SGNet: A Python repository from yyyyy1231

Spatial information guided Convolution for Real-Time RGBD Semantic Segmentation

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.

Prerequisites

Environments

PyTorch == 0.4.1
tqdm
CUDA==8.0
CUDNN=7.1.4
pillow
numpy
tensorboardX
tqdm

Trained model and dataset

Download NYUDv2 dataset and trained model:

	Dataset	model	model
OneDrive	NYUDv2	SGNet	SGNet_ASPP
BaiduDrive(passwd: scon)	NYUDv2	SGNet	SGNet_ASPP

Usage

Put the pretrained model into pretrained_weights folder and unzip the dataset into dataset 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

Citation

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}
}

Contact

If you have any questions, feel free to contact me via linzhuochen🥳foxmail😲com

yyyyy1231/SGNet