSR net for inference 2020-08-20 11:57:34 -06:00
James Betker
24bdcc1181 Let SwitchedSpsr transform count be specified 2020-08-18 09:10:25 -06:00
James Betker
40bb0597bb misc 2020-08-18 08:50:24 -06:00
James Betker
74cdaa2226 Some work on extensible trainer 2020-08-18 08:49:32 -06:00
James Betker
0c98c61f4a Enable start_step to be specified 2020-08-15 18:34:59 -06:00
James Betker
868d0aa442 Undo early dim reduction on grad branch for SPSR_arch 2020-08-14 16:23:42 -06:00
James Betker
2d205f52ac Unite spsr_arch switched gens 
Found a pretty good basis model.
 2020-08-12 17:04:45 -06:00
James Betker
bdaa67deb7 Misc 2020-08-12 08:46:15 -06:00
James Betker
3d0ece804b SPSR LR2 2020-08-12 08:45:49 -06:00
James Betker
ab04ca1778 Extensible trainer (in progress) 2020-08-12 08:45:23 -06:00
James Betker
cb316fabc7 Use LR data for image gradient prediction when HR data is disjoint 2020-08-10 15:00:28 -06:00
James Betker
f0e2816239 Denoise attention maps 2020-08-10 14:59:58 -06:00
James Betker
59aba1daa7 LR switched SPSR arch 
This variant doesn't do conv processing at HR, which should save
a ton of memory in inference. Lets see how it works.
 2020-08-10 13:03:36 -06:00
James Betker
4e972144ae More attention fixes for switched_spsr 2020-08-07 21:11:50 -06:00
James Betker
d02509ef97 spsr_switched missing import 2020-08-07 21:05:29 -06:00
James Betker
887806ffa0 Finish up spsr_switched 2020-08-07 21:03:48 -06:00
James Betker
1d5f4f6102 Crossgan 2020-08-07 21:03:39 -06:00
James Betker
fd7b6ca0a9 Comptue gan_grad_branch.... 2020-08-06 12:11:40 -06:00
James Betker
30b16d5235 Update how branch GAN grad is disseminated 2020-08-06 11:13:02 -06:00
James Betker
1f21c02f8b Add cross-compare discriminator 2020-08-06 08:56:21 -06:00
James Betker
be272248af More RAGAN fixes 2020-08-05 16:47:21 -06:00
James Betker
26a6a5d512 Compute grad GAN loss against both the branch and final target, simplify pixel loss 
Also fixes a memory leak issue where we weren't detaching our loss stats when
logging them. This stabilizes memory usage substantially.
 2020-08-05 12:08:15 -06:00
James Betker
299ee13988 More RAGAN fixes 2020-08-05 11:03:06 -06:00
James Betker
b8a4df0a0a Enable RAGAN in SPSR, retrofit old RAGAN for efficiency 2020-08-05 10:34:34 -06:00
James Betker
3ab39f0d22 Several new spsr nets 2020-08-05 10:01:24 -06:00
James Betker
3c0a2d6efe Fix grad branch debug out 2020-08-04 16:43:43 -06:00
James Betker
ec2a795d53 Fix multistep optimizer (feeding from wrong config params) 2020-08-04 16:42:58 -06:00
James Betker
4bfbdaf94f Don't recompute generator outputs for D in standard operation 
Should significantly improve training performance with negligible
results differences.
 2020-08-04 11:28:52 -06:00
James Betker
11b227edfc Whoops 2020-08-04 10:30:40 -06:00
James Betker
6d25bcd5df Apply fixes to grad discriminator 2020-08-04 10:25:13 -06:00
James Betker
96d66f51c5 Update requirements 2020-08-03 16:57:56 -06:00
James Betker
c7e5d3888a Add pix_grad_branch loss to metrics 2020-08-03 16:21:05 -06:00
James Betker
0d070b47a7 Add simplified SPSR architecture 
Basically just cleaning up the code, removing some bad conventions,
and reducing complexity somewhat so that I can play around with
this arch a bit more easily.
 2020-08-03 10:25:37 -06:00
James Betker
47e24039b5 Fix bug that makes feature loss run even when it is off 2020-08-02 20:37:51 -06:00
James Betker
328afde9c0 Integrate SPSR into SRGAN_model 
SPSR_model really isn't that different from SRGAN_model. Rather than continuing to re-implement
everything I've done in SRGAN_model, port the new stuff from SPSR over.

This really demonstrates the need to refactor SRGAN_model a bit to make it cleaner. It is quite the
beast these days..
 2020-08-02 12:55:08 -06:00
James Betker
c8da78966b Substantial SPSR mods & fixes 
- Added in gradient accumulation via mega-batch-factor
- Added AMP
- Added missing train hooks
- Added debug image outputs
- Cleaned up including removing GradientPenaltyLoss, custom SpectralNorm
- Removed all the custom discriminators
 2020-08-02 10:45:24 -06:00
James Betker
f894ba8f98 Add SPSR_module 
This is a port from the SPSR repo, it's going to need a lot of work to be properly integrated
but as of this commit it at least runs.
 2020-08-01 22:02:54 -06:00
James Betker
f33ed578a2 Update how attention_maps are created 2020-08-01 20:23:46 -06:00
James Betker
c139f5cd17 More torch 1.6 fixes 2020-07-31 17:03:20 -06:00
James Betker
a66fbb32b6 Fix fixed_disc DataParallel issue 2020-07-31 16:59:23 -06:00
James Betker
8dd44182e6 Fix scale torch warning 2020-07-31 16:56:04 -06:00
James Betker
bcebed19b7 Fix pixdisc bugs 2020-07-31 16:38:14 -06:00
James Betker
eb11a08d1c Enable disjoint feature networks 
This is done by pre-training a feature net that predicts the features
of HR images from LR images. Then use the original feature network
and this new one in tandem to work only on LR/Gen images.
