{"id":19839804,"url":"https://github.com/qdata/c-tran","last_synced_at":"2025-04-12T21:29:56.415Z","repository":{"id":41261227,"uuid":"332824789","full_name":"QData/C-Tran","owner":"QData","description":"General Multi-label Image Classification with Transformers","archived":false,"fork":false,"pushed_at":"2024-11-02T02:16:30.000Z","size":3119,"stargazers_count":263,"open_issues_count":12,"forks_count":43,"subscribers_count":7,"default_branch":"main","last_synced_at":"2025-04-04T01:18:42.373Z","etag":null,"topics":["computer-vision","multi-label-classification","transformers"],"latest_commit_sha":null,"homepage":"","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/QData.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2021-01-25T17:19:22.000Z","updated_at":"2025-04-01T16:14:38.000Z","dependencies_parsed_at":"2024-11-12T12:38:32.250Z","dependency_job_id":null,"html_url":"https://github.com/QData/C-Tran","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/QData%2FC-Tran","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/QData%2FC-Tran/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/QData%2FC-Tran/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/QData%2FC-Tran/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/QData","download_url":"https://codeload.github.com/QData/C-Tran/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248634724,"owners_count":21137105,"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":["computer-vision","multi-label-classification","transformers"],"created_at":"2024-11-12T12:24:24.838Z","updated_at":"2025-04-12T21:29:56.394Z","avatar_url":"https://github.com/QData.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"**General Multi-label Image Classification with Transformers**\u003cbr/\u003e\nJack Lanchantin, Tianlu Wang, Vicente Ordóñez Román, Yanjun Qi\u003cbr/\u003e\nConference on Computer Vision and Pattern Recognition (CVPR) 2021\u003cbr/\u003e\n[[paper]](https://arxiv.org/abs/2011.14027) [[poster]](https://github.com/QData/C-Tran/blob/main/supplemental/ctran_poster.pdf) [[slides]](https://github.com/QData/C-Tran/blob/main/supplemental/ctran_slides.pdf)\n\u003cbr/\u003e\n\n\n\n## Training and Running C-Tran ##\n\nPython version 3.7 is required and all major packages used and their versions are listed in `requirements.txt`.\n\n### C-Tran on COCO80 Dataset ###\nDownload COCO data (19G)\n```\nwget https://www.cs.virginia.edu/~yq2h/jack/vision/coco.tar.gz\nmkdir -p data/\ntar -xvf coco.tar.gz -C data/\n```\n\nTrain New Model\n```\npython main.py  --batch_size 16  --lr 0.00001 --optim 'adam' --layers 3  --dataset 'coco' --use_lmt --dataroot data/\n```\n\n\n### C-Tran on VOC20 Dataset ###\nDownload VOC2007 data (1.7G)\n```\nwget https://www.cs.virginia.edu/~yq2h/jack/vision/voc.tar.gz\nmkdir -p data/\ntar -xvf voc.tar.gz -C data/\n```\n\nTrain New Model\n```\npython main.py  --batch_size 16  --lr 0.00001 --optim 'adam' --layers 3  --dataset 'voc' --use_lmt --grad_ac_step 2 --dataroot data/\n```\n\n\n## Citing ##\n\n```bibtex\n@article{lanchantin2020general,\n  title={General Multi-label Image Classification with Transformers},\n  author={Lanchantin, Jack and Wang, Tianlu and Ordonez, Vicente and Qi, Yanjun},\n  journal={arXiv preprint arXiv:2011.14027},\n  year={2020}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fqdata%2Fc-tran","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fqdata%2Fc-tran","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fqdata%2Fc-tran/lists"}