S-DMM

This is a code sample for the paper "Deep Metric Learning-Based Feature Embedding for Hyperspectral Image Classification"

Requirements

Python 2.x/3.x

Pytorch 0.4.1

GPU

Run the S-DMM

Please set your parameters in train.py or test.py before runing them.

Training, run: python train.py

Test, run: python test.py

About datasets and checkpoints

The datasets is available in http://www.ehu.eus/ccwintco/index.php?title=Hyperspectral_Remote_Sensing_Scenes

The saving trainTestSplit and checkpoints of our experiments can be download in https://pan.baidu.com/s/1cXrVnLf662wtCW6xX3LWhg

Note

This is the code for the same-scene HSI classification; The code for cross-scene HSI classification is in https://github.com/szubing/ED-DMM-UDA