You can either use a docker container to install the framework or build the environment like in the Installation script provided by openmmlab.
- Have Docker installed on your machine
- cd into docker folder of this repository
- run
docker compose up -d. This should build the image based on the "Dockerfile" and create a container called "openpcdet"
I you intend to install tensorboard please use following commands inside the container:
pip install tensorboard && tensorboard --logdir /app/OpenPCDet/output/custom_models --bind_all- Tensorboard will be available on localhost:6006 on the device where the container is running
To foreward this port of a remote server to your local device use:
ssh -N -L 6006:localhost:6006 <username>@<ip-adress> -i <private key to use or login, noramlly located in ~/.ssh/id_...>
All the codes are tested in the following environment:
- Linux (tested on Ubuntu 14.04/16.04/18.04/20.04/21.04)
- Python 3.6+
- PyTorch 1.1 or higher (tested on PyTorch 1.1, 1,3, 1,5~1.10)
- CUDA 9.0 or higher (PyTorch 1.3+ needs CUDA 9.2+)
spconv v1.0 (commit 8da6f96)orspconv v1.2orspconv v2.x
NOTE: Please re-install pcdet v0.5 by running python setup.py develop even if you have already installed previous version.
a. Clone this repository.
git clone https://github.com/open-mmlab/OpenPCDet.gitb. Install the dependent libraries as follows:
- Install the SparseConv library, we use the implementation from
[spconv].- If you use PyTorch 1.1, then make sure you install the
spconv v1.0with (commit 8da6f96) instead of the latest one. - If you use PyTorch 1.3+, then you need to install the
spconv v1.2. As mentioned by the author ofspconv, you need to use their docker if you use PyTorch 1.4+. - You could also install latest
spconv v2.xwith pip, see the official documents of spconv.
- If you use PyTorch 1.1, then make sure you install the
c. Install this pcdet library and its dependent libraries by running the following command:
python setup.py develop