GAN-based-Visible-Thermal-Person-ReID

GAN based Image to Image translation model to disentangle identity specific and identity independent components from both Visible and Thermal images. Repository is based on DG-Net implementation.

This project was done as a part of Deep Learning for Computer Vision Course (DLCV): DS-265 at Indian Institute of Science (IISc)

We proposed a Structure based encoder to encode structural information from Visible and Thermal Images. For more details about the project work, please refer to the Project report

Datasets

• SYSU-MM01
• RegDB (Dataset can be downloaded from this website by submitting a copyright form.)

Training

1. Setup the yaml file. Check out configs/latest.yaml. Change the data_root field to the path of your prepared folder-based dataset, e.g. ../Market-1501/pytorch.

2. Start training

python train.py --config configs/latest.yaml

Or train with low precision (fp16)

python train.py --config configs/latest-fp16.yaml

Intermediate image outputs and model binary files are saved in outputs/latest.

3. Check the loss log

 tensorboard --logdir logs/latest

For more details on Training and Testing procedures, please refer to the DG-Net implementation.