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
