- Cuda 11.8.0
- Pytorch 2.0
- Python 3.10
- open3d 0.17.0
conda activate digitaltweens
Create a new conda environment
conda create -n digitaltweens python=3.10
Activate the conda environment
conda activate digitaltweens
conda install -c "nvidia/label/cuda-11.8.0" cuda-toolkit
pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
Check if pytorch is installed
python
In the python environment run:
>>> import torch
>>> torch.cuda.is_available()
true
Install nksr repository
pip install nksr -f https://nksr.s3.ap-northeast-1.amazonaws.com/whl/torch-2.0.0%2Bcu118.html
Install dependencies
pip install torch_scatter open3d python-pycg[full] -f https://pycg.s3.4
ap-northeast-1.amazonaws.com/packages/index.html
conda deactivate
python script_viz_ply.py