 2020-07-31 16:29:47 -06:00
James Betker
6e086d0c20 Fix fixed_disc 2020-07-31 15:07:10 -06:00
James Betker
d5fa059594 Add capability to have old discriminators serve as feature networks 2020-07-31 14:59:54 -06:00
James Betker
6b45b35447 Allow multi_step_lr_scheduler to load a new LR schedule when restoring state 2020-07-31 11:21:11 -06:00
James Betker
e37726f302 Add feature_model for training custom feature nets 2020-07-31 11:20:39 -06:00
James Betker
7629cb0e61 Add FDPL Loss 
New loss type that can replace PSNR loss. Works against the frequency domain
and focuses on frequency features loss during hr->lr conversion.
 2020-07-30 20:47:57 -06:00
James Betker
85ee64b8d9 Turn down feadisc intensity 
Honestly - this feature is probably going to be removed soon, so backwards
compatibility is not a huge deal anymore.
 2020-07-27 15:28:55 -06:00
James Betker
ebb199e884 Get rid of safety valve (probably being encountered in val) 2020-07-26 22:51:59 -06:00
James Betker
0892d5fe99 LQGT_dataset gan debug 2020-07-26 22:48:35 -06:00
James Betker
d09ed4e5f7 Misc fixes 2020-07-26 22:44:24 -06:00
James Betker
c54784ae9e Fix feature disc log item error 2020-07-26 22:25:59 -06:00
James Betker
9a8f227501 Allow separate dataset to pushed in for GAN-only training 2020-07-26 21:44:45 -06:00
James Betker
b06e1784e1 Fix SRG4 & switch disc 
"fix". hehe.
 2020-07-25 17:16:54 -06:00
James Betker
e6e91a1d75 Add SRG4 
Back to the idea that maybe what we need is a hybrid
approach between pure switches and RDB.
 2020-07-24 20:32:49 -06:00
James Betker
3320ad685f Fix mega_batch_factor not set for test 2020-07-24 12:26:44 -06:00
James Betker
c50cce2a62 Add an abstract, configurabler weight scheduling class and apply it to the feature weight 2020-07-23 17:03:54 -06:00
James Betker
9ccf771629 Fix feature validation, wrong device 
Only shows up in distributed training for some reason.
 2020-07-23 10:16:34 -06:00
James Betker
a7541b6d8d Fix illegal tb_logger use in distributed training 2020-07-23 09:14:01 -06:00
James Betker
bba283776c Enable find_unused_parameters for DistributedDataParallel 
attention_norm has some parameters which are not used to compute grad,
which is causing failures in the distributed case.
 2020-07-23 09:08:13 -06:00
James Betker
dbf6147504 Add switched discriminator 
The logic is that the discriminator may be incapable of providing a truly
targeted loss for all image regions since it has to be too generic
(basically the same argument for the switched generator). So add some
switches in! See how it works!
 2020-07-22 20:52:59 -06:00
James Betker
8a0a1569f3 Enable force_multiple in LQ_dataset 2020-07-22 20:51:16 -06:00
James Betker
106b8da315 Assert that temperature is set properly in eval mode. 2020-07-22 20:50:59 -06:00
James Betker
c74b9ee2e4 Add a way to disable grad on portions of the generator graph to save memory 2020-07-22 11:40:42 -06:00
James Betker
e3adafbeac Add convert_model.py and a hacky way to add extra layers to a model 2020-07-22 11:39:45 -06:00
James Betker
7f7e17e291 Update feature discriminator further 
Move the feature/disc losses closer and add a feature computation layer.
 2020-07-20 20:54:45 -06:00
James Betker
46aa776fbb Allow feature discriminator unet to only output closest layer to feature output 2020-07-19 19:05:08 -06:00
James Betker
8a9f215653 Huge set of mods to support progressive generator growth 2020-07-18 14:18:48 -06:00
James Betker
47a525241f Make attention norm optional 2020-07-18 07:24:02 -06:00
James Betker
ad97a6a18a Progressive SRG first check-in 2020-07-18 07:23:26 -06:00
James Betker
b08b1cad45 Fix feature decay 2020-07-16 23:27:06 -06:00
James Betker
3e7a83896b Fix pixgan debugging issues 2020-07-16 11:45:19 -06:00
James Betker
a1bff64d1a More fixes 2020-07-16 10:48:48 -06:00
James Betker
240f254263 More loss fixes 2020-07-16 10:45:50 -06:00
James Betker
6cfa67d831 Fix featuredisc broadcast error 2020-07-16 10:18:30 -06:00
James Betker
8d061a2687 Add u-net discriminator with feature output 2020-07-16 10:10:09 -06:00
James Betker
0c4c388e15 Remove dualoutputsrg 
Good idea, didn't pan out.
 2020-07-16 10:09:24 -06:00
James Betker
4bcc409fc7 Fix loadSRG2 typo 2020-07-14 10:20:53 -06:00
James Betker
1e4083a35b Apply temperature mods to all SRG models 
(Honestly this needs to be base classed at this point)
 2020-07-14 10:19:35 -06:00
James Betker
7659bd6818 Fix temperature equation 2020-07-14 10:17:14 -06:00
James Betker
853468ef82 Allow legacy state_dicts in srg2 2020-07-14 10:03:45 -06:00
James Betker
1b1431133b Add DualOutputSRG 
Also removes the old multi-return mechanism that Generators support.
Also fixes AttentionNorm.
 2020-07-14 09:28:24 -06:00
James Betker
a2285ff2ee Scale anorm by transform count 2020-07-13 08:49:09 -06:00
James Betker
dd0bbd9a7c Enable AttentionNorm on SRG2 2020-07-13 08:38:17 -06:00
James Betker
4c0f770f2a Fix inverted temperature curve bug 2020-07-12 11:02:50 -06:00
James Betker
14d23b9d20 Fixes, do fake swaps less often in pixgan discriminator 2020-07-11 21:22:11 -06:00
James Betker
ba6187859a err5 2020-07-10 23:02:56 -06:00
James Betker
902527dfaa err4 2020-07-10 23:00:21 -06:00
James Betker
020b3361fa err3 2020-07-10 22:57:34 -06:00
James Betker
b3a2c21250 err2 2020-07-10 22:52:02 -06:00
James Betker
716433db1f err1 2020-07-10 22:50:56 -06:00
James Betker
ef9f1307eb Sometimes don't use compression artifacts 2020-07-10 22:25:53 -06:00
James Betker
0b7193392f Implement unet disc 
The latest discriminator architecture was already pretty much a unet. This
one makes that official and uses shared layers. It also upsamples one additional
time and throws out the lowest upsampling result.

