{"id":28518420,"url":"https://github.com/sharpiless/pix2seq-mmdetection","last_synced_at":"2026-03-07T03:32:50.739Z","repository":{"id":49789057,"uuid":"482688618","full_name":"Sharpiless/Pix2seq-mmdetection","owner":"Sharpiless","description":"Unofficial implement of \"Pix2seq: A Language Modeling Framework for Object Detection\" on mmdetection","archived":false,"fork":false,"pushed_at":"2022-04-18T03:03:15.000Z","size":8589,"stargazers_count":33,"open_issues_count":1,"forks_count":4,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-09-05T01:07:34.723Z","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":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Sharpiless.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2022-04-18T02:25:58.000Z","updated_at":"2025-04-29T08:46:10.000Z","dependencies_parsed_at":"2022-09-13T19:50:51.395Z","dependency_job_id":null,"html_url":"https://github.com/Sharpiless/Pix2seq-mmdetection","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/Sharpiless/Pix2seq-mmdetection","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Sharpiless%2FPix2seq-mmdetection","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Sharpiless%2FPix2seq-mmdetection/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Sharpiless%2FPix2seq-mmdetection/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Sharpiless%2FPix2seq-mmdetection/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Sharpiless","download_url":"https://codeload.github.com/Sharpiless/Pix2seq-mmdetection/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Sharpiless%2FPix2seq-mmdetection/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30206579,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-07T03:24:23.086Z","status":"ssl_error","status_checked_at":"2026-03-07T03:23:11.444Z","response_time":53,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":[],"created_at":"2025-06-09T05:37:10.459Z","updated_at":"2026-03-07T03:32:50.727Z","avatar_url":"https://github.com/Sharpiless.png","language":"Python","readme":"## Introduction\n\nThis is an unofficial replication of \"Pix2seq: A Language Modeling Framework for Object Detection\" with pretrained model on mmdetection.\n\n## License\n\nThis project is released under the [Apache 2.0 license](LICENSE).\n\n## Installation\n\nPlease refer to [get_started.md](docs/get_started.md) for installation.\n\n## Train \u0026 Evaluation\n\nTrain by running (about 10 days with 8*V100 32GB)\n```bash\npython -m torch.distributed.launch --nproc_per_node=8 --master_port=5003 \\\n  tools/train.py configs/pix2seq/pix2seq_r50_8x4_50e_coco.py --work-dir pix2seq-output --gpus 8 --launcher pytorch\n```\n\nor\n\nDownload [pretrained pix2seq weights](https://drive.google.com/file/d/1Ku8ZORiLtMs66uleS3aXId7pxlJrTK9d/view?usp=sharing).\n\nEvaluate with single gpu:\n```bash\npython tools/test.py configs/pix2seq/pix2seq_r50_8x4_300_coco.py \\\n  weights/checkpoints.pth --work-dir pix2seq-output --eval bbox --show-dir pix2seq-vis\n```\n\nEvaluate with 8 gpus:\n```bash\npython -m torch.distributed.launch --nproc_per_node=8 --master_port=5003 \\\n  tools/test.py configs/pix2seq/pix2seq_r50_8x4_300_coco.py weights/checkpoints.pth \\\n  --work-dir pix2seq-output --eval bbox --launcher pytorch\n```\n\n| Method  | backbone | Epoch | Batch Size | AP   | AP50  | AP75  | Weights |\n| :-----: | :------: | :----:| :---------:| :---:| :---: | :---: | :---:   |\n| Ours    | R50      | 300   | 32         | 36.4 | 52.8  | 38.5  | [model](https://github.com/Sharpiless/Pix2seq-mmdetection/releases/download/v1.0/checkpoints.pth) |\n| Paper   | R50      | 300   | 128        | 43.0 | 61.0  | 45.6  | - |\n\n\n## Visualization\n\n![](https://github.com/Sharpiless/Pix2seq-mmdetection/blob/main/resources/007114.jpg)\n\n![](https://github.com/Sharpiless/Pix2seq-mmdetection/blob/main/resources/007351.jpg)\n\n![](https://github.com/Sharpiless/Pix2seq-mmdetection/blob/main/resources/008322.jpg)\n\n![](https://github.com/Sharpiless/Pix2seq-mmdetection/blob/main/resources/000000289393.jpg)\n\n![](https://github.com/Sharpiless/Pix2seq-mmdetection/blob/main/resources/000000212559.jpg)\n\n![](https://github.com/Sharpiless/Pix2seq-mmdetection/blob/main/resources/000000255664.jpg)\n\n## TO-DO\n\n- [x] random shuffle targets\n- [x] training from scratch\n- [x] drop class token\n- [x] stochastic depth\n- [x] large scale jittering\n- [ ] support for custom dataset\n- [x] two independent augmentations for each image\n- [x] FrozenBatchNorm2d in backbones\n- [x] auto-argument\n- [x] nucleus sampling\n\n## Acknowledgement\n\n[https://github.com/gaopengcuhk/Pretrained-Pix2Seq](https://github.com/gaopengcuhk/Pretrained-Pix2Seq)\n\n[https://github.com/open-mmlab/mmdetection](https://github.com/open-mmlab/mmdetection)\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsharpiless%2Fpix2seq-mmdetection","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsharpiless%2Fpix2seq-mmdetection","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsharpiless%2Fpix2seq-mmdetection/lists"}