The tensorflow code of the paper"Dual-Graph Convolutional Network Based on Band Attention and Sparse Constraint for Hyperspectral Band Selection" Users can directly run main.py to train the BSD-GCN on Indian Pines. If users hope to handle with new datasets, please switch to pre_data\sample_cuda, input "python setup.py install" in terminal and uncomment the "Get_graph_file(data_set)" in line 10 of utils. It is used to build the graph on HSI dataset. The new dataset and labels should be put in data/ori_data.
forked from xidian-yzw/BSD-GCN
-
Notifications
You must be signed in to change notification settings - Fork 0
GNN2QSU/BSD-GCN
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
The tensorflow code of the paper"Dual-Graph Convolutional Network Based on Band Attention and Sparse Constraint for Hyperspectral Band Selection"
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published
Languages
- Python 85.1%
- Cuda 8.6%
- C++ 5.0%
- C 1.3%