e5995630fc
fix
2019-02-10 23:00:08 +04:00
0866b2c509
manual extractor: added zoom for small faces
2019-02-10 22:40:57 +04:00
bda3fb3da1
refactoring
2019-02-10 21:40:58 +04:00
a65b557b0e
loss history with epoch now saves to preview history images
2019-02-07 22:34:51 +04:00
0d76bee2ee
fix Trainer.py for debug
2019-02-07 11:37:55 +04:00
72a640c66c
fox Converter.py for debug
2019-02-07 11:29:20 +04:00
5a1fb199f4
added support of non-english characters in paths
2019-02-05 19:33:55 +04:00
883da4b9ed
fix Util.py, SAE: lowest ae dims now can be 32 (for testing)
2019-02-05 14:43:54 +04:00
0fb3dd53ce
fix extractor jpg quality
2019-02-05 14:08:56 +04:00
6d95dd4a99
DFL now works with JPG files by default. Old PNG files also supported. Added util convertor PNG to JPG.
2019-02-04 19:47:24 +04:00
7ed7f2bab9
fixed bug in manual extractor on windows 10
2019-01-26 06:20:47 +04:00
72646becd1
forcing all tqdm's to ascii in order to work properly on Chinese windows
2019-01-24 21:32:07 +04:00
318e6608f7
Extractor: increased speed of deleted debug files searcher
2019-01-23 09:48:45 +04:00
21460c2e13
upd manual extractor help message
2019-01-22 18:15:55 +04:00
2571f23bc4
Extractor added new feature --manual-output-debug-fix,
...
Performs manual reextract input-dir frames which were deleted from [output_dir]_debug\ dir.
2019-01-22 12:46:54 +04:00
b6c4171ea1
optimizations of nnlib and SampleGeneratorFace,
...
refactorings
2019-01-22 11:52:04 +04:00
3bbc008207
change jpeg quality to 50%
2019-01-22 10:05:20 +04:00
8016ee32cc
change aligned_debug files from png to jpg
2019-01-22 09:55:41 +04:00
946688567d
enhanced SAE model. You should to restart training.
...
new default style power = 2.0
fix DF default batch sizes.
upd readme
2019-01-17 21:41:40 +04:00
1f2b1481ef
now you can train models on multiple GPU's on same workspace without cloning any folders.
...
Model files names will be prefixed with GPU index if GPU choosed explicitly on train/convert start.
if you leave GPU idx choice default, then best GPU idx will be choosed and model file names will not contain index prefix.
It gives you possibility to train same fake with various models or options on multiple GPUs.
H64 and H128: now you can choose 'Lighter autoencoder'. It is same as vram gb <= 4 before this update.
added archived_models.zip contains old experiments
RecycleGAN: archived
devicelib: if your system has no NVML installed (some old cards), then it will work with gpu_idx=0 as 'Generic GeForce GPU' with 2GB vram.
refactorings
2019-01-14 10:48:23 +04:00
12383570e8
Fix for systems without NVSMI
2019-01-13 16:38:17 +04:00
4625bcec1c
fix multigpu extractor
2019-01-13 13:59:22 +04:00
2473dabf37
fix loss history
2019-01-11 19:19:29 +04:00
c3f175862a
fix manual extractor bug
2019-01-10 05:12:02 +04:00
e8620919a7
update devicelib/nnlib to detect compute capability
2019-01-08 10:48:06 +04:00
cf41e1b962
fix sort by final
2019-01-07 17:27:10 +04:00
ff3a208e80
fix sort by final
2019-01-07 14:57:46 +04:00
abdbe7fd8d
added sort by 'final'
2019-01-07 14:20:44 +04:00
b5ba7d52cb
increased speed of sort by hist sim for ten thousands of faces
2019-01-04 22:54:09 +04:00
57e1e59c03
revert sort_by_hist
2019-01-02 23:53:27 +04:00
7b70e7eec1
added new model U-net Face Morpher.
...
removed AVATAR - useless model was just for demo
removed MIAEF128 - use UFM insted
removed LIAEF128YAW - use model option sort by yaw on start for any model
All models now ask some options on start.
Session options (such as target epoch, batch_size, write_preview_history etc) can be overrided by special command arg.
Converter now always ask options and no more support to define options via command line.
fix bug when ConverterMasked always used not predicted mask.
SampleGenerator now always generate samples with replicated border, exclude mask samples.
refactorings
2019-01-02 17:26:12 +04:00
f3782a012b
Update Trainer.py
2019-01-01 19:50:31 +04:00
5c0c79e528
fix last PR
2019-01-01 19:42:19 +04:00
c707fc0658
Update Trainer.py
2019-01-01 18:09:27 +04:00
a8694b73f0
DockerFile for Mac users to run DeepfaceLab with CPU Mode ( #95 )
...
* fix localization nullpointer exception
* fix devicelib error line:61,remove e
* support create docker from cpu dockerfile
* support preview or not when train(resolve cannot connect to X server)
2019-01-01 18:08:21 +04:00
f8824f9601
refactoring. Added RecycleGAN for testing.
2018-12-28 19:38:52 +04:00
a37af3e965
remove print_on_no_embedded_data=True on sort_by_hist_dissim
2018-12-25 19:50:25 +04:00
44798c2b85
refactoring
2018-12-22 19:37:25 +04:00
0d7387165a
added --cpu-only mode for all stages. Upd readme. Added requirements-cpu.txt
2018-12-21 16:54:22 +04:00
d04e8b1d91
increased speed of sort by hist
2018-12-20 18:04:13 +04:00
bc5ca1ab59
removed sort by hist-blur
2018-12-20 12:57:16 +04:00
9926dc626a
refactorings, improved sort by hist-dissim
2018-12-20 12:43:00 +04:00
4ff67ad26b
fix --aligned-dir arg
2018-12-20 04:14:42 +04:00
26571eff6a
added sort -by black . Places images which contains black area at end of folder. Useful to get rid of src faces which cutted by screen.
2018-12-18 18:08:04 +04:00
db142bcc02
increased speed of 'sort by hist-dissim' by running in parallel
2018-12-18 17:51:54 +04:00
43da6f84d6
improved sort by blur. Now it's better than laplacian, and multiprocessed.
2018-12-18 16:51:36 +04:00
98ee1bb339
Added option hist-match threshold, used for decrease artifacts of hist-match.
...
Fix terminating converter thread in debug mode.
Added DeepFaceLab converter overview to readme.
2018-12-14 10:40:46 +04:00
1bd3a8e0c1
fix error on small mask region size in converter,
...
error catching on convert face
2018-12-12 20:48:30 +04:00
b52793218e
fix
2018-12-08 10:44:46 +04:00
d11637ec55
limiting max convert subprocessors to 6
2018-12-08 10:12:41 +04:00
iperov