AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |
Back to Blog
14:44:41 MainProcess MainThread gpu_stats _log DEBUG Active GPU Devices: 14:44:41 MainProcess MainThread gpu_stats _log DEBUG GPU Device count: 1 14:44:41 MainProcess MainThread gpu_stats _log DEBUG Apple Silicon Detected. 14:44:41 MainProcess MainThread gpu_stats _log DEBUG Initializing GPUStats I would also be happy to help out by doing some testing.Ĭode: Select all 14:44:41 MainProcess MainThread logger log_setup INFO Log level set to: INFO I have some basic Python experience, but if any developer reads this, perhaps you can point me in the right direction I think I need to find a way to get GPU stats from the M1 chip. Next I want to try and get GPU training working. CPU training works, using all M1 cores.fastcluster doesn't install on amd64, skipped that, so Extract is not working for now. ![]() So Faceswap either needs to be modified to support Tensorflow 2.7 or Python 3.9?.tensorflow-macos 2.5/2.6 installation works using Python 3.9, but we can't use that to run Faceswap.tensorflow-macos 2.5/2.6 don't seem to like Python 3.8, installation fails.Anaconda is not supported, but we can use Miniforge instead. ![]() I followed the instructions from Apple, modified the instructions a bit and documented my working setup here: ![]() After several days of trial and error, I was able to set up a testing environment using: After getting myself a M1 MacBook Pro, I was curious to see if I could make Faceswap work on it.
0 Comments
Read More
Leave a Reply. |