1. Install Pytorch 1.1 with Python 3.5.

2. Clone this repo.

git clone https://github.com/DotWang/ASSMN.git

3. Training and evaluation with trainval.py.

   For example, for Indian Pines dataset, if SeMN and SaMN are all employed:

CUDA_VISIBLE_DEVICES=0 python trainval.py \
	--dataset 'indian' \
	--dr-num 4 --dr-method 'pca' \
	--mi -1 --ma 1 \
	--half-size 13 --rsz 27 \
	--experiment-num 10 \
	--lr 1e-2 --epochs 200 --batch-size 16 \
	--scheme 2 --strategy 's2' \
	--spec-time-steps 2 \
	--group 'alternate' --seq 'cascade' \
	--npi-num 2

    Then the assessment results are recorded in the corresponding *.mat file and the generated model is saved.

4. Predicting with the previous stored model through infer.py

CUDA_VISIBLE_DEVICES=0 python infer.py \
      --dataset 'indian' \
      --mi -1 --ma 1 \
      --half-size 13 --rsz 27 \
      --bz 50000 \
      --scheme 2 --strategy 's2' 

    and then produce the final classification map.

If this repo is useful for your research, please cite our paper.

@ARTICLE{wd_2021_assmn,
  author={D. {Wang} and B. {Du} and L. {Zhang} and Y. {Xu}},
  journal={IEEE Transactions on Geoscience and Remote Sensing}, 
  title={Adaptive Spectral–Spatial Multiscale Contextual Feature Extraction for Hyperspectral Image Classification}, 
  year={2021},
  volume={59},
  number={3},
  pages={2461-2477},
  doi={10.1109/TGRS.2020.2999957}
  }

Thanks Andrea Palazzi for providing the Pytorch implementation of Convolutional LSTM!

[1] Image-level/Patch-free Hyperspectral Image Classification
    Fully Contextual Network for Hyperspectral Scene Parsing, IEEE TGRS, 2021 | Paper | Github
    Di Wang^∗, Bo Du, and Liangpei Zhang

[2] Graph Convolution based Hyperspectral Image Classification
    Spectral-Spatial Global Graph Reasoning for Hyperspectral Image Classification, IEEE TNNLS, 2023 | Paper | Github
    Di Wang^∗, Bo Du, and Liangpei Zhang

[3] Neural Architecture Search for Hyperspectral Image Classification
    HKNAS: Classification of Hyperspectral Imagery Based on Hyper Kernel Neural Architecture Search, IEEE TNNLS, 2023 | Paper | Github
    Di Wang^∗, Bo Du, Liangpei Zhang, and Dacheng Tao

[4] ImageNet Pretraining and Transformer based Hyperspectral Image Classification
    DCN-T: Dual Context Network with Transformer for Hyperspectral Image Classification, IEEE TIP, 2023 | Paper | Github
    Di Wang^∗, Jing Zhang, Bo Du, Liangpei Zhang, and Dacheng Tao