P4NSU: Projection-based Pretraining for Nonlinear Sparse Unmixing in Spectral Imaging

🔨 Installation

1. Install Anaconda or Miniconda

2. Install Git

3. Open commond line, create environment and enter with the following commands:

    conda create -n P4NSU python=3.8
    conda activate P4NSU
   

4. Clone the repository and enter:

    git clone https://github.com/Ryan21wy/P4NSU.git
    cd P4NSU
   

5. Install dependency with the following commands:

    pip install -r requirements.txt --extra-index-url https://download.pytorch.org/whl/cu116
   

🎨 Datasets

All datasets are available in Hugging Face. You can download the datasets directly from the website, or use the following Python code to download them automatically:

!pip install huggingface_hub -q

from huggingface_hub import snapshot_download

# Download dataset to a local folder called 'P4NSU'
snapshot_download(repo_id="RyanWy/P4NSU", 
                  repo_type="dataset", 
                  local_dir="./P4NSU")

To learn how to pretrain and finetune your own models, some samples are available at Google Colab demo.

🧑‍💻 Contact

Wang Yue
E-mail: ryanwy@csu.edu.cn