The intent is to delete the old vgg pixdisc, but I'll keep it around for a bit since
I'm still trying out a few models with it.
 2020-07-10 16:24:42 -06:00
James Betker
812c684f7d Update pixgan swap algorithm 
- Swap multiple blocks in the image instead of just one. The discriminator was clearly
  learning that most blocks have one region that needs to be fixed.
- Relax block size constraints. This was in place to gaurantee that the discriminator
  signal was clean. Instead, just downsample the "loss image" with bilinear interpolation.
  The result is noisier, but this is actually probably healthy for the discriminator.
 2020-07-10 15:56:14 -06:00
James Betker
33ca3832e1 Move ExpansionBlock to arch_util 
Also makes all processing blocks have a conformant signature.

Alters ExpansionBlock to perform a processing conv on the passthrough
before the conjoin operation - this will break backwards compatibilty with SRG2.
 2020-07-10 15:53:41 -06:00
James Betker
5e8b52f34c Misc changes 2020-07-10 09:45:48 -06:00
James Betker
5f2c722a10 SRG2 revival 
Big update to SRG2 architecture to pull in a lot of things that have been learned:
- Use group norm instead of batch norm
- Initialize the weights on the transformations low like is done in RRDB rather than using the scalar. Models live or die by their early stages, and this ones early stage is pretty weak
- Transform multiplexer to use u-net like architecture.
- Just use one set of configuration variables instead of a list - flat networks performed fine in this regard.
 2020-07-09 17:34:51 -06:00
James Betker
12da993da8 More fixes... 2020-07-08 22:07:09 -06:00
James Betker
7d6eb28b87 More fixes 2020-07-08 22:00:57 -06:00
James Betker
b2507be13c Fix up pixgan loss and pixdisc 2020-07-08 21:27:48 -06:00
James Betker
26a4a66d1c Bug fixes and new gan mechanism 
- Removed a bunch of unnecessary image loggers. These were just consuming space and never being viewed
- Got rid of support of artificial var_ref support. The new pixdisc is what i wanted to implement then - it's much better.
- Add pixgan GAN mechanism. This is purpose-built for the pixdisc. It is intended to promote a healthy discriminator
- Megabatchfactor was applied twice on metrics, fixed that

Adds pix_gan (untested) which swaps a portion of the fake and real image with each other, then expects the discriminator
to properly discriminate the swapped regions.
 2020-07-08 17:40:26 -06:00
James Betker
4305be97b4 Update log metrics 
They should now be universal regardless of job configuration
 2020-07-07 15:33:22 -06:00
James Betker
8a4eb8241d SRG3 work 
Operates on top of a pre-trained SpineNET backbone (trained on CoCo 2017 with RetinaNet)

This variant is extremely shallow.
 2020-07-07 13:46:40 -06:00
James Betker
0acad81035 More SRG2 adjustments.. 2020-07-06 22:40:40 -06:00
James Betker
086b2f0570 More bugs 2020-07-06 22:28:07 -06:00
James Betker
d4d4f85fc0 Bug fixes 2020-07-06 22:25:40 -06:00
James Betker
3c31bea1ac SRG2 architectural changes 2020-07-06 22:22:29 -06:00
James Betker
9a1c3241f5 Switch discriminator to groupnorm 2020-07-06 20:59:59 -06:00
James Betker
60c6352843 Misc 2020-07-06 20:44:07 -06:00
James Betker
6beefa6d0c PixDisc - Add two more levels of losses coming from this gen at higher resolutions 2020-07-06 11:15:52 -06:00
James Betker
2636d3b620 Fix assertion error 2020-07-06 09:23:53 -06:00
James Betker
8f92c0a088 Interpolate attention well before softmax 2020-07-06 09:18:30 -06:00
James Betker
72f90cabf8 More pixdisc fixes 2020-07-05 22:03:16 -06:00
James Betker
909007ee6a Add G_warmup 
Let the Generator get to a point where it is at least competing with the discriminator before firing off.

Backwards from most GAN architectures, but this one is a bit different from most.
 2020-07-05 21:58:35 -06:00
James Betker
a47a5dca43 Fix pixdisc bug 2020-07-05 21:57:52 -06:00
James Betker
d0957bd7d4 Alter weight initialization for transformation blocks 2020-07-05 17:32:46 -06:00
James Betker
16d1bf6dd7 Replace ConvBnRelus in SRG2 with Silus 2020-07-05 17:29:20 -06:00
James Betker
10f7e49214 Add ConvBnSilu to replace ConvBnRelu 
Relu produced good performance gains over LeakyRelu, but
GAN performance degraded significantly. Try SiLU as an alternative
to see if it's the leaky-ness we are looking for or the smooth activation
curvature.
 2020-07-05 13:39:08 -06:00
James Betker
9934e5d082 Move SRG1 to identical to new 2020-07-05 08:49:34 -06:00
James Betker
416538f31c SRG1 conjoined except ConvBnRelu 2020-07-05 08:44:17 -06:00
James Betker
c58c2b09ca Back to remove all biases (looks like a ConvBnRelu made its way in..) 2020-07-04 22:41:02 -06:00
James Betker
86cda86e94 Re-add biases, also add new init 
A/B testing where we lost our GAN competitiveness.
 2020-07-04 22:24:42 -06:00
James Betker
b03741f30e Remove all biases from generator 
Continuing to investigate loss of GAN competitiveness, this is a big difference
between "old" SRG1 and "new".
 2020-07-04 22:19:55 -06:00
James Betker
726e946e79 Turn BN off in SRG1 
This wont work well but just testing if GAN performance comes back
 2020-07-04 14:51:27 -06:00
James Betker
0ee39d419b OrderedDict not needed 2020-07-04 14:09:27 -06:00
James Betker
9048105b72 Break out SRG1 as separate network 
Something strange is going on. These networks do not respond to
discriminator gradients properly anymore. SRG1 did, however so
reverting back to last known good state to figure out why.
