{"id":13546218,"url":"https://github.com/mitmul/deeppose","last_synced_at":"2025-04-05T18:08:39.282Z","repository":{"id":23115085,"uuid":"26469569","full_name":"mitmul/deeppose","owner":"mitmul","description":"DeepPose implementation in Chainer","archived":false,"fork":false,"pushed_at":"2019-11-05T13:14:06.000Z","size":140,"stargazers_count":411,"open_issues_count":29,"forks_count":129,"subscribers_count":32,"default_branch":"master","last_synced_at":"2025-03-29T17:10:03.277Z","etag":null,"topics":["chainer"],"latest_commit_sha":null,"homepage":"http://static.googleusercontent.com/media/research.google.com/ja//pubs/archive/42237.pdf","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/mitmul.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":"2014-11-11T04:35:32.000Z","updated_at":"2025-03-17T23:51:08.000Z","dependencies_parsed_at":"2022-08-21T20:30:48.858Z","dependency_job_id":null,"html_url":"https://github.com/mitmul/deeppose","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mitmul%2Fdeeppose","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mitmul%2Fdeeppose/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mitmul%2Fdeeppose/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mitmul%2Fdeeppose/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mitmul","download_url":"https://codeload.github.com/mitmul/deeppose/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247378149,"owners_count":20929297,"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":["chainer"],"created_at":"2024-08-01T12:00:34.137Z","updated_at":"2025-04-05T18:08:39.260Z","avatar_url":"https://github.com/mitmul.png","language":"Python","funding_links":[],"categories":["Preferred Networks Research"],"sub_categories":["Computer Vision"],"readme":"# DeepPose\n\nNOTE: This is not official implementation. Original paper is [DeepPose: Human Pose Estimation via Deep Neural Networks](http://arxiv.org/abs/1312.4659).\n\n# Requirements\n\n- Python 3.5.1+\n  - [Chainer 1.13.0+](https://github.com/pfnet/chainer)\n  - numpy 1.9+\n  - scikit-image 0.11.3+\n  - OpenCV 3.1.0+\n\nI strongly recommend to use Anaconda environment. This repo may be able to be used in Python 2.7 environment, but I haven't tested.\n\n## Installation of dependencies\n\n```\npip install chainer\npip install numpy\npip install scikit-image\n# for python3\nconda install -c https://conda.binstar.org/menpo opencv3\n# for python2\nconda install opencv\n```\n\n# Dataset preparation\n\n```\nbash datasets/download.sh\npython datasets/flic_dataset.py\npython datasets/lsp_dataset.py\npython datasets/mpii_dataset.py\n```\n\n- [FLIC-full dataset](http://vision.grasp.upenn.edu/cgi-bin/index.php?n=VideoLearning.FLIC)\n- [LSP Extended dataset](http://www.comp.leeds.ac.uk/mat4saj/lspet_dataset.zip)\n- **MPII dataset**\n    - [Annotation](http://datasets.d2.mpi-inf.mpg.de/leonid14cvpr/mpii_human_pose_v1_u12_1.tar.gz)\n    - [Images](http://datasets.d2.mpi-inf.mpg.de/andriluka14cvpr/mpii_human_pose_v1.tar.gz)\n\n## MPII Dataset\n\n- [MPII Human Pose Dataset](http://human-pose.mpi-inf.mpg.de/#download)\n- training images: 18079, test images: 6908\n  - test images don't have any annotations\n  - so we split trining imges into training/test joint set\n  - each joint set has\n- training joint set: 17928, test joint set: 1991\n\n# Start training\n\nStarting with the prepared shells is the easiest way. If you want to run `train.py` with your own settings, please check the options first by `python scripts/train.py --help` and modify one of the following shells to customize training settings.\n\n## For FLIC Dataset\n\n```\nbash shells/train_flic.sh\n```\n\n## For LSP Dataset\n\n```\nbash shells/train_lsp.sh\n```\n\n## For MPII Dataset\n\n```\nbash shells/train_mpii.sh\n```\n\n### GPU memory requirement\n\n- AlexNet\n  - batchsize: 128 -\u003e about 2870 MiB\n  - batchsize: 64 -\u003e about 1890 MiB\n  - batchsize: 32 (default) -\u003e 1374 MiB\n- ResNet50\n  - batchsize: 32 -\u003e 6877 MiB\n\n# Prediction\n\nWill add some tools soon\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmitmul%2Fdeeppose","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmitmul%2Fdeeppose","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmitmul%2Fdeeppose/lists"}