This is the implementation of article: "Multi-stage convolutional autoencoder network for hyperspectral unmixing".

Citation

If you find our work useful in your research or publication, please cite:

Yu Y, Ma Y, Mei X, et al. Multi-stage convolutional autoencoder network for hyperspectral unmixing[J]. International Journal of Applied Earth Observation and Geoinformation, 2022, 113: 102981.

Usage

Run MSNet_samson.py

If you want to run the code in your own data, you can accordingly change the input and change the parameters.

The format of input:

A represents the ground truth of abundance.

M represents the ground truth of endmembers.

M1 represents the initialization of endmembers by VCA.

Y represents the HSI.