Skip to content

PyTorch实现高分遥感语义分割(地物分类);2019年遥感图像稀疏表征智能分析竞赛-语义分割赛道

Notifications You must be signed in to change notification settings

zhangyhcumt/High-Resolution-Remote-Sensing-Semantic-Segmentation-PyTorch

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

33 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

High-Resolution-Remote-Sensing-Semantic-Segmentation-PyTorch

待完善……感谢关注,Star or Fork

TODO:

  • 完善网络模型(将支持:DeepLabV3, FPN, SegNet, UNet, PSPNet)
  • 完善(膨胀)预测代码
  • 加入后处理方法
  • 引入半监督方法:伪标签
  • 增加数据增强方法:MixUp、Crop_and_Patch
  • 改善代码结构
  • 加入tensorboardX可视化输出
  • 类别不均衡解决办法:focal loss
  • 引入辅助loss:边缘损失、KL散度、向量场损失
  • 总结训练步骤、技巧
  • 分享预训练模型

数据分享

Reference

https://github.com/kazuto1011/deeplab-pytorch
https://github.com/fregu856/deeplabv3

Contact

author: hk
qq:3025531252
email: 3025531252@qq.com

About

PyTorch实现高分遥感语义分割(地物分类);2019年遥感图像稀疏表征智能分析竞赛-语义分割赛道

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%