Ten Deepfake

VRAM consumption gone trough the roof with BN. Unable to train at 400+ res and reasonable batch size on 24gb vram

I tried DF model 416 res at batch 4 was OOM where I can normally run heavier LIAE model 416 at batch 10 no issues. like u mentioned problem may...

reusing model - freezing encoder/decoder letting interAB train, then unfreeze ?

conda create -n deepfacelab -c main python=3.7 cudnn=7.6.5 cudatoolkit=10.1.243 replace requirements_cuda.txt with this tqdm numpy numexpr h5py==3.1.0 opencv-python==4.1.0.25 ffmpeg-python==0.1.17 scikit-image==0.14.2 scipy==1.4.1 colorama tensorflow-gpu==2.4.0 pyqt5 tf2onnx==1.9.3 ffmpeg python -m pip install...

BEST WAY: 1. Install Lambda Stack: LAMBDA_REPO=$(mktemp) && \ wget -O${LAMBDA_REPO} https://lambdalabs.com/static/misc/lambda-stack-repo.deb && \ sudo dpkg -i ${LAMBDA_REPO} && rm -f ${LAMBDA_REPO} && \ sudo apt-get update && sudo apt-get...