This is an unofficial implementation of "Hardness-Aware Deep Metric Learning" (CVPR 2019 Oral) in Pytorch.
cd pytorch-hdml
pip install pipenv
pipenv install
cd data
python cars196_downloader.py
python cars196_converter.py
Execute a training script. When executed, the tensorboard log is saved.
pipenv shell
python train_triplet.py
- Implementation of Npair loss HDML
Official tensorflow implementation https://github.com/wzzheng/HDML