@@ -23,38 +23,46 @@ Zachary Teed and Jia Deng, CVPR 2021
## Installation
### Requirements:
* Cuda >= 10.1 (with nvcc compiler)
* PyTorch >= 1.8
### Installing (from source):
We recommend installing within a virtual enviornment. Make sure you clone using the `--recursive` flag. If you are using Anaconda, the following command can be used to install all dependencies
```
Requires torch >= 2 and CUDA >= 11. Tested up to torch==2.7 and CUDA 12. Make sure PyTorch and CUDA major versions match.
To run the examples, you will need OpenCV and Open3D. Depending on your operating system, OpenCV and Open3D can either be installed with pip or may need to be built from source
```
pip install opencv-python open3d
# install requirements
pip install torch torchvision torchaudio wheel
# optional: specify GPU architectures
export TORCH_CUDA_ARCH_LIST="7.5;8.6;8.9;9.0"
# install lietorch
pip install--no-build-isolation .
```
### Installing (from source)
### Installing (with pip)
```bash
# optional: specify GPU architectures
export TORCH_CUDA_ARCH_LIST="7.5;8.6;8.9;9.0"
Clone the repo using the `--recursive` flag and install using `setup.py` (may take up to 10 minutes)