Find a file
Laurent FAINSIN ba68f223e6 🔧 add pyproject.toml
2023-04-24 15:07:34 +02:00
.vscode 🔧 add settings.json vscode config 2023-04-24 11:46:04 +02:00
torchemd 🚚 move code to package 2023-04-24 15:07:12 +02:00
.editorconfig 🔧 add .editorconfig 2023-04-24 11:43:35 +02:00
.gitattributes 🙈 add .gitattribute 2023-04-24 11:42:40 +02:00
.gitignore 🙈 better .gitignore 2023-04-24 11:37:16 +02:00
pyproject.toml 🔧 add pyproject.toml 2023-04-24 15:07:34 +02:00
README.md update 2019-09-10 01:06:14 -07:00

PyTorch Wrapper for Point-cloud Earth-Mover-Distance (EMD)

Dependency

The code has been tested on Ubuntu 16.04, PyTorch 1.1.0, CUDA 9.0.

Usage

First compile using

    python setup.py install

Then, copy the lib file out to the main directory,

    cp build/lib.linux-x86_64-3.6/emd_cuda.cpython-36m-x86_64-linux-gnu.so .

Then, you can use it by simply

    from emd import earth_mover_distance
    d = earth_mover_distance(p1, p2, transpose=False)  # p1: B x N1 x 3, p2: B x N2 x 3

Check test_emd_loss.py for example.

Author

The cuda code is originally written by Haoqiang Fan. The PyTorch wrapper is written by Kaichun Mo. Also, Jiayuan Gu provided helps.

License

MIT