Commit graph

13 commits

Author SHA1 Message Date
Colombo
0c2e1c3944 SAEHD:
Maximum resolution is increased to 640.

‘hd’ archi is removed. ‘hd’ was experimental archi created to remove subpixel shake, but ‘lr_dropout’ and ‘disable random warping’ do that better.

‘uhd’ is renamed to ‘-u’
dfuhd and liaeuhd will be automatically renamed to df-u and liae-u in existing models.

Added new experimental archi (key -d) which doubles the resolution using the same computation cost.
It is mean same configs will be x2 faster, or for example you can set 448 resolution and it will train as 224.
Strongly recommended not to train from scratch and use pretrained models.

New archi naming:
'df' keeps more identity-preserved face.
'liae' can fix overly different face shapes.
'-u' increased likeness of the face.
'-d' (experimental) doubling the resolution using the same computation cost
Examples: df, liae, df-d, df-ud, liae-ud, ...

Improved GAN training (GAN_power option).  It was used for dst model, but actually we don’t need it for dst.
Instead, a second src GAN model with x2 smaller patch size was added, so the overall quality for hi-res models should be higher.

Added option ‘Uniform yaw distribution of samples (y/n)’:
	Helps to fix blurry side faces due to small amount of them in the faceset.

Quick96:
	Now based on df-ud archi and 20% faster.

XSeg trainer:
	Improved sample generator.
Now it randomly adds the background from other samples.
Result is reduced chance of random mask noise on the area outside the face.
Now you can specify ‘batch_size’ in range 2-16.

Reduced size of samples with applied XSeg mask. Thus size of packed samples with applied xseg mask is also reduced.
2020-06-19 09:45:55 +04:00
Colombo
eda6433936 refactoring 2020-03-08 23:19:04 +04:00
Colombo
01376fd17c decreased time of training initialization 2020-02-18 10:01:33 +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
Colombo
38b85108b3 DFL-2.0 initial branch commit 2020-01-21 18:43:39 +04:00
Colombo
21b25038ac optimized sample generator 2020-01-05 11:53:31 +04:00
Colombo
9ed0111824 fix 2019-12-22 19:10:57 +04:00
Colombo
754d6c385c refactorings 2019-12-22 19:00:59 +04:00
Colombo
50f892d57d all models: removed options 'src_scale_mod', and 'sort samples by yaw as target'
If you want, you can manually remove unnecessary angles from src faceset after sort by yaw.

Optimized sample generators (CPU workers). Now they consume less amount of RAM and work faster.

added
4.2.other) data_src/dst util faceset pack.bat
	Packs /aligned/ samples into one /aligned/samples.pak file.
	After that, all faces will be deleted.

4.2.other) data_src/dst util faceset unpack.bat
	unpacks faces from /aligned/samples.pak to /aligned/ dir.
	After that, samples.pak will be deleted.

Packed faceset load and work faster.
2019-12-21 23:16:55 +04:00
Colombo
c04740eac1 1 2019-12-17 09:53:17 +04:00
Colombo
e8673e3fcc nothing interesting 2019-12-11 22:33:23 +04:00
Colombo
77b390c04b 1 2019-11-24 19:51:07 +04:00
Colombo
6b14741160 1 2019-11-21 11:40:55 +04:00