This repo provides details about how to use SOLIDER pretrained representation on pedestrian detection task. We modify the code from Pedestron, and you can refer to the original repo for more details.

Details of installation and dataset preparation can be found in Pedestron.

You can download models from SOLIDER, or use SOLIDER to train your own models. Before training, you should use convert_model_version.py to convert the pretrained models to the right version.

Train with single GPU:

python tools/train.py ${CONFIG_FILE}

Train with multiple GPUs:

./tools/dist_train.sh ${CONFIG_FILE} ${GPU_NUM} [optional arguments]

CONFIG_FILE can be found in configs/solider.

Test:

sh run.sh

• We use the pretrained models from SOLIDER.
• The semantic weight is set to 1.0 in these experiments.

If you find this code useful for your research, please cite our paper

@inproceedings{chen2023beyond,
  title={Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks},
  author={Weihua Chen and Xianzhe Xu and Jian Jia and Hao Luo and Yaohua Wang and Fan Wang and Rong Jin and Xiuyu Sun},
  booktitle={The IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year={2023},
}