Skip to content

A simple Spatial Pyramid Pooling layer which could be added in CNN

License

Notifications You must be signed in to change notification settings

yifanjiang19/sppnet-pytorch

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

sppnet-pytorch

SPP layer could be added in CNN model between convolutional layer and fully-connected lay, so that you can input multi-size images into your CNN model. We use this structure in the paper Pedestrian-Synthesis-GAN: Generating Pedestrian Data in Real Scene and Beyond

The function spatial_pyramid_pool() in file spp_layer.py is independent. It could be added in your own models.

See this:Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition

Citation

If you find this work useful for your research, please cite:

@article{ouyang2018pedestrian,
  title={Pedestrian-Synthesis-GAN: Generating Pedestrian Data in Real Scene and Beyond},
  author={Ouyang, Xi and Cheng, Yu and Jiang, Yifan and Li, Chun-Liang and Zhou, Pan},
  journal={arXiv preprint arXiv:1804.02047},
  year={2018}
}

and

@inproceedings{he2014spatial,
  title={Spatial pyramid pooling in deep convolutional networks for visual recognition},
  author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
  booktitle={European conference on computer vision},
  pages={346--361},
  year={2014},
  organization={Springer}
}

Releases

No releases published

Packages

No packages published

Languages