Home

Awesome

SE3Transformer

It is a fork of NVIDIA's SE(3)-Transformer implementation. I made some minor modifications, including


Installation

for CPU only

pip install git+http://github.com/huhlim/SE3Transformer

for CUDA (GPU) usage

  1. Install DGL library with CUDA support
# This is an example with cudatoolkit=11.3.
# Set a proper cudatoolkit version that is compatible with your CUDA drivier and DGL library.
conda install dgl -c dglteam/label/cu113
# or
pip install dgl -f https://data.dgl.ai/wheels/cu113/repo.html
  1. Install this package
pip install git+http://github.com/huhlim/SE3Transformer

Code Snippets


Usage