iperov 5c43f4245e transfercolor via lab converter now implemented by tensorflow-cpu, which is x2 faster than skimage. ...

We cannot use GPU for lab converter in converter multiprocesses, because almost all VRAM ate by model process, so even 300Mb free VRAM not enough for tensorflow lab converter.
Removed skimage dependency.
Refactorings.

2018-12-01 12:11:54 +04:00

..

Model_AVATAR

fix avatar multigpu mode

2018-06-07 12:18:42 +04:00

Model_DF

min vram -0.5gb for all models

2018-06-05 16:23:43 +04:00

Model_H64

increased H64 decoder size for 4GB+

2018-06-07 10:06:24 +04:00

Model_H128

increased speed of train on H64, H128 models.

2018-06-06 18:40:36 +04:00

Model_LIAEF128

min vram -0.5gb for all models

2018-06-05 16:23:43 +04:00

Model_LIAEF128YAW

min vram -0.5gb for all models

2018-06-05 16:23:43 +04:00

Model_MIAEF128

min vram -0.5gb for all models

2018-06-05 16:23:43 +04:00

__init__.py

initial

2018-06-04 17:12:43 +04:00

BaseTypes.py

initial

2018-06-04 17:12:43 +04:00

ConverterBase.py

initial

2018-06-04 17:12:43 +04:00

ConverterImage.py

initial

2018-06-04 17:12:43 +04:00

ConverterMasked.py

transfercolor via lab converter now implemented by tensorflow-cpu, which is x2 faster than skimage.

2018-12-01 12:11:54 +04:00

ModelBase.py

transfercolor via lab converter now implemented by tensorflow-cpu, which is x2 faster than skimage.

2018-12-01 12:11:54 +04:00

TrainingDataGenerator.py

initial

2018-06-04 17:12:43 +04:00

TrainingDataGeneratorBase.py

initial

2018-06-04 17:12:43 +04:00