Commit Graph

270 Commits

Author SHA1 Message Date
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