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
a. Clone this repository.
b. 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
- Install the torch-scatter library, we use the the implementation from
[pytorch_scatter].
c. Install this library and its dependent libraries by running the following command:
python setup.py developd. We recommend the users to check the version of numba. We find using numba==0.48.0 can significantly save memory.