 2020-07-04 13:28:50 -06:00
James Betker
188de5e15a Misc changes 2020-07-04 13:22:50 -06:00
James Betker
510b2f887d Remove RDB from srg2 
Doesnt seem to work so great.
 2020-07-03 22:31:20 -06:00
James Betker
77d3765364 Fix new feature loss calc 2020-07-03 22:20:13 -06:00
James Betker
ed6a15e768 Add feature to dataset which allows it to force images to be a certain size. 2020-07-03 15:19:16 -06:00
James Betker
da4335c25e Add a feature-based validation test 2020-07-03 15:18:57 -06:00
James Betker
703dec4472 Add SpineNet & integrate with SRG 
New version of SRG uses SpineNet for a switch backbone.
 2020-07-03 12:07:31 -06:00
James Betker
3ed7a2b9ab Move ConvBnRelu/Lelu to arch_util 2020-07-03 12:06:38 -06:00
James Betker
ea9c6765ca Move train imports into init_dist 2020-07-02 15:11:21 -06:00
James Betker
e9ee67ff10 Integrate RDB into SRG 
The last RDB for each cluster is switched.
 2020-07-01 17:19:55 -06:00
James Betker
6ac6c95177 Fix scaling bug 2020-07-01 16:42:27 -06:00
James Betker
30653181ba Experiment: get rid of post_switch_conv 2020-07-01 16:30:40 -06:00
James Betker
17191de836 Experiment: bring initialize_weights back again 
Something really strange going on here..
 2020-07-01 15:58:13 -06:00
James Betker
d1d573de07 Experiment: new init and post-switch-conv 2020-07-01 15:25:54 -06:00
James Betker
480d1299d7 Remove RRDB with switching 
This idea never really panned out, removing it.
 2020-07-01 12:08:32 -06:00
James Betker
e2398ac83c Experiment: revert initialization changes 2020-07-01 12:08:09 -06:00
James Betker
78276afcaa Experiment: Back to lelu 2020-07-01 11:43:25 -06:00
James Betker
b945021c90 SRG v2 - Move to Relu, rely on Module-based initialization 2020-07-01 11:33:32 -06:00
James Betker
ee6443ad7d Add numeric stability computation script 2020-07-01 11:30:34 -06:00
James Betker
c0bb123504 Misc changes 2020-07-01 11:28:23 -06:00
James Betker
604763be68 NSG r7 
Converts the switching trunk to a VGG-style network to make it more comparable
to SRG architectures.
 2020-07-01 09:54:29 -06:00
James Betker
87f1e9c56f Invert ResGen2 to operate in LR space 2020-06-30 20:57:40 -06:00
James Betker
e07d8abafb NSG rev 6 
- Disable style passthrough
- Process multiplexers starting at base resolution
 2020-06-30 20:47:26 -06:00
James Betker
3ce1a1878d NSG improvements (r5) 
- Get rid of forwards(), it makes numeric_stability.py not work properly.
- Do stability auditing across layers.
- Upsample last instead of first, work in much higher dimensionality for transforms.
 2020-06-30 16:59:57 -06:00
James Betker
75f148022d Even more NSG improvements (r4) 2020-06-30 13:52:47 -06:00
James Betker
773753073f More NSG improvements (v3) 
Move to a fully fixup residual network for the switch (no
batch norms). Fix a bunch of other small bugs. Add in a
temporary latent feed-forward from the bottom of the
switch. Fix several initialization issues.
 2020-06-29 20:26:51 -06:00
James Betker
4b82d0815d NSG improvements 
- Just use resnet blocks for the multiplexer trunk of the generator
- Every block initializes itself, rather than everything at the end
- Cleans up some messy parts of the architecture, including unnecessary
  kernel sizes and places where BN is not used properly.
 2020-06-29 10:09:51 -06:00
James Betker
978036e7b3 Add NestedSwitchGenerator 
An evolution of SwitchedResidualGenerator, this variant nests attention
modules upon themselves to extend the representative capacity of the
model significantly.
 2020-06-28 21:22:05 -06:00
James Betker
6f2bc36c61 Distill_torchscript mods 
Starts down the path of writing a custom trace that works using torch's hook mechanism.
 2020-06-27 08:28:09 -06:00
James Betker
db08dedfe2 Add recover_tensorboard_log 
Generates a tb_logger from raw console output. Useful for colab sessions
that crash.
 2020-06-27 08:26:57 -06:00
James Betker
c8a670842e Missed networks.py in last commit 2020-06-25 18:36:06 -06:00
James Betker
407224eba1 Re-work SwitchedResgen2 
Got rid of the converged multiplexer bases but kept the configurable architecture. The
new multiplexers look a lot like the old one.

Took some queues from the transformer architecture: translate image to a higher filter-space
and stay there for the duration of the models computation. Also perform convs after each
switch to allow the model to anneal issues that arise.
 2020-06-25 18:17:05 -06:00
James Betker
42a10b34ce Re-enable batch norm on switch processing blocks 
Found out that batch norm is causing the switches to init really poorly -
not using a significant number of transforms. Might be a great time to
re-consider using the attention norm, but for now just re-enable it.
 2020-06-24 21:15:17 -06:00
James Betker
4001db1ede Add ConfigurableSwitchComputer 2020-06-24 19:49:37 -06:00
James Betker
83c3b8b982 Add parameterized noise injection into resgen 2020-06-23 10:16:02 -06:00
James Betker
0584c3b587 Add negative_transforms switch to resgen 2020-06-23 09:41:12 -06:00
James Betker
dfcbe5f2db Add capability to place additional conv into discriminator 
This should allow us to support larger images sizes. May need
to add another one of these.
