{"id":13422311,"url":"https://github.com/CHENGY12/DMML","last_synced_at":"2025-03-15T12:30:39.344Z","repository":{"id":36085203,"uuid":"198652594","full_name":"CHENGY12/DMML","owner":"CHENGY12","description":"code for ICCV19 paper \"Deep Meta Metric Learning\"","archived":false,"fork":false,"pushed_at":"2024-07-25T10:12:44.000Z","size":38,"stargazers_count":109,"open_issues_count":2,"forks_count":18,"subscribers_count":3,"default_branch":"master","last_synced_at":"2024-10-27T23:57:51.378Z","etag":null,"topics":["baseline","meta-learning","metric-learning","person-reidentification","pytorch","resnet-50","vehicle-reidentification"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/CHENGY12.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2019-07-24T14:32:27.000Z","updated_at":"2024-09-27T08:52:32.000Z","dependencies_parsed_at":"2022-09-16T20:13:08.786Z","dependency_job_id":null,"html_url":"https://github.com/CHENGY12/DMML","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/CHENGY12%2FDMML","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CHENGY12%2FDMML/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CHENGY12%2FDMML/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CHENGY12%2FDMML/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CHENGY12","download_url":"https://codeload.github.com/CHENGY12/DMML/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243730929,"owners_count":20338739,"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":["baseline","meta-learning","metric-learning","person-reidentification","pytorch","resnet-50","vehicle-reidentification"],"created_at":"2024-07-30T23:00:41.432Z","updated_at":"2025-03-15T12:30:39.021Z","avatar_url":"https://github.com/CHENGY12.png","language":"Python","funding_links":[],"categories":["Deep Meta Metric Learning. ICCV 2019"],"sub_categories":["[few-shot 知乎](https://zhuanlan.zhihu.com/p/58298920)"],"readme":"# Deep Meta Metric Learning (DMML)\nThis repo contains PyTorch code for ICCV19' paper: Deep Meta Metric Learning, including person re-identification experiments on Market-1501 and DukeMTMC-reID datasets.\n\n## Requirements\n- Python 3.6+\n- PyTorch 0.4\n- tensorboardX 1.6\n\nTo install all python packages, please run the following command:\n```\npip install -r requirements.txt\n```\n## Datasets\n### Downloading\n- Market-1501 dataset can be downloaded from [here](http://www.liangzheng.org/Project/project_reid.html).\n- DukeMTMC-reID dataset can be downloaded from [here](http://vision.cs.duke.edu/DukeMTMC/).\n### Preparation\nAfter downloading the datasets above, move them to the `datasets/` folder in the project root directory, and rename dataset folders to 'market1501' and 'duke' respectively. I.e., the `datasets/` folder should be organized as:\n```\n|-- market1501\n    |-- bounding_box_train\n    |-- bounding_box_test\n    |-- ...\n|-- duke\n    |-- bounding_box_train\n    |-- bounding_box_test\n    |-- ...\n```\n\n## Usage\n### Training\nAfter adding dataset directory in `demo.sh`, simply run the following command to train DMML on Market-1501:\n```\nbash demo.sh\n```\nUsage instructions of all training parameters can be found in `config.py`.\n### Evaluation\nTo evaluate the performance of a trained model, run\n```\npython eval.py\n```\nwhich will output Rank-1, Rank-5, Rank-10 and mAP scores.\n\n### Citation\nPlease use the citation provided below if it is useful to your research:\n\nGuangyi Chen, Tianren Zhang, Jiwen Lu, and Jie Zhou, Deep Meta Metric Learning, ICCV, 2019.\n```bash\n@inproceedings{chen2019deep,\n  title={Deep Meta Metric Learning},\n  author={Chen, Guangyi and Zhang, Tianren and Lu, Jiwen and Zhou, Jie},\n  booktitle={ICCV},\n  year={2019}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FCHENGY12%2FDMML","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FCHENGY12%2FDMML","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FCHENGY12%2FDMML/lists"}