Lin-Zhuo Chen, Zheng Lin, Ziqin Wang, Yong-Liang Yang and Ming-Ming Cheng
⭐ Project Home »
The official repo of the TIP 2021 paper `` Spatial information guided Convolution for Real-Time RGBD Semantic Segmentation.
- PyTorch == 0.4.1
- tqdm
- CUDA==8.0
- CUDNN=7.1.4
- pillow
- numpy
- tensorboardX
- tqdm
Download NYUDv2 dataset and trained model:
Dataset | model | model | |
---|---|---|---|
OneDrive | NYUDv2 | SGNet | SGNet_ASPP |
BaiduDrive(passwd: scon) | NYUDv2 | SGNet | SGNet_ASPP |
-
Put the pretrained model into
pretrained_weights
folder and unzip the dataset intodataset
folder. -
To compile the InPlace-ABN and S-Conv operation, please run:
## compile InPlace-ABN cd graphs/ops/libs sh build.sh python build.py ## compile S-Conv cd .. sh make.sh
-
Modify the config in
configs/sgnet_nyud_test.json
(mainly check "trained_model_path"). To test the model with imput size$480 \times 640$ , please run:## SGNet python main.py ./configs/sgnet_nyud_test.json ## SGNet_ASPP python main.py ./configs/sgnet_aspp_nyud_test.json
-
You can run the follow command to test the model inference speed, input the image size such as
$480 \times 640$ :## SGNet python main.py ./configs/sgnet_nyud_fps.json ## SGNet_ASPP python main.py ./configs/sgnet_aspp_nyud_fps.json
If you find this work is useful for your research, please cite our paper:
@ARTICLE{chen2021sconv,
title={Spatial Information Guided Convolution for Real-Time RGBD Semantic Segmentation},
author={Chen, Lin-Zhuo and Lin, Zheng and Wang, Ziqin and Yang, Yong-Liang and Cheng, Ming-Ming},
journal={IEEE Transactions on Image Processing},
year={2021}
}
If you have any questions, feel free to contact me via linzhuochen🥳foxmail😲com