 2020-06-23 09:40:33 -06:00
James Betker
bad33de906 Add simple resize to extract images 2020-06-23 09:39:51 -06:00
James Betker
030648f2bc Remove batchnorms from resgen 2020-06-22 17:23:36 -06:00
James Betker
68bcab03ae Add growth channel to switch_growths for flat networks 2020-06-22 10:40:16 -06:00
James Betker
3b81712c49 Remove BN from transforms 2020-06-19 16:52:56 -06:00
James Betker
61364ec7d0 Fix inverse temperature curve logic and add upsample factor 2020-06-19 09:18:30 -06:00
James Betker
0551139b8d Fix resgen temperature curve below 1 
It needs to be inverted to maintain a true linear curve
 2020-06-18 16:08:07 -06:00
James Betker
efc80f041c Save & load amp state 2020-06-18 11:38:48 -06:00
James Betker
2e3b6bad77 Log tensorboard directly into experiments directory 2020-06-18 11:33:02 -06:00
James Betker
778e7b6931 Add a double-step to attention temperature 2020-06-18 11:29:31 -06:00
James Betker
d2d5e097d5 Add profiling to SRGAN for testing timings 2020-06-18 11:29:10 -06:00
James Betker
45a900fafe Misc 2020-06-18 11:28:55 -06:00
James Betker
59b0533b06 Fix attimage step size 2020-06-17 18:45:24 -06:00
James Betker
645d0ca767 ResidualGen mods 
- Add filters_mid spec which allows a expansion->squeeze for the transformation layers.
- Add scale and bias AFTER the switch
- Remove identity transform (models were converging on this)
- Move attention image generation and temperature setting into new function which gets called every step with a save path
 2020-06-17 17:18:28 -06:00
James Betker
6f8406fbdc Fixed ConfigurableSwitchedGenerator bug 2020-06-16 16:53:57 -06:00
James Betker
7d541642aa Get rid of SwitchedResidualGenerator 
Just use the configurable one instead..
 2020-06-16 16:23:29 -06:00
James Betker
379b96eb55 Output histograms with SwitchedResidualGenerator 
This also fixes the initialization weight for the configurable generator.
 2020-06-16 15:54:37 -06:00
James Betker
f8b67f134b Get proper contiguous view for backwards compatibility 2020-06-16 14:27:16 -06:00
James Betker
2def96203e Mods to SwitchedResidualGenerator_arch 
- Increased processing for high-resolution switches
- Do stride=2 first in HalvingProcessingBlock
 2020-06-16 14:19:12 -06:00
James Betker
70c764b9d4 Create a configurable SwichedResidualGenerator 
Also move attention image generator out of repo
 2020-06-16 13:24:07 -06:00
James Betker
df1046c318 New arch: SwitchedResidualGenerator_arch 
The concept here is to use switching to split the generator into two functions:
interpretation and transformation. Transformation is done at the pixel level by
relatively simple conv layers, while interpretation is computed at various levels
by far more complicated conv stacks. The two are merged using the switching
mechanism.

This architecture is far less computationally intensive that RRDB.
 2020-06-16 11:23:50 -06:00
James Betker
ddfd7f67a0 Get rid of biggan 
Not really sure it's a great fit for what is being done here.
 2020-06-16 11:21:44 -06:00
James Betker
0a714e8451 Fix initialization in mhead switched rrdb 2020-06-15 21:32:03 -06:00
James Betker
be7982b9ae Add skip heads to switcher 
These pass through the input so that it can be selected by the attention mechanism.
 2020-06-14 12:46:54 -06:00
James Betker
6c27ddc9b5 Misc 2020-06-14 11:03:02 -06:00
James Betker
6c0e9f45c7 Add GPU mem tracing module 2020-06-14 11:02:54 -06:00
James Betker
48532a0a8a Fix initial_stride on lowdim models 2020-06-14 11:02:16 -06:00
James Betker
532704af40 Multiple modifications for experimental RRDB architectures 
- Add LowDimRRDB; essentially a "normal RRDB" but the RDB blocks process at a low dimension using PixelShuffle
- Add switching wrappers around it
- Add support for switching on top of multi-headed inputs and outputs
- Moves PixelUnshuffle to arch_util
 2020-06-13 11:37:27 -06:00
James Betker
e89f28ead0 Update multirrdb to do HR fixing in the base image dimension. 2020-06-11 08:43:39 -06:00
James Betker
d3b2cbfe7c Fix loading new state dicts for RRDB 2020-06-11 08:25:57 -06:00
James Betker
5ca53e7786 Add alternative first block for PixShuffleRRDB 2020-06-10 21:45:24 -06:00
James Betker
43b7fccc89 Fix mhead attention integration bug for RRDB 2020-06-10 12:02:33 -06:00
James Betker
12e8fad079 Add serveral new RRDB architectures 2020-06-09 13:28:55 -06:00
James Betker
296135ec18 Add doResizeLoss to dataset 
doResizeLoss has a 50% chance to resize the LQ image to 50% size,
then back to original size. This is useful to training a generator to
recover these lost pixel values while also being able to do
repairs on higher resolution images during training.
 2020-06-08 11:27:06 -06:00
James Betker
786a4288d6 Allow switched RRDBNet to record metrics and decay temperature 2020-06-08 11:10:38 -06:00
James Betker
ae3301c0ea SwitchedRRDB work 
Renames AttentiveRRDB to SwitchedRRDB. Moves SwitchedConv to
an external repo (neonbjb/switchedconv). Switchs RDB blocks instead
of conv blocks. Works good!
 2020-06-08 08:47:34 -06:00
James Betker
93528ff8df Merge branch 'gan_lab' of https://github.com/neonbjb/mmsr into gan_lab 2020-06-07 16:59:31 -06:00
James Betker
805bd129b7 Switched conv partial impl 2020-06-07 16:59:22 -06:00
James Betker
9e203d07c4 Merge remote-tracking branch 'origin/gan_lab' into gan_lab 2020-06-07 16:56:12 -06:00
James Betker
299d855b34 Enable forced learning rates 2020-06-07 16:56:05 -06:00
James Betker
efb5b3d078 Add switched_conv 2020-06-07 16:45:07 -06:00
James Betker
063719c5cc Fix attention conv bugs 2020-06-06 18:31:02 -06:00
James Betker
cbedd6340a Add RRDB with attention 2020-06-05 21:02:08 -06:00
James Betker
ef5d8a0ed1 Misc 2020-06-05 21:01:50 -06:00
James Betker
318a604405 Allow weighting of input data 
This essentially allows you to give some datasets more
importance than others for the purposes of reaching a more
refined network.
