72ba6b103c
added Intel's plaidML backend to use OpenCL engine. Check new requirements. smart choosing of backend in device.py env var 'force_plaidML' can be choosed to forced using plaidML all tf functions transferred to pure keras MTCNN transferred to pure keras, but it works slow on plaidML (forced to CPU in this case) default batch size for all models and VRAMs now 4, feel free to adjust it on your own SAE: default style options now ZERO, because there are no best values for all scenes, set them on your own. SAE: return back option pixel_loss, feel free to enable it on your own. SAE: added option multiscale_decoder default is true, but you can disable it to get 100% same as H,DF,LIAEF model behaviour. fix converter output to .png added linux fork reference to doc/doc_build_and_repository_info.md
1 KiB
Build and Repository Info
DeepFaceLab officially supports Windows-only. If you want to support Mac/Linux/Docker - create a fork, it will be referenced here.
Linux fork by @lbfs
Installing dlib on Windows
The version of dlib in pip is compiled without CUDA support. Therefore you have to compile it manually in order to use the dlib face extractor.
Command line example for Windows: python setup.py install -G "Visual Studio 14 2015" --yes DLIB_USE_CUDA
CPU mode
It is possible to run from script for all stages using the --cpu-only flag. To run from script, install the separate dependencies for CPU mode using pip -r requirements-cpu.txt.
Please note that extraction and training will take much long without a GPU and performance will greatly suffer without one. In particular, do not use DLIB extractor in CPU mode, it's too slow to run without a GPU. Train only on 64px resolution models like H64 or SAE (with low settings) and the lightweight encoder.