{"id":20841694,"url":"https://github.com/jahongir7174/sixdrepnet","last_synced_at":"2025-07-28T12:09:26.709Z","repository":{"id":225922484,"uuid":"764367929","full_name":"jahongir7174/SixDRepNet","owner":"jahongir7174","description":"6D Rotation Representation for Unconstrained Head Pose Estimation","archived":false,"fork":false,"pushed_at":"2024-03-27T22:26:04.000Z","size":86170,"stargazers_count":7,"open_issues_count":1,"forks_count":1,"subscribers_count":0,"default_branch":"master","last_synced_at":"2025-03-24T12:46:59.149Z","etag":null,"topics":["head-pose-estimation","opencv-python","python","pytorch"],"latest_commit_sha":null,"homepage":"https://arxiv.org/pdf/2202.12555.pdf","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/jahongir7174.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,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-02-28T00:12:30.000Z","updated_at":"2024-10-22T00:40:13.000Z","dependencies_parsed_at":"2024-03-05T02:05:50.394Z","dependency_job_id":"7a6569a3-00da-48b3-a1ed-c7e33493ed56","html_url":"https://github.com/jahongir7174/SixDRepNet","commit_stats":null,"previous_names":["jahongir7174/sixdrepnet"],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jahongir7174%2FSixDRepNet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jahongir7174%2FSixDRepNet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jahongir7174%2FSixDRepNet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jahongir7174%2FSixDRepNet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jahongir7174","download_url":"https://codeload.github.com/jahongir7174/SixDRepNet/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248231326,"owners_count":21069297,"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":["head-pose-estimation","opencv-python","python","pytorch"],"created_at":"2024-11-18T01:21:20.003Z","updated_at":"2025-04-10T14:04:49.132Z","avatar_url":"https://github.com/jahongir7174.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"6D Rotation Representation for Unconstrained Head Pose Estimation\n\n### Note\n\n* The default train dataset is `300W-LP`\n* The default test dataset is `AFLW2000`\n\n### Installation\n\n```\nconda create -n PyTorch python=3.11\nconda activate PyTorch\nconda install pytorch torchvision torchaudio pytorch-cuda=11.8 -c pytorch -c nvidia\npip install opencv-python==4.5.5.64\npip install scipy\npip install tqdm\npip install timm\n```\n\n### Train\n\n* Configure your dataset path in `main.py` for training\n* Download [IMAGENET](https://github.com/jahongir7174/SixDRepNet/releases/tag/v0.0.1) pretrained weights\n* Run `python main.py --train` for Single-GPU training\n* Run `bash main.sh $ --train` for Multi-GPU training, `$` is number of GPUs\n\n### Test\n\n* Configure your dataset path in `main.py` for testing\n* Run `python main.py --test` for testing\n\n### Demo\n\n* Configure your video path in `main.py` for visualizing the demo\n* Run `python main.py --demo` for demo\n\n### Results\n\n|   Backbone   | Epochs | Pitch |  Yaw | Roll |  MAE | Parameters(M) | FLOPS (B) | Throughput (images/s) |\n|:------------:|:------:|------:|-----:|-----:|-----:|--------------:|----------:|----------------------:|\n|  RepNet-A2   |   90   |  4.78 | 3.68 | 3.25 | 3.90 |         25.49 |       5.1 |                  1322 |\n| RepNet-B1G2* |   30   |  4.91 | 3.63 | 3.37 | 3.97 |         41.36 |       8.8 |                   792 |\n\n`*` means that the results are from original repo, see reference\n\n![Alt Text](./demo/demo.gif)\n\n#### Reference\n\n* https://github.com/thohemp/6DRepNet\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjahongir7174%2Fsixdrepnet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjahongir7174%2Fsixdrepnet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjahongir7174%2Fsixdrepnet/lists"}