 2020-06-04 10:05:21 -06:00
James Betker
edf0f8582e Fix rrdb bug 2020-06-02 11:15:55 -06:00
James Betker
dc17545083 Add RRDB Initial Stride 
Allows downsampling immediately before processing, which reduces network complexity on
higher resolution images but keeps a higher filter count.
 2020-06-02 10:47:15 -06:00
James Betker
76a38b6a53 Misc 2020-06-02 09:35:52 -06:00
James Betker
726d1913ac Allow validating in batches, remove val size limit 2020-06-02 08:41:22 -06:00
James Betker
90125f5bed Allow blurring to be specified 2020-06-02 08:40:52 -06:00
James Betker
8355f3d1b3 Only log discriminator data when gan is activated 2020-06-01 15:48:16 -06:00
James Betker
f1a1fd14b1 Introduce (untested) colab mode 2020-06-01 15:09:52 -06:00
James Betker
a38dd62489 Only train discriminator/gan losses when gan_w > 0 2020-06-01 15:09:10 -06:00
James Betker
1eb9c5a059 Fix grayscale 2020-05-29 22:04:50 -06:00
James Betker
2b03e40f98 Debug process_video 2020-05-29 20:44:50 -06:00
James Betker
74b313aaa9 Add grayscale downsampling option 2020-05-29 20:34:00 -06:00
James Betker
b123ed8a45 Add attention resnet 
Not ready for prime time, but is a first draft.
 2020-05-29 20:02:10 -06:00
James Betker
5e9da65d81 Fix process_video bugs 2020-05-29 12:47:22 -06:00
James Betker
beac71ad18 Allow minivids to start at any specified number 2020-05-28 20:27:42 -06:00
James Betker
57682ebee3 Separate feature extractors out, add resnet feature extractor 2020-05-28 20:26:30 -06:00
James Betker
156cee240a Remove reliance on magick, only wait for ffmpeg at last second, fix image ordering issue 2020-05-27 23:09:46 -06:00
James Betker
b551e86adb Encode videos to HEVC 
MP4 doesnt support 8K
 2020-05-27 20:04:45 -06:00
James Betker
bdeafad8c5 Only run 'convert' not magick 2020-05-27 17:24:10 -06:00
James Betker
41c1efbf56 Add dynamic video processing script 2020-05-27 17:09:11 -06:00
James Betker
f745be9dea Fix vgg disc arch 2020-05-27 13:31:22 -06:00
James Betker
6962ccb306 Adjust motion blur 
0 is invalid.
 2020-05-27 13:09:46 -06:00
James Betker
f6815df58b Misc 2020-05-27 08:04:47 -06:00
James Betker
e27a49454e Enable vertical splitting on inference images to support very large resolutions. 2020-05-27 08:04:35 -06:00
James Betker
96ac26a8b7 Allow injection of random low-amplitude noise & motion blur into generator 2020-05-27 08:04:11 -06:00
James Betker
69cbfa2f0c Adjust dataset mutations a bit 
Adjusts the compression artfacts to be more aggressive, and blurring to be less aggressive.
 2020-05-26 13:48:34 -06:00
James Betker
2931142458 Allow multiple gt image dirs 2020-05-25 19:21:09 -06:00
James Betker
4e44b8a1aa Clean up video stuff 2020-05-25 19:20:49 -06:00
James Betker
8464cae168 HQ blurring doesnt actually work right - hq images arent the right size when they are blurred 
Just revert it and blur the lq images..
 2020-05-24 22:32:54 -06:00
James Betker
5fd8749cf2 More updates - need more blurring 2020-05-24 22:13:27 -06:00
James Betker
9627cc2c49 Update HR gaussian blur params 2020-05-24 18:00:31 -06:00
James Betker
2f8b0250b9 Blur HR image before downsizing, when available 2020-05-24 17:18:44 -06:00
James Betker
cc4571eb8d Randomize blur effect 2020-05-24 12:35:41 -06:00
James Betker
27a548c019 Enable blurring via settings 2020-05-24 11:56:39 -06:00
James Betker
3c2e5a0250 Apply fixes to resgen 2020-05-24 07:43:23 -06:00
James Betker
446322754a Support generators that don't output intermediary values. 2020-05-23 21:09:54 -06:00
James Betker
987cdad0b6 Misc mods 2020-05-23 21:09:38 -06:00
James Betker
9b44f6f5c0 Add AssistedRRDB and remove RRDBNetXL 2020-05-23 21:09:21 -06:00
James Betker
445e7e7053 Extract subimages mod 2020-05-23 21:07:41 -06:00
James Betker
90073fc761 Update LQ_dataset to support inference on split image videos 2020-05-23 21:05:49 -06:00
James Betker
74bb0fad33 Allow dataset classes to add noise internally 2020-05-23 21:04:24 -06:00
James Betker
af1968f9e5 Allow passthrough discriminator to have passthrough disabled from config 2020-05-19 09:41:16 -06:00
James Betker
67139602f5 Test modifications 
Allows bifurcating large images put into the test pipeline

This code is fixed and not dynamic. Needs some fixes.
 2020-05-19 09:37:58 -06:00
James Betker
6400607fc5 ONNX export support 2020-05-19 09:36:04 -06:00
James Betker
89c71293ce IDEA update 2020-05-19 09:35:26 -06:00
James Betker
9cde58be80 Make RRDB usable in the current iteration 2020-05-16 18:36:30 -06:00
James Betker
b95c4087d1 Allow an alt_path for saving models and states 2020-05-16 09:10:51 -06:00
James Betker
f911ef0d3e Add corruptor_usage_probability 
Governs how often a corruptor is used, vs feeding uncorrupted images.
 2020-05-16 09:05:43 -06:00
James Betker
635c53475f Restore swapout models just before a checkpoint 2020-05-16 07:45:19 -06:00
James Betker
a33ec3e22b Fix skips & images samples 
- Makes skip connections between the generator and discriminator more
  extensible by adding additional configuration options for them and supporting
  1 and 0 skips.
