Coder Social home page Coder Social logo

dasgil's Introduction

DASGIL: Domain Adaptation for Semantic and Geometric-aware Image-based Localization

This is our Pytorch implementation for DASGIL (arxiv) by Hanjiang Hu, Zhijian Qiao and Ming Cheng.

Text alternative when image is not available

Prerequisites

  • Linux or macOS
  • Python 3
  • CPU or NVIDIA GPU + CUDA CuDNN

Getting Started

Installation

  • Install requisite Python libraries.
pip install -r requirements.txt
  • Clone this repo:
git clone https://github.com/HanjiangHu/DASGIL.git

Training

KITTI and Virtual KITTI 2 dataset are used to train the model, while Extended CMU-Seasons dataset is used to test. The datasets involved in this paper are well organized HERE. Please uncompress it under the root path. Our pretrained models are found HERE. Please uncompress it under the root path.

  • Training on KITTI and Virtual KITTI Dataset:
python train.py --name DASGIL
  • Fine-tune the pretrained model:
python train.py --name DASGIL --continue_train --which_epoch 200

Testing

  • Testing on the Extended CMU-Seasons Dataset:
python test.py --name DASGIL --which_epoch 200

Results

The test results will be saved to ./output. The txt results should be merged into a single txt file and submitted to the official benchmark website.

Our DASGIL results on Extended CMU-Seasons Dataset could be found on the benchmark website.

Other Details

  • See ./options/train_options.py for training-specific flags, ./options/test_options.py for test-specific flags, and ./options/base_options.py for all common flags.
  • CPU/GPU (default --gpu_ids 0): set--gpu_ids -1 to use CPU mode (NOT recommended); set --gpu_ids 0,1,2 for multi-GPU mode.

If you use this code in your own work, please cite:

H. Hu, M. Cheng, Z. Liu and H. Wang โ€DASGIL: Domain Adaptation for Semantic and Geometric-aware Image-based Localizationโ€,

@misc{hu2020dasgil,
      title={DASGIL: Domain Adaptation for Semantic and Geometric-aware Image-based Localization}, 
      author={Hanjiang Hu and Ming Cheng and Zhe Liu and Hesheng Wang},
      year={2020},
      eprint={2010.00573},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

dasgil's People

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.