{"id":15026520,"url":"https://github.com/aim-uofa/adelaidet","last_synced_at":"2025-05-14T15:07:24.591Z","repository":{"id":37249806,"uuid":"235718232","full_name":"aim-uofa/AdelaiDet","owner":"aim-uofa","description":"AdelaiDet is an open source toolbox for multiple instance-level detection and recognition tasks.","archived":false,"fork":false,"pushed_at":"2024-08-23T00:56:57.000Z","size":679,"stargazers_count":3431,"open_issues_count":306,"forks_count":653,"subscribers_count":83,"default_branch":"master","last_synced_at":"2025-04-11T06:15:50.729Z","etag":null,"topics":["abcnet","adelaidet","blendmask","boxinst","condinst","densecl","fcos","instance-segmentation","meinst","object-detection","ocr","solo","solov2","text-detection","text-recognition"],"latest_commit_sha":null,"homepage":"https://git.io/AdelaiDet","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/aim-uofa.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":"2020-01-23T03:48:55.000Z","updated_at":"2025-04-11T02:46:54.000Z","dependencies_parsed_at":"2023-01-24T01:31:25.628Z","dependency_job_id":"1136e362-5a39-49e0-b368-47cba986f312","html_url":"https://github.com/aim-uofa/AdelaiDet","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/aim-uofa%2FAdelaiDet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aim-uofa%2FAdelaiDet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aim-uofa%2FAdelaiDet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aim-uofa%2FAdelaiDet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/aim-uofa","download_url":"https://codeload.github.com/aim-uofa/AdelaiDet/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254169660,"owners_count":22026213,"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":["abcnet","adelaidet","blendmask","boxinst","condinst","densecl","fcos","instance-segmentation","meinst","object-detection","ocr","solo","solov2","text-detection","text-recognition"],"created_at":"2024-09-24T20:04:37.116Z","updated_at":"2025-05-14T15:07:24.568Z","avatar_url":"https://github.com/aim-uofa.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n    \u003cimg src=\"docs/adel-logo.svg\" width=\"160\" \u003e\n\u003c/div\u003e\n\n#  AdelaiDet\n\nAs of Jan. 2024, the CloudStor server is dead. Model files are hosted on huggingface:\n\n- https://huggingface.co/ZjuCv/AdelaiDet/tree/main\n- https://huggingface.co/tianzhi/AdelaiDet-FCOS/tree/main\n- https://huggingface.co/tianzhi/AdelaiDet-CondInst/tree/main\n- https://huggingface.co/tianzhi/AdelaiDet-BoxInst/tree/main\n\n\n*AdelaiDet* is an open source toolbox for multiple instance-level recognition tasks on top of [Detectron2](https://github.com/facebookresearch/detectron2).\nAll instance-level recognition works from our group are open-sourced here.\n\nTo date, AdelaiDet implements the following algorithms:\n\n* [FCOS](configs/FCOS-Detection/README.md)\n* [BlendMask](configs/BlendMask/README.md)\n* [MEInst](configs/MEInst-InstanceSegmentation/README.md)\n* [ABCNet](configs/BAText/README.md)\n* [ABCNetv2](configs/BAText#quick-start-abcnetv2) \n* [CondInst](configs/CondInst/README.md)\n* [SOLO](https://arxiv.org/abs/1912.04488) ([mmdet version](https://github.com/WXinlong/SOLO))\n* [SOLOv2](configs/SOLOv2/README.md)\n* [BoxInst](configs/BoxInst/README.md) ([video demo](https://www.youtube.com/watch?v=NuF8NAYf5L8))\n* [DenseCL](configs/DenseCL/README.md)\n* [FCPose](configs/FCPose/README.md)\n\n\n\n## Models\n### COCO Object Detecton Baselines with [FCOS](https://arxiv.org/abs/1904.01355)\nName | inf. time | box AP | download\n--- |:---:|:---:|:---\n[FCOS_R_50_1x](configs/FCOS-Detection/R_50_1x.yaml) | 16 FPS | 38.7 | [model](https://huggingface.co/tianzhi/AdelaiDet-FCOS/resolve/main/FCOS_R_50_1x.pth?download=true)\n[FCOS_MS_R_101_2x](configs/FCOS-Detection/MS_R_101_2x.yaml) | 12 FPS | 43.1 | [model](https://huggingface.co/tianzhi/AdelaiDet-FCOS/resolve/main/FCOS_MS_R_101_2x.pth?download=true)\n[FCOS_MS_X_101_32x8d_2x](configs/FCOS-Detection/MS_X_101_32x8d_2x.yaml) | 6.6 FPS | 43.9 | [model](https://huggingface.co/tianzhi/AdelaiDet-FCOS/resolve/main/FCOS_MS_X_101_32x8d_2x.pth?download=true)\n[FCOS_MS_X_101_32x8d_dcnv2_2x](configs/FCOS-Detection/MS_X_101_32x8d_2x_dcnv2.yaml) | 4.6 FPS | 46.6 | [model](https://huggingface.co/tianzhi/AdelaiDet-FCOS/resolve/main/FCOS_MS_X_101_32x8d_dcnv2_2x.pth?download=true)\n[FCOS_RT_MS_DLA_34_4x_shtw](configs/FCOS-Detection/FCOS_RT/MS_DLA_34_4x_syncbn_shared_towers.yaml) | 52 FPS | 39.1 | [model](https://huggingface.co/tianzhi/AdelaiDet-FCOS/resolve/main/FCOS_RT_MS_DLA_34_4x_syncbn_shared_towers.pth?download=true)\n\nMore models can be found in FCOS [README.md](configs/FCOS-Detection/README.md).