iperov 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
..
Model_DF	SAE: new options face_style_power, bg_style_power instead of style_power. Zero - means dont use style.	2019-01-10 18:28:12 +04:00
Model_H64	now you can train models on multiple GPU's on same workspace without cloning any folders.	2019-01-14 10:48:23 +04:00
Model_H128	now you can train models on multiple GPU's on same workspace without cloning any folders.	2019-01-14 10:48:23 +04:00
Model_LIAEF128	SAE: new options face_style_power, bg_style_power instead of style_power. Zero - means dont use style.	2019-01-10 18:28:12 +04:00
Model_SAE	SAE: 'adaptive kernel size' now as an option	2019-01-13 10:03:01 +04:00
__init__.py	refactoring	2018-12-24 13:45:40 +04:00
archived_models.zip	now you can train models on multiple GPU's on same workspace without cloning any folders.	2019-01-14 10:48:23 +04:00
ConverterBase.py	added new model U-net Face Morpher.	2019-01-02 17:26:12 +04:00
ConverterImage.py	added new model U-net Face Morpher.	2019-01-02 17:26:12 +04:00
ConverterMasked.py	Fix bug in ConverterMasked when overexposed pixels appear sometimes	2019-01-09 13:57:26 +04:00
ModelBase.py	now you can train models on multiple GPU's on same workspace without cloning any folders.	2019-01-14 10:48:23 +04:00