Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Steps for setting up the environment in new GPU like 4090 #216

Open
epratheeban opened this issue Feb 23, 2024 · 2 comments
Open

Steps for setting up the environment in new GPU like 4090 #216

epratheeban opened this issue Feb 23, 2024 · 2 comments

Comments

@epratheeban
Copy link

PS: This is not an issue. Adding it here as the fellow community dont need spend too much time in setting up the env

Anaconda || Ubuntu 22.04 || Python 3.8 || CUDA 12.1 || Pytorch 2.1.2 || Pytorch3D '0.7.6'

  1. Make sure your system have cuda version is 12.1
  2. Install anaconda

for some reasons installing g++ 7 in ubunutu 22.04 is not supported due to compatability issues . So I used Pytorch3d

then follow these

Please follow the below steps

conda create -n deca python=3.8
conda activate deca
pip install torch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 --index-url https://download.pytorch.org/whl/cu121
git clone https://github.com/facebookresearch/pytorch3d.git
cd pytorch3d && pip install -e .
rm -rf build/ **/*.so
pip install -e .
cd ..
pip install numpy==1.23
pip install scipy>=1.4.1
pip install scikit-image>=0.15
pip install opencv-python>=4.1.1
pip install PyYAML==5.1.1
pip install face-alignment==1.3.4
pip install yacs==0.1.8
pip install ninja
pip install fvcore
pip install chumpy>=0.69 
@mwb3262716541
Copy link

it is useful,thanks for sharing!

@JiangThea
Copy link

very useful,thanks!!!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants