System/Hardware Requirements

To get started, the following requirements should be fulfilled.

  • System requirements. OpenCOOD is tested under Ubuntu 18.04

  • Adequate GPU. A minimum of 6GB gpu is recommended.

  • Disk Space. Estimate 100GB of space is recommended for data downoading.

  • Python Python3.7 is required.


1. Dependency Installation

First, download OpenCOOD github to your local folder if you haven’t done it yet.

git clone
cd OpenCOOD

Next we create a conda environment and install the requirements.

conda env create -f environment.yml
conda activate opencood
python develop

If conda install failed, install through pip

pip install -r requirements.txt

2. Pytorch Installation (>=1.8, tested on 1.8-1.12.0)

Go to to install pytorch cuda version.

3. Spconv (1.2.1 or 2.x)

OpenCOOD support both spconv 1.2.1 and 2.x to generate voxel features.

To install spconv 1.2.1, please follow the guide in

To install spconv 2.x, please run the following commands (if you are using cuda 11.3):

pip install spconv-cu113

Tips for installing spconv 1.2.1:

  1. make sure your cmake version >= 3.13.2

  2. CUDNN and CUDA runtime library (use nvcc --version to check) needs to be installed on your machine.

4. Bbx IOU cuda version compile

Install bbx nms calculation cuda version

python opencood/utils/ build_ext --inplace

5. Dependencies for FPV-RCNN (optional)

Install the dependencies for fpv-rcnn.

python opencood/pcdet_utils/ build_ext --inplace