- Places the temp/ directory with sample images from the training process appear
  in the training directory instead of the codes/ directory.
 2020-05-15 13:50:49 -06:00
James Betker
cdf641e3e2 Remove working options from repo 2020-05-15 07:50:55 -06:00
James Betker
bd4d478572 config changes 2020-05-15 07:41:18 -06:00
James Betker
79593803f2 biggan arch, initial work (not implemented) 2020-05-15 07:40:45 -06:00
James Betker
61ed51d9e4 Improve corruptor logic: switch corruptors randomly 2020-05-14 23:14:32 -06:00
James Betker
d72e154442 Allow more LQ than GT images in corrupt mode 2020-05-14 20:46:20 -06:00
James Betker
8a514b9645 Misc changes 2020-05-14 20:45:38 -06:00
James Betker
a946483f1c Fix discriminator noise floor 2020-05-14 20:45:06 -06:00
James Betker
c8ab89d243 Add model swapout 
Model swapout is a feature where, at specified intervals,
a random D and G model will be swapped in place for the
one being trained. After a short period of time, this model
is swapped back out. This is intended to increase training
diversity.
 2020-05-13 16:53:38 -06:00
James Betker
c336d32fd3 Config updates 2020-05-13 15:27:49 -06:00
James Betker
5bcf187fb6 Disable LMDB support 
It doesn't play nice with multiple dataroots and I don't
really see any need to continue support since I'm not
testing it.
 2020-05-13 15:27:33 -06:00
James Betker
e36f22e14a Allow "corruptor" network to be specified 
This network is just a fixed (pre-trained) generator
that performs a corruption transformation that the
generator-in-training is expected to undo alongside
SR.
 2020-05-13 15:26:55 -06:00
James Betker
f389025b53 Change ResGen noise feature 
It now injects noise directly into the input filters, rather than a
pure noise filter. The pure noise filter was producing really
poor results (and I'm honestly not quite sure why).
 2020-05-13 09:22:06 -06:00
James Betker
343af70a8d Add code for compiling model to torchscript 
I want to be able to export it to other formats too in the future.
 2020-05-13 09:21:13 -06:00
James Betker
585b05e66b Cap test workers at 10 2020-05-13 09:20:45 -06:00
James Betker
037a5a3cdb Config updates 2020-05-13 09:20:28 -06:00
James Betker
fc3ec8e3a2 Add a noise floor to th discriminator noise factor 2020-05-13 09:19:22 -06:00
James Betker
5d1b4caabf Allow noise to be injected at the generator inputs for resgen 2020-05-12 16:26:29 -06:00
James Betker
06d18343f7 Allow noise to be added to discriminator inputs 2020-05-12 16:25:38 -06:00
James Betker
9210a62f58 Add rotating log buffer to trainer 
Should stabilize stats output.
 2020-05-12 10:09:45 -06:00
James Betker
f217216c81 Implement ResGenv2 
Implements a ResGenv2 architecture which slightly increases the complexity
of the final output layer but causes it to be shared across all skip outputs.
 2020-05-12 10:09:15 -06:00
James Betker
1596a98493 Get rid of skip layers from vgg disc 2020-05-12 10:08:12 -06:00
James Betker
c540244789 Config file update 2020-05-12 10:07:58 -06:00
James Betker
62a97c53d1 Handle tuple-returning generators in test 2020-05-11 11:15:26 -06:00
James Betker
f994466289 Initialize test dataloader with a worker count proportional to the batch size. 2020-05-10 10:49:37 -06:00
James Betker
ef48e819aa Allow resgen to have a conditional number of upsamples applied to it 2020-05-10 10:48:37 -06:00
James Betker
8969a3ce70 Add capability to start at arbitrary frames 2020-05-10 10:48:05 -06:00
James Betker
03351182be Use amp in SR_model for inference 2020-05-07 21:45:33 -06:00
James Betker
dbca0d328c Fix multi-lq bug 2020-05-06 23:16:35 -06:00
James Betker
aa0305def9 Resnet discriminator overhaul 
It's been a tough day figuring out WTH is going on with my discriminators.
It appears the raw FixUp discriminator can get into an "defective" state where
they stop trying to learn and just predict as close to "0" D_fake and D_real as
possible. In this state they provide no feedback to the generator and never
recover. Adding batch norm back in seems to fix this so it must be some sort
of parameterization error.. Should look into fixing this in the future.
 2020-05-06 17:27:30 -06:00
James Betker
602f86bfa4 Random config changes 2020-05-06 17:25:48 -06:00
James Betker
574e7e882b Fix up OOM issues when running a disjoint D update ratio and megabatches 2020-05-06 17:25:25 -06:00
James Betker
eee9d6d9ca Support skip connections in vgg arch discriminator. 2020-05-06 17:24:34 -06:00
James Betker
5c1832e124 Add support for multiple LQ paths 
I want to be able to specify many different transformations onto
the target data; the model should handle them all. Do this by
allowing multiple LQ paths to be selected and the dataset class
selects one at random.
 2020-05-06 17:24:17 -06:00
James Betker
3cd85f8073 Implement ResGen arch 
This is a simpler resnet-based generator which performs mutations
on an input interspersed with interpolate-upsampling. It is a two
part generator:
1) A component that "fixes" LQ images with a long string of resnet
    blocks. This component is intended to remove compression artifacts
    and other noise from a LQ image.
2) A component that can double the image size. The idea is that this
    component be trained so that it can work at most reasonable
    resolutions, such that it can be repeatedly applied to itself to
    perform multiple upsamples.

The motivation here is to simplify what is being done inside of RRDB.
I don't believe the complexity inside of that network is justified.
 2020-05-05 11:59:46 -06:00
James Betker
9f4581aacb Fix megabatch scaling, log low and med-res gen images 2020-05-05 08:34:57 -06:00
James Betker
3b4e54c4c5 Add support for passthrough disc/gen 
Add RRDBNetXL, which performs processing at multiple image sizes.
Add DiscResnet_passthrough, which allows passthrough of image at different sizes for discrimination.
Adjust the rest of the repo to allow generators that return more than just a single image.
