MSSC

The code for our paper Improving Pedestrian Attribute Recognition With Multi-Scale Spatial Calibrate.

Dataset Info

PA100K[Paper][Github]

RAP : A Richly Annotated Dataset for Pedestrian Attribute Recognition

• v1.0 [Paper][Project]
• v2.0 [Paper][Project]

Get Started

1. Run git clone https://github.com/iceicei/MSSC.git
2. Create a directory to dowload above datasets.

   cd MSSC
   

3. Prepare datasets to have following structure:

   ${project_dir}/data
       PA100k
           data/
           annotation.mat
           README.txt
       RAP
           RAP_dataset/
           RAP_annotation.mat
           README.txt
       RAP2
           RAP_dataset/
           RAP_annotation.mat
           README.txt
   

4. Run the format_xxxx.py to generate dataset.pkl respectively

   python ./dataset/preprocess/format_pa100k.py
   python ./dataset/preprocess/format_rap.py
   python ./dataset/preprocess/format_rap2.py
   

5. Train MSSC

   python train.py PA100k
   

Citation

If you use this method or this code in your research, please cite as: