ucalyptus/bs-nets-implementation-pytorch

BS-Nets: An End-to-End Framework For Band Selection of Hyperspectral Image

bs-nets-implementation-pytorch's Issues

Refactoring ipynb

http://ucalyptus.github.io/Hacktoberfest2019 for more issues.

Test

Is your feature request related to a problem? Please describe.
A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]

Describe the solution you'd like
A clear and concise description of what you want to happen.

Describe alternatives you've considered
A clear and concise description of any alternative solutions or features you've considered.

Additional context
Add any other context or screenshots about the feature request here.

TODO: Push Dual Attention to different branch

TODO

Band selection rules

Is your feature request related to a problem? Please describe.
A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]

Describe the solution you'd like
A clear and concise description of what you want to happen.

Describe alternatives you've considered
A clear and concise description of any alternative solutions or features you've considered.

Additional context

First of all, thank you for the code. However, I found that the information entropy of each channel of the model output tensor was used when selecting the band in your code. In the original paper, “According to the learned sparse band weights, we can determine the informative bands by averaging the band weights for all the training samples. Those bands that have larger average weights are considered to be significant since they make more contributions to the reconstruction.”That means the weight of each channel output by the channel attention module is used ,this is different from the method you use，is there any reason for you to do this,please?

Is there any tips on running this demo? It seems a little bit mess on code. Could you kindly give the .py file for reference