Efficient operations for fusing semantically annotated RGB-D measurements in a 3D voxel grid in pytorch.
Project description
grid_fusion_pytorch
Efficient operations for fusing semantically annotated RGB-D measurements in a 3D voxel grid in pytorch. Uses TORCH.UTILS.CPP_EXTENSION following the structure of DirectVoxGO.
Setup
- Clone this repository.
git clone https://github.com/JanNogga/grid_fusion_pytorch.git
- Build the docker image.
cd grid_fusion_pytorch/docker && chmod +x build.sh && chmod +x run.sh && ./build.sh
- Run a container.
./run.sh
- In the container, switch to this repository.
cd grid_fusion_pytorch/
- Finally use the custom cuda kernels. The cuda kernel defined in lib/cuda is compiled just-in-time.
python run.py
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
grid_fusion_pytorch-0.1.tar.gz
(28.0 kB
view hashes)
Built Distribution
Close
Hashes for grid_fusion_pytorch-0.1-py3-none-any.whl
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 90567763dd7f738db49aff51756996f0ea679dc0f6c761395b64646f6620163a |
|
| MD5 | 72fabcafb8333fcf9741979362c29389 |
|
| BLAKE2b-256 | 8ca9ad8924419a3d8309237f6b0339d228f063caa3ae071ef5e8aacc80ea21c2 |
