Skip to content
master
Go to file
Code

Latest commit

 

Git stats

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
 
 
 
 
 
 
 
 
 
 

README.md

3DGNN

This is the Caffe implementation of 3D Graph Neural Networks for RGBD Semantic Segmentation:

Setup

Requirement

Required CUDA (7.0) + Ubuntu14.04.

Installation

For installation, please follow the instructions of Caffe and DeepLab v2.

Data Preparation

Please download the data and model through the google drive link: https://drive.google.com/file/d/1AqQA-ipfc80caklR9kyUxunycrZjg7T2/view?usp=sharing

  1. Download the trained model (https://mycuhk-my.sharepoint.com/:u:/g/personal/1155051740_link_cuhk_edu_hk/ETsf3ekhGbxOp1xYKJxv2hQB8I5OCCui86QLvWvK65_5sw?e=KThQe9).
  2. Download the prepared training data (prepared hdf5 data) (https://mycuhk-my.sharepoint.com/:u:/g/personal/1155051740_link_cuhk_edu_hk/EVGJ_xXvtNVCh7spid94AmQB_byhW49i-VH_vqx8oZbrZQ?e=COhKwr).
  3. Download the testing data (https://mycuhk-my.sharepoint.com/:u:/g/personal/1155051740_link_cuhk_edu_hk/EVdjeNQqnINOj359HN8WXDgBsouAqSoZC1lRgkSbPNo2hA?e=e0w2sO).
  4. Download the original provided data (https://mycuhk-my.sharepoint.com/:u:/g/personal/1155051740_link_cuhk_edu_hk/EZuJHYVcULRNkQ3qm34ugIoBg-69Vprq2POiaat4u5ZLXQ?e=QmWXec).

Usage

  1. Clone the repository.

  2. Build Caffe and matcaffe:

    cd caffe_code
    make -j8 && make matcaffe
  3. Inference:

    • Evaluation code is in folder 'matlabscript'.
    • Download trained models and unzip it. Pretrained model is saved in folder "model/nyu_40/".
    cd matlabscript
    run nyu_crop_data_mask_msc.m
    • The result is saved in folder "../result/nyu_40_msc/"
  4. Training:

    • Training data preparation
        cd matlabscript
        run generatedata (setting training = true)
        cd ..
        cd train_data_hdf5_file_generate
        python generate_hdf5
        cd ..

    We have also provided the training data in folder "traindata/"

    • Run caffe training

Citation

If you use our code for research, please cite our paper:

@inproceedings{qi20173d,
  title={3D Graph Neural Networks for RGBD Semantic Segmentation},
  author={Qi, Xiaojuan and Liao, Renjie and Jia, Jiaya and Fidler, Sanja and Urtasun, Raquel},
  booktitle={ICCV},
  year={2017}
}

Question

If you have any question or request about the code and data, please email me at qxj0125@gmail.com . If you need more information for other datasets plesase send email.

License

MIT License

About

No description or website provided.

Topics

Resources

License

Releases

No releases published

Packages

No packages published
You can’t perform that action at this time.