{"id":18614298,"url":"https://github.com/minar09/pgn_tf","last_synced_at":"2025-07-27T03:11:08.864Z","repository":{"id":53091981,"uuid":"250517315","full_name":"minar09/PGN_tf","owner":"minar09","description":"Part Grouping Network (PGN) implementation in TensorFlow, for custom parsing dataset","archived":false,"fork":false,"pushed_at":"2020-09-17T11:42:11.000Z","size":386,"stargazers_count":11,"open_issues_count":3,"forks_count":6,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-04-11T11:01:29.084Z","etag":null,"topics":["cihp","custom-dataset","human-parsing","human-segmentation","inference","parsing","pgn","segmentation","tensorflow","tensorflow-gpu","testing","tf"],"latest_commit_sha":null,"homepage":"https://github.com/Engineering-Course/CIHP_PGN","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/minar09.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2020-03-27T11:31:00.000Z","updated_at":"2024-05-31T16:34:38.000Z","dependencies_parsed_at":"2022-09-13T15:02:44.632Z","dependency_job_id":null,"html_url":"https://github.com/minar09/PGN_tf","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/minar09/PGN_tf","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/minar09%2FPGN_tf","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/minar09%2FPGN_tf/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/minar09%2FPGN_tf/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/minar09%2FPGN_tf/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/minar09","download_url":"https://codeload.github.com/minar09/PGN_tf/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/minar09%2FPGN_tf/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":267293886,"owners_count":24065333,"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","status":"online","status_checked_at":"2025-07-27T02:00:11.917Z","response_time":82,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["cihp","custom-dataset","human-parsing","human-segmentation","inference","parsing","pgn","segmentation","tensorflow","tensorflow-gpu","testing","tf"],"created_at":"2024-11-07T03:25:53.398Z","updated_at":"2025-07-27T03:11:08.822Z","avatar_url":"https://github.com/minar09.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"## Disclaimer\nThis is a slightly modified version of original [CIHP-PGN](https://github.com/Engineering-Course/CIHP_PGN) github repository, for testing with custom parsing datasets with visualization. Please refer to the original repository for details.\n\n## Part Grouping Network (PGN)\nKe Gong, Xiaodan Liang, Yicheng Li, Yimin Chen, Ming Yang and Liang Lin, \"Instance-level Human Parsing via Part Grouping Network\", ECCV 2018 (Oral).\n\n### Introduction\n\nPGN is a state-of-art deep learning methord for semantic part segmentation, instance-aware edge detection and instance-level human parsing built on top of [Tensorflow](http://www.tensorflow.org).\n\nThis distribution provides a publicly available implementation for the key model ingredients reported in our latest [paper](http://openaccess.thecvf.com/content_ECCV_2018/papers/Ke_Gong_Instance-level_Human_Parsing_ECCV_2018_paper.pdf) which is accepted by ECCV 2018.\n\n\n### Crowd Instance-level Human Parsing (CIHP) Dataset\n\nThe PGN is trained and evaluated on our [CIHP dataset](http://www.sysu-hcp.net/lip) for isntance-level human parsing.  Please check it for more model details. The dataset is also available at [google drive](https://drive.google.com/drive/folders/0BzvH3bSnp3E9ZW9paE9kdkJtM3M?usp=sharing) and [baidu drive](http://pan.baidu.com/s/1nvqmZBN).\n\n### Pre-trained models\n\nWe have released our trained models of PGN on CIHP dataset at [google drive](https://drive.google.com/open?id=1Mqpse5Gen4V4403wFEpv3w3JAsWw2uhk).\n\n## Installation\nRun `pip install -r requirements.txt` with python 3.6 and pip installed.\n\n### Inference\n1. Download the pre-trained model and store in $HOME/checkpoint.\n2. Prepare the images and store in $HOME/datasets.\n3. Run test_pgn.py.\n4. The results are saved in $HOME/output\n5. Evaluation scripts are in $HOME/evaluation. Copy the groundtruth files (in _Instance_ids_ folder) into $HOME/evaluation/Instance_part_val before you run the script.\n\n### Training\n1. Download the pre-trained model and store in $HOME/checkpoint.\n2. Download CIHP dataset or prepare your own data and store in $HOME/datasets.\n3. For CIHP dataset, you need to generate the edge labels and left-right flipping labels (optional). We have provided a script for reference.\n4. Run train_pgn.py to train PGN.\n5. Use test_pgn.py to generate the results with the trained models.\n6. The instance tool is used for instance partition process from semantic part segmentation maps and instance-aware edge maps, which is written in MATLAB.\n\n## Related work\n+ Self-supervised Structure-sensitive Learning [SSL](https://github.com/Engineering-Course/LIP_SSL), CVPR2017\n+ Joint Body Parsing \u0026 Pose Estimation Network  [JPPNet](https://github.com/Engineering-Course/LIP_JPPNet), T-PAMI2018\n+ Graphonomy: Universal Human Parsing via Graph Transfer Learning [Graphonomy](https://github.com/Gaoyiminggithub/Graphonomy), CVPR2019\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fminar09%2Fpgn_tf","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fminar09%2Fpgn_tf","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fminar09%2Fpgn_tf/lists"}