github/DeepFaceLab
1
0
Fork 0
mirror of https://github.com/iperov/DeepFaceLab.git synced 2025-07-05 20:42:11 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions
1317 commits 3 branches 2 tags 866 MiB
Commit graph

164 commits

Author SHA1 Message Date
Colombo
a3a493bb93 _ 2020-03-13 10:44:50 +04:00
Colombo
61472cdaf7 global refactoring and fixes, 
removed support of extracted(aligned) PNG faces. Use old builds to convert from PNG to JPG.

fanseg model file in facelib/ is renamed
 2020-03-13 08:09:00 +04:00
Colombo
d731930537 fixes 2020-03-09 00:18:01 +04:00
Colombo
143792fd31 added fanseg for future WF segmentation model 2020-03-08 00:49:12 +04:00
Colombo
3b6ad4abf9 refactoring 2020-03-07 20:51:54 +04:00
Colombo
d6a685887f fix nick 2020-03-07 19:20:07 +04:00
Colombo
0bac399841 update leras 2020-03-07 16:05:53 +04:00
Colombo
ada60ccefe code refactoring, 
lr_dropout is now disabled in pretraining mode
changed help message for lr_dropout and random_warp
 2020-03-07 13:59:47 +04:00
Colombo
54548afe1a refactoring 2020-03-06 01:21:38 +04:00
Colombo
cd76425db3 update leras 2020-03-04 15:08:10 +04:00
Colombo
884913e35d upd leras 2020-03-02 07:09:39 +04:00
Colombo
757ec77e44 refactoring 2020-03-01 19:09:50 +04:00
Colombo
cbff72f597 _ 2020-02-29 15:53:48 +04:00
Colombo
6d122fd742 _ 2020-02-29 15:50:17 +04:00
Colombo
516e23584e _ 2020-02-29 15:48:31 +04:00
Colombo
803f7f9717 _ 2020-02-29 15:40:11 +04:00
Colombo
b093112f2f _ 2020-02-29 15:39:43 +04:00
Colombo
a21c55cf25 _ 2020-02-29 15:36:37 +04:00
Colombo
f55a65c304 _ 2020-02-29 15:34:27 +04:00
Colombo
55162d6e6c _ 2020-02-29 15:32:36 +04:00
Colombo
27e24d5d28 _ 2020-02-29 15:24:14 +04:00
Colombo
c900c65c31 _ 2020-02-29 15:20:17 +04:00
Colombo
63c0bdbf16 )_ 2020-02-29 15:10:59 +04:00
Colombo
98d3657cbc _ 2020-02-29 15:00:46 +04:00
Colombo
7f609d0f0a fix for linux 2020-02-29 14:49:46 +04:00
Colombo
dbf28eeebf fix for linux 2020-02-29 14:36:10 +04:00
Colombo
5eca4958b7 fix for linux 2020-02-29 14:34:08 +04:00
Colombo
fcbfbdd560 _ 2020-02-29 14:31:21 +04:00
Colombo
7e276a4ec7 _ 2020-02-29 14:12:53 +04:00
Colombo
7180076ecf fix 2020-02-29 13:31:36 +04:00
Colombo
90ae68ae61 fix input_in_time for linux 2020-02-29 11:05:04 +04:00
Colombo
59be114485 upd leras 2020-02-27 16:20:14 +04:00
Colombo
9860a38907 upd SampleGenerator 2020-02-27 09:58:46 +04:00
Colombo
1898bd6881 _ 2020-02-26 23:50:42 +04:00
Colombo
f07bbd5fb0 update leras 2020-02-26 13:32:32 +04:00
Colombo
0324592b67 update leras/layers.py 2020-02-24 22:23:08 +04:00
Colombo
f1d115b63b added experimental face type 'whole_face' 
Basic usage instruction: https://i.imgur.com/w7LkId2.jpg

	'whole_face' requires skill in Adobe After Effects.

	For using whole_face you have to extract whole_face's by using
	4) data_src extract whole_face
	and
	5) data_dst extract whole_face
	Images will be extracted in 512 resolution, so they can be used for regular full_face's and half_face's.

	'whole_face' covers whole area of face include forehead in training square,
	but training mask is still 'full_face'
	therefore it requires manual final masking and composing in Adobe After Effects.

added option 'masked_training'
	This option is available only for 'whole_face' type.
	Default is ON.
	Masked training clips training area to full_face mask,
	thus network will train the faces properly.
	When the face is trained enough, disable this option to train all area of the frame.
	Merge with 'raw-rgb' mode, then use Adobe After Effects to manually mask, tune color, and compose whole face include forehead.
 2020-02-21 16:21:04 +04:00
Colombo
7a790489f2 fix SubprocessorBase.py 2020-02-19 22:09:45 +04:00
Colombo
7a9cd6379f bug fixes 2020-02-19 15:27:22 +04:00
Colombo
6aa585fa33 fix leras 2020-02-19 07:00:29 +04:00
Colombo
9598ba0141 SAEHD: 
added option Eyes priority (y/n)

	fix eye problems during training  ( especially on HD architectures )
	by forcing the neural network to train eyes with higher priority
	before/after https://i.imgur.com/YQHOuSR.jpg

	It does not guarantee the right eye direction.
 2020-02-18 14:30:07 +04:00
Colombo
01376fd17c decreased time of training initialization 2020-02-18 10:01:33 +04:00
Colombo
e0a55ff1c3 update leras 2020-02-17 18:26:19 +04:00
Colombo
b24b1e2950 Merger: fixes and better quality 2020-02-01 04:42:43 +04:00
Colombo
3f813d5611 refactoring 2020-01-31 14:31:26 +04:00
Colombo
80036f950f leras ModelBase.summary() 2020-01-28 21:38:15 +04:00
Colombo
7386a9d6fd optimized face sample generator, CPU load is significantly reduced 
SAEHD:

added new option
GAN power 0.0 .. 10.0
	Train the network in Generative Adversarial manner.
	Forces the neural network to learn small details of the face.
	You can enable/disable this option at any time,
	but better to enable it when the network is trained enough.
	Typical value is 1.0
	GAN power with pretrain mode will not work.

Example of enabling GAN on 81k iters +5k iters
https://i.imgur.com/OdXHLhU.jpg
https://i.imgur.com/CYAJmJx.jpg

dfhd: default Decoder dimensions are now 48
the preview for 256 res is now correctly displayed

fixed model naming/renaming/removing

Improvements for those involved in post-processing in AfterEffects:

Codec is reverted back to x264 in order to properly use in AfterEffects and video players.

Merger now always outputs the mask to workspace\data_dst\merged_mask

removed raw modes except raw-rgb
raw-rgb mode now outputs selected face mask_mode (before square mask)

'export alpha mask' button is replaced by 'show alpha mask'.
You can view the alpha mask without recompute the frames.

8) 'merged *.bat' now also output 'result_mask.' video file.
8) 'merged lossless' now uses x264 lossless codec (before PNG codec)
result_mask video file is always lossless.

Thus you can use result_mask video file as mask layer in the AfterEffects.
 2020-01-28 12:24:45 +04:00
TooMuchFun
9b6bb4cd34 fix io not imported (#580) 2020-01-27 06:56:03 +04:00
Colombo
17337ea8f8 fixed model renaming/deleting 2020-01-26 14:49:37 +04:00
Colombo
c485e1718a fixes 2020-01-26 12:56:21 +04:00