Skip to content

Place Recognition library based on Python and PyTorch framework

License

Notifications You must be signed in to change notification settings

EgorProkopov/open_place_recognition

 
 

Repository files navigation

Open Place Recognition library

Installation

Pre-requisites

  • The library requires PyTorch~=1.13 and MinkowskiEngine library to be installed manually. See PyTorch website and MinkowskiEngine repository for the detailed instructions.

  • Another option is to use the suggested Dockerfile. The following commands should be used to build, start and enter the container:

    1. Build the image

      bash docker/build.sh
    2. Start the container with the datasets directory mounted:

      bash docker/start.sh [DATASETS_DIR]
    3. Enter the container (if needed):

      bash docker/into.sh

Library installation

  • After the pre-requisites are met, install the Open Place Recognition library with the following command:

    pip install .

Usage

Currently only MinkLoc++ pretrained on Oxford RobotCar available. You can download it using google drive link (the link is subject to change).

If everything is installed correctly, you can use the library like below:

from opr.models import minkloc_multimodal

baseline_model = minkloc_multimodal(weights="path_to_checkpoint")

License

MIT License (the license is subject to change in future versions)

About

Place Recognition library based on Python and PyTorch framework

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 98.2%
  • Shell 1.8%