{"id":13627664,"url":"https://github.com/TuSimple/rl-multishot-reid","last_synced_at":"2025-04-17T00:32:16.585Z","repository":{"id":68971781,"uuid":"114955385","full_name":"TuSimple/rl-multishot-reid","owner":"TuSimple","description":"Multi-shot Pedestrian Re-identification via Sequential Decision Making (CVPR2018)","archived":false,"fork":false,"pushed_at":"2017-12-21T02:58:35.000Z","size":53,"stargazers_count":93,"open_issues_count":5,"forks_count":26,"subscribers_count":15,"default_branch":"master","last_synced_at":"2025-04-06T02:51:12.949Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","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/TuSimple.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,"governance":null,"roadmap":null,"authors":null}},"created_at":"2017-12-21T02:57:36.000Z","updated_at":"2024-01-11T07:33:42.000Z","dependencies_parsed_at":"2024-01-14T08:06:29.132Z","dependency_job_id":null,"html_url":"https://github.com/TuSimple/rl-multishot-reid","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/TuSimple%2Frl-multishot-reid","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TuSimple%2Frl-multishot-reid/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TuSimple%2Frl-multishot-reid/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TuSimple%2Frl-multishot-reid/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/TuSimple","download_url":"https://codeload.github.com/TuSimple/rl-multishot-reid/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":249293024,"owners_count":21245670,"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":"2024-08-01T22:00:36.985Z","updated_at":"2025-04-17T00:32:16.335Z","avatar_url":"https://github.com/TuSimple.png","language":"Python","funding_links":[],"categories":["\u003ca name=\"Vision\"\u003e\u003c/a\u003e2. Vision"],"sub_categories":["2.6 ReID"],"readme":"* [Multi-shot Re-identification](#1)\n* [Preparations](#1.1)\n* [Usage](#1.2)\n\n\u003ch3 id=\"1\"\u003eMulti-shot Re-identification Based on Reinforcement Learning\u003c/h3\u003e\n\n---\n\nTraining and testing codes for multi-shot Re-Identification. Currently, these codes are tested on the PRID-2011 dataset, iLiDS-VID dataset and MARS dataset. For algorithm details and experiment results, please refer our paper: [Multi-shot Pedestrian Re-identification via Sequential Decision Making](https://arxiv.org/abs/1712.07257)\n\n\u003ch3 id=\"1.1\"\u003ePreparations\u003c/h3\u003e\n\n---\n\nBefore starting running this code, you should make the following preparations:\n\n* Download the [MARS](http://www.liangzheng.com.cn/Project/project_mars.html)\n, [iLIDS-VID](http://www.eecs.qmul.ac.uk/~xiatian/downloads_qmul_iLIDS-VID_ReID_dataset.html) and [PRID-2011](https://www.tugraz.at/institute/icg/research/team-bischof/lrs/downloads/PRID11/).\n* Install MXNet following the [instructions](http://mxnet.io/get_started/index.html#setup-and-installation) and install the python interface. Currently the repo is tested on commit e06c55.\n\n\u003ch3 id=\"1.2\"\u003eUsage\u003c/h3\u003e\n\n---\n\n* Download the datasets and unzip.\n* Prepare data file. Generate image list file according to the file `preprocess_ilds_image.py`\n, `preprocess_prid_image.py` and `preprocess_mars_image.py` under `baseline` folder.\n* The code is split to two stage, the first stage is a image based re-id task,\nplease refer the script `run.sh` in `baseline` folder. The codes for this stage is based on [this repo](https://github.com/TuSimple/re-identification). The usage is:\n```shell\nsh run.sh $gpu $dataset $network $recfloder\n```\ne.g. If you want to train MARS dataset on gpu 0 using inception-bn, please run:\n```shell\nsh run.sh 0 MARS inception-bn /data3/matt/MARS/recs\n```\n* The second stage is a multi-shot re-id task based on reinforcement learning.\nPlease refer the script `run.sh` in `RL` folder. The usage is:\n```shell\nsh run.sh $gpu $unsure-penalty $dataset $network $recfloder\n```\n* For evaluation, please use `baseline/baseline_test.py` and `RL/find_eg.py`. In `RL/find_eg.py`, we also show some example episodes with good quality generated by our algorithm.\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FTuSimple%2Frl-multishot-reid","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FTuSimple%2Frl-multishot-reid","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FTuSimple%2Frl-multishot-reid/lists"}