Colombo d781af3d1f fixed GPU detection and indexes, got rid of using nvml, now using direct cuda lib to determine gpu info that match tensorflow indexes, ... removed TrueFace model. added SAEv2 model. Differences from SAE: + default e_ch_dims is now 21 + new encoder produces more stable face and less scale jitter before: https://i.imgur.com/4jUcol8.gifv after: https://i.imgur.com/lyiax49.gifv - scale of the face is less changed within frame size + decoder now has only 1 residual block instead of 2, result is same quality with less decoder size + added mid-full face, which covers 30% more area than half face. + added option " Enable 'true face' training " Enable it only after 50k iters, when the face is sharp enough. the result face will be more like src. The most src-like face with 'true-face-training' you can achieve with DF architecture.		2019-10-05 16:26:23 +04:00
..
__init__.py	initial code to extract umdfaces.io dataset and train pose estimator	2019-04-23 08:14:09 +04:00
Sample.py	SAE : WARNING, RETRAIN IS REQUIRED !	2019-09-19 11:13:56 +04:00
SampleGeneratorBase.py	SAE : WARNING, RETRAIN IS REQUIRED !	2019-09-19 11:13:56 +04:00
SampleGeneratorFace.py	SAE : WARNING, RETRAIN IS REQUIRED !	2019-09-19 11:13:56 +04:00
SampleGeneratorFaceTemporal.py	fixed error "Failed to get convolution algorithm" on some systems	2019-08-11 11:17:22 +04:00
SampleGeneratorImageTemporal.py	fixed error "Failed to get convolution algorithm" on some systems	2019-08-11 11:17:22 +04:00
SampleLoader.py	SAE : WARNING, RETRAIN IS REQUIRED !	2019-09-19 11:13:56 +04:00
SampleProcessor.py	fixed GPU detection and indexes, got rid of using nvml, now using direct cuda lib to determine gpu info that match tensorflow indexes,	2019-10-05 16:26:23 +04:00