Commit graph

9 commits

Author SHA1 Message Date
iperov
35877dbfd7 AMP, SAEHD: added option use_fp16: Increases training/inference speed, reduces model size. Model may crash. Enable it after 1-5k iters.
AMP: removed lr_dropout, now it is enabled by default;
2021-07-14 23:03:54 +04:00
iperov
ee1bc83a14 AMP, SAEHD: reverted GAN to december version. 2021-07-07 21:45:43 +04:00
iperov
11add4cd4f update GAN model 2021-01-03 19:25:39 +04:00
iperov
54fc3162ed new gan 2021-01-03 01:08:20 +04:00
iperov
ad5733c5bb upd PatchDiscriminator 2020-12-31 17:38:41 +04:00
iperov
ae9e16b4a5 SAEHD: new GAN 2020-12-30 14:33:14 +04:00
Colombo
e8b04053e4 SAEHD:
Changed help for “Learning rate dropout” option:

When the face is trained enough, you can enable this option to get extra sharpness and reduce subpixel shake for less amount of iterations.

Enabled it before “disable random warp” and before GAN. n disabled. y enabled

cpu enabled on CPU. This allows not to use extra VRAM, sacrificing 20% time of iteration.

 Changed help for GAN option:

Train the network in Generative Adversarial manner.

Forces the neural network to learn small details of the face.

Enable it only when the face is trained enough and don't disable.

Typical value is 0.1

improved GAN. Now it produces better skin detail, less patterned aggressive artifacts, works faster.
https://i.imgur.com/Nbh3mw1.png
2020-07-16 22:19:17 +04:00
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
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