{"id":18340900,"url":"https://github.com/tinyvision/solider-pedestriandetection","last_synced_at":"2025-04-13T10:05:15.938Z","repository":{"id":150677180,"uuid":"620089947","full_name":"tinyvision/SOLIDER-PedestrianDetection","owner":"tinyvision","description":null,"archived":false,"fork":false,"pushed_at":"2023-04-03T07:41:46.000Z","size":23743,"stargazers_count":10,"open_issues_count":3,"forks_count":1,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-03-27T01:23:51.700Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/tinyvision.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-03-28T02:20:14.000Z","updated_at":"2024-12-17T21:45:00.000Z","dependencies_parsed_at":null,"dependency_job_id":"a5cce99f-fd4e-495e-a1c7-811843d1b966","html_url":"https://github.com/tinyvision/SOLIDER-PedestrianDetection","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tinyvision%2FSOLIDER-PedestrianDetection","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tinyvision%2FSOLIDER-PedestrianDetection/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tinyvision%2FSOLIDER-PedestrianDetection/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tinyvision%2FSOLIDER-PedestrianDetection/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/tinyvision","download_url":"https://codeload.github.com/tinyvision/SOLIDER-PedestrianDetection/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248695438,"owners_count":21146954,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-11-05T20:24:36.629Z","updated_at":"2025-04-13T10:05:15.914Z","avatar_url":"https://github.com/tinyvision.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# SOLIDER on [Pedestrian Detection]\n\n[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/beyond-appearance-a-semantic-controllable/pedestrian-detection-on-citypersons)](https://paperswithcode.com/sota/pedestrian-detection-on-citypersons?p=beyond-appearance-a-semantic-controllable)\n\nThis repo provides details about how to use [SOLIDER](https://github.com/tinyvision/SOLIDER) pretrained representation on pedestrian detection task.\nWe modify the code from [Pedestron](https://github.com/hasanirtiza/Pedestron), and you can refer to the original repo for more details.\n\n## Installation and Datasets\n\nDetails of installation and dataset preparation can be found in [Pedestron](https://github.com/hasanirtiza/Pedestron).\n\n## Prepare Pre-trained Models \nYou can download models from [SOLIDER](https://github.com/tinyvision/SOLIDER), or use [SOLIDER](https://github.com/tinyvision/SOLIDER) to train your own models.\nBefore training, you should use `convert_model_version.py` to convert the pretrained models to the right version.\n\n## Training\n\nTrain with single GPU:\n\n```shell\npython tools/train.py ${CONFIG_FILE}\n```\n\nTrain with multiple GPUs:\n```shell\n./tools/dist_train.sh ${CONFIG_FILE} ${GPU_NUM} [optional arguments]\n```\n\n`CONFIG_FILE` can be found in `configs/solider`.\n\nTest:\n\n```shell\nsh run.sh\n```\n\n## Performance\n\n| Method | Model | CityPersons\u003cbr\u003e(MR-2) |\n| ------ | :---: | :---: |\n| SOLIDER | Swin Tiny | 10.3/40.8 |\n| SOLIDER | Swin Small | 10.0/39.2 |\n| SOLIDER | Swin Base | 9.7/39.4 |\n\n- We use the pretrained models from [SOLIDER](https://github.com/tinyvision/SOLIDER).\n- The semantic weight is set to 1.0 in these experiments.\n\n## Citation\n\nIf you find this code useful for your research, please cite our paper\n\n```\n@inproceedings{chen2023beyond,\n  title={Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks},\n  author={Weihua Chen and Xianzhe Xu and Jian Jia and Hao Luo and Yaohua Wang and Fan Wang and Rong Jin and Xiuyu Sun},\n  booktitle={The IEEE/CVF Conference on Computer Vision and Pattern Recognition},\n  year={2023},\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftinyvision%2Fsolider-pedestriandetection","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftinyvision%2Fsolider-pedestriandetection","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftinyvision%2Fsolider-pedestriandetection/lists"}