All the codes are tested in the following environment:
- Linux (tested on Ubuntu 20.04/22.04)
- Python 3.9+
- PyTorch <= 1.10 (Deprecation of THC.h in PyTorch >=1.11.*)
- CUDA >= 10.0
spconv v2.x
a. Clone this repository.
git clone [email protected]:ut-amrl/coda-models.gitb. Install the dependent libraries as follows
conda env create -f environment.yml
If the above command fails, you can also run the following commands in order:
ROS support (optional)
conda install mamba -c conda-forge
conda config --env --add channels conda-forge
conda config --env --add channels robostack-staging
conda config --env --remove channels defaults
conda install ros-noetic-desktop
Model Inference (mandatory)
conda install -c "nvidia/label/cuda-11.3.1" cuda
conda install -c conda-forge cudatoolkit-dev==11.3.1
conda install pytorch==1.10.0 torchvision==0.11.0 torchaudio==0.10.0 cudatoolkit=11.3 -c pytorch -c conda-forge
pip install spconv-cu113
pip install -r requirements.txt
c. Install this repository
python setup.py develop
Verify your installation by following any of the tutorials in the Getting Started section.