{"id":13732211,"url":"https://github.com/eldar/pose-tensorflow","last_synced_at":"2025-05-16T14:07:53.644Z","repository":{"id":48093237,"uuid":"84482531","full_name":"eldar/pose-tensorflow","owner":"eldar","description":" Human Pose estimation with TensorFlow framework ","archived":false,"fork":false,"pushed_at":"2019-12-07T23:30:02.000Z","size":1586,"stargazers_count":1141,"open_issues_count":65,"forks_count":383,"subscribers_count":56,"default_branch":"master","last_synced_at":"2025-04-12T11:55:46.878Z","etag":null,"topics":["deep-learning","pose-estimation","tensorflow"],"latest_commit_sha":null,"homepage":null,"language":"C++","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"lgpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/eldar.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":"2017-03-09T19:52:15.000Z","updated_at":"2025-03-16T09:24:58.000Z","dependencies_parsed_at":"2022-08-12T18:30:58.587Z","dependency_job_id":null,"html_url":"https://github.com/eldar/pose-tensorflow","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/eldar%2Fpose-tensorflow","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eldar%2Fpose-tensorflow/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eldar%2Fpose-tensorflow/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/eldar%2Fpose-tensorflow/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/eldar","download_url":"https://codeload.github.com/eldar/pose-tensorflow/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254544146,"owners_count":22088807,"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":["deep-learning","pose-estimation","tensorflow"],"created_at":"2024-08-03T02:01:49.188Z","updated_at":"2025-05-16T14:07:49.149Z","avatar_url":"https://github.com/eldar.png","language":"C++","readme":"# Human Pose Estimation with TensorFlow\n\n![](images/teaser.png)\n\nHere you can find the implementation of the Human Body Pose Estimation algorithm,\npresented in the [DeeperCut](http://arxiv.org/abs/1605.03170) and [ArtTrack](http://arxiv.org/abs/1612.01465) papers:\n\n**Eldar Insafutdinov, Leonid Pishchulin, Bjoern Andres, Mykhaylo Andriluka and Bernt Schiele\nDeeperCut:  A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model.\nIn _European Conference on Computer Vision (ECCV)_, 2016**\n\n**Eldar Insafutdinov, Mykhaylo Andriluka, Leonid Pishchulin, Siyu Tang, Evgeny Levinkov, Bjoern Andres and Bernt Schiele\nArtTrack: Articulated Multi-person Tracking in the Wild.\nIn _Conference on Computer Vision and Pattern Recognition (CVPR)_, 2017**\n\n\u003cp align=\"center\"\u003e\n    \u003ca href=\"https://www.mpi-inf.mpg.de/departments/computer-vision-and-multimodal-computing/\"\u003e\u003cimg width=\"50%\" src=\"images/mpilogo-inf-narrow.png\"\u003e\u003c/a\u003e\n\u003c/p\u003e\n\nFor more information visit http://pose.mpi-inf.mpg.de\n\n## Prerequisites\n\nThe implementation is in Python 3 and TensorFlow. We recommended using `conda` to install the dependencies.\nFirst, create a Python 3.6 environment:\n\n```bash\nconda create -n py36 python=3.6\nconda activate py36\n```\n\nThen, install basic dependencies with conda:\n\n```bash\nconda install numpy scikit-image pillow scipy pyyaml matplotlib cython\n```\n\nInstall TensorFlow and remaining packages with pip:\n```bash\npip install tensorflow-gpu easydict munkres\n```\n\nWhen running training or prediction scripts, please make sure to set the environment variable\n`TF_CUDNN_USE_AUTOTUNE` to 0 (see [this ticket](https://github.com/tensorflow/tensorflow/issues/5048)\nfor explanation).\n\nIf your machine has multiple GPUs, you can select which GPU you want to run on\nby setting the environment variable, eg. `CUDA_VISIBLE_DEVICES=0`.\n\n## Demo code\n\nSingle-Person (if there is only one person in the image)\n\n```\n# Download pre-trained model files\n$ cd models/mpii\n$ ./download_models.sh\n$ cd -\n\n# Run demo of single person pose estimation\n$ TF_CUDNN_USE_AUTOTUNE=0 python3 demo/singleperson.py\n```\n\nMultiple People\n\n```\n# Compile dependencies\n$ ./compile.sh\n\n# Download pre-trained model files\n$ cd models/coco\n$ ./download_models.sh\n$ cd -\n\n# Run demo of multi person pose estimation\n$ TF_CUDNN_USE_AUTOTUNE=0 python3 demo/demo_multiperson.py\n```\n\n## Training models\n\nPlease follow these [instructions](models/README.md)\n\n## Citation\nPlease cite ArtTrack and DeeperCut in your publications if it helps your research:\n\n    @inproceedings{insafutdinov2017cvpr,\n\t    title = {ArtTrack: Articulated Multi-person Tracking in the Wild},\n\t    booktitle = {CVPR'17},\n\t    url = {http://arxiv.org/abs/1612.01465},\n\t    author = {Eldar Insafutdinov and Mykhaylo Andriluka and Leonid Pishchulin and Siyu Tang and Evgeny Levinkov and Bjoern Andres and Bernt Schiele}\n    }\n\n    @article{insafutdinov2016eccv,\n        title = {DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model},\n\t    booktitle = {ECCV'16},\n        url = {http://arxiv.org/abs/1605.03170},\n        author = {Eldar Insafutdinov and Leonid Pishchulin and Bjoern Andres and Mykhaylo Andriluka and Bernt Schiele}\n    }\n\n","funding_links":[],"categories":["Popular implementations","AI"],"sub_categories":["TensorFlow"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Feldar%2Fpose-tensorflow","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Feldar%2Fpose-tensorflow","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Feldar%2Fpose-tensorflow/lists"}