 2020-05-04 14:01:43 -06:00
James Betker
44b89330c2 Support inference across batches, support inference on cpu, checkpoint 
This is a checkpoint of a set of long tests with reduced-complexity networks. Some takeaways:
1) A full GAN using the resnet discriminator does appear to converge, but the quality is capped.
2) Likewise, a combination GAN/feature loss does not converge. The feature loss is optimized but
    the model appears unable to fight the discriminator, so the G-loss steadily increases.

Going forwards, I want to try some bigger models. In particular, I want to change the generator
to increase complexity and capacity. I also want to add skip connections between the
disc and generator.
 2020-05-04 08:48:25 -06:00
James Betker
9c7debe75c Add colab option 2020-05-02 17:47:25 -06:00
James Betker
832f3587c5 Turn off EVDR (so we dont need the weird convs) 2020-05-02 17:47:14 -06:00
James Betker
8341bf7646 Enable megabatching 2020-05-02 17:46:59 -06:00
James Betker
61d3040cf5 Add doCrop into LQGT 2020-05-02 17:46:30 -06:00
James Betker
9e1acfe396 Fixup upconv for the next attempt! 2020-05-01 19:56:14 -06:00
James Betker
7eaabce48d Full resnet corrupt, no BN 
And it works! Thanks fixup..
 2020-04-30 19:17:30 -06:00
James Betker
03258445bc tblogger.. 2020-04-30 12:35:51 -06:00
James Betker
b6e036147a Add more batch norms to FlatProcessorNet_arch 2020-04-30 11:47:21 -06:00
James Betker
66e91a3d9e Revert "Enable skip-through connections from disc to gen" 
This reverts commit b7857f35c3.
 2020-04-30 11:45:07 -06:00
James Betker
f027e888ed Clear out tensorboard on job restart. 2020-04-30 11:44:53 -06:00
James Betker
b7857f35c3 Enable skip-through connections from disc to gen 2020-04-30 11:30:11 -06:00
James Betker
bf634fc9fa Make resnet w/ BN discriminator use leaky relus 2020-04-30 11:28:59 -06:00
James Betker
3781ea725c Add Resnet Discriminator with BN 2020-04-29 20:51:57 -06:00
James Betker
a5188bb7ca Remover fixup code from arch_util 
Going into it's own arch.
 2020-04-29 15:17:43 -06:00
James Betker
5b8a77f02c Discriminator part 1 
New discriminator. Includes spectral norming.
 2020-04-28 23:00:29 -06:00
James Betker
2c145c39b6 Misc changes 2020-04-28 11:50:16 -06:00
James Betker
46f550e42b Change downsample_dataset to do no image modification 
I'm  preprocessing the images myself now. There's no need to have
the dataset do this processing as well.
 2020-04-28 11:50:04 -06:00
James Betker
8ab595e427 Add FlatProcessorNet 
After doing some thinking and reading on the subject, it occurred to me that
I was treating the generator like a discriminator by focusing the network
complexity at the feature levels. It makes far more sense to process each conv
level equally for the generator, hence the FlatProcessorNet in this commit. This
network borrows some of the residual pass-through logic from RRDB which makes
the gradient path exceptionally short for pretty much all model parameters and
can be trained in O1 optimization mode without overflows again.
 2020-04-28 11:49:21 -06:00
James Betker
b8f67418d4 Retool HighToLowResNet 
The receptive field of the original was *really* low. This new one has a
receptive field of 36x36px patches. It also has some gradient issues
that need to be worked out
 2020-04-26 01:13:42 -06:00
James Betker
02ff4a57fd Enable HighToLowResNet to do a 1:1 transform 2020-04-25 21:36:32 -06:00
James Betker
35bd1ecae4 Config changes for discriminator advantage run 
Still going from high->low, discriminator discerns on low. Next up disc works on high.
 2020-04-25 11:24:28 -06:00
James Betker
d95808f4ef Implement downsample GAN 
This bad boy is for a workflow where you train a model on disjoint image sets to
downsample a "good" set of images like a "bad" set of images looks. You then
use that downsampler to generate a training set of paired images for supersampling.
 2020-04-24 00:00:46 -06:00
James Betker
ea54c7618a Print error when image read fails 2020-04-23 23:59:32 -06:00
James Betker
e98d92fc77 Allow test to operate on batches 2020-04-23 23:59:09 -06:00
James Betker
8ead9ae183 Lots more config files 2020-04-23 23:58:27 -06:00
James Betker
ea5f432f5a Log total gen loss 2020-04-22 14:02:10 -06:00
James Betker
79aff886b5 Modifications that allow developer to explicitly specify a different image set for PIX and feature losses 2020-04-22 10:11:14 -06:00
James Betker
12d92dc443 Add GTLQ dataset 2020-04-22 00:40:38 -06:00
James Betker
4d269fdac6 Support independent PIX dataroot 2020-04-22 00:40:13 -06:00
James Betker
05aafef938 Support variant input sizes and scales 2020-04-22 00:39:55 -06:00
James Betker
ebda70fcba Fix AMP 2020-04-22 00:39:31 -06:00
James Betker
f4b33b0531 Some random fixes/adjustments 2020-04-22 00:38:53 -06:00
James Betker
2538ca9f33 Add my own configs 2020-04-22 00:37:54 -06:00
James Betker
af5dfaa90d Change GT_size to target_size 2020-04-22 00:37:41 -06:00
James Betker
cc834bd5a3 Support >128px image squares 2020-04-21 16:32:59 -06:00
James Betker
4f6d3f0dfb Enable AMP optimizations & write sample train images to folder. 2020-04-21 16:28:06 -06:00
PRAGMA
1fb12871fd
Create requirements.txt 2019-11-24 07:48:52 +00:00
XintaoWang
a25ee9464d test w/o GT 2019-09-01 22:20:10 +08:00
XintaoWang
0098663b6b SRGAN model supprots dist training 2019-09-01 22:14:29 +08:00
XintaoWang
866a858e59 add deform_conv_cuda_kernel.cu 2019-08-27 17:49:12 +08:00
XintaoWang
037933ba66 mmsr 2019-08-23 21:42:47 +08:00