\n\n### COCO Instance Segmentation Baselines with [BlendMask](https://arxiv.org/abs/2001.00309)\n\nModel | Name |inf. time | box AP | mask AP | download\n--- |:---:|:---:|:---:|:---:|:---:\nMask R-CNN | [R_101_3x](https://github.com/facebookresearch/detectron2/blob/master/configs/COCO-InstanceSegmentation/mask_rcnn_R_101_FPN_3x.yaml) | 10 FPS | 42.9 | 38.6 |\nBlendMask | [R_101_3x](configs/BlendMask/R_101_3x.yaml) | 11 FPS | 44.8 | 39.5 | [model](https://huggingface.co/ZjuCv/AdelaiDet/blob/main/R_101_3x.pth)\nBlendMask | [R_101_dcni3_5x](configs/BlendMask/R_101_dcni3_5x.yaml) | 10 FPS | 46.8 | 41.1 | [model](https://huggingface.co/ZjuCv/AdelaiDet/blob/main/R_101_dcni3_5x.pth)\n\nFor more models and information, please refer to BlendMask [README.md](configs/BlendMask/README.md).\n\n### COCO Instance Segmentation Baselines with [MEInst](https://arxiv.org/abs/2003.11712)\n\nName | inf. time | box AP | mask AP | download\n--- |:---:|:---:|:---:|:---:\n[MEInst_R_50_3x](https://github.com/aim-uofa/AdelaiDet/configs/MEInst-InstanceSegmentation/MEInst_R_50_3x.yaml) | 12 FPS | 43.6 | 34.5 | [model](https://huggingface.co/ZjuCv/AdelaiDet/blob/main/MEInst_R_50_3x.pth)\n\nFor more models and information, please refer to MEInst [README.md](configs/MEInst-InstanceSegmentation/README.md).\n\n### Total_Text results with [ABCNet](configs/BAText/README.md)\n\nName | inf. time | e2e-hmean | det-hmean | download\n---  |:---------:|:---------:|:---------:|:---:\n[v1-totaltext](configs/BAText/TotalText/attn_R_50.yaml) | 11 FPS | 67.1 | 86.0 | [model](https://huggingface.co/ZjuCv/AdelaiDet/blob/main/tt_e2e_attn_R_50.pth)\n[v2-totaltext](configs/BAText/TotalText/v2_attn_R_50.yaml) | 7.7 FPS | 71.8 | 87.2 | [model](https://huggingface.co/ZjuCv/AdelaiDet/blob/main/model_v2_totaltext.pth)\n\nFor more models and information, please refer to ABCNet [README.md](configs/BAText/README.md).\n\n### COCO Instance Segmentation Baselines with [CondInst](https://arxiv.org/abs/2003.05664)\n\nName | inf. time | box AP | mask AP | download\n--- |:---:|:---:|:---:|:---:\n[CondInst_MS_R_50_1x](configs/CondInst/MS_R_50_1x.yaml) | 14 FPS | 39.7 | 35.7 | [model](https://huggingface.co/tianzhi/AdelaiDet-CondInst/resolve/main/CondInst_MS_R_50_1x.pth?download=true)\n[CondInst_MS_R_50_BiFPN_3x_sem](configs/CondInst/MS_R_50_BiFPN_3x_sem.yaml) | 13 FPS | 44.7 | 39.4 | [model](https://huggingface.co/tianzhi/AdelaiDet-CondInst/resolve/main/CondInst_MS_R_50_BiFPN_3x_sem.pth?download=true)\n[CondInst_MS_R_101_3x](configs/CondInst/MS_R_101_3x.yaml) | 11 FPS | 43.3 | 38.6 | [model](https://huggingface.co/tianzhi/AdelaiDet-CondInst/resolve/main/CondInst_MS_R_101_3x.pth?download=true)\n[CondInst_MS_R_101_BiFPN_3x_sem](configs/CondInst/MS_R_101_BiFPN_3x_sem.yaml) | 10 FPS | 45.7 | 40.2 | [model](https://huggingface.co/tianzhi/AdelaiDet-CondInst/resolve/main/CondInst_R_101_BiFPN_3x_sem.pth?download=true)\n\nFor more models and information, please refer to CondInst [README.md](configs/CondInst/README.md).\n\nNote that:\n- Inference time for all projects is measured on a NVIDIA 1080Ti with batch size 1.\n- APs are evaluated on COCO2017 val split unless specified.\n\n\n## Installation\n\nFirst install Detectron2 following the official guide: [INSTALL.md](https://github.com/facebookresearch/detectron2/blob/master/INSTALL.md).\n\n*Please use Detectron2 with commit id [9eb4831](https://github.com/facebookresearch/detectron2/commit/9eb4831f742ae6a13b8edb61d07b619392fb6543) if you have any issues related to Detectron2.*\n\nThen build AdelaiDet with:\n\n```\ngit clone https://github.com/aim-uofa/AdelaiDet.git\ncd AdelaiDet\npython setup.py build develop\n```\n\nIf you are using docker, a pre-built image can be pulled with:\n\n```\ndocker pull tianzhi0549/adet:latest\n```\n\nSome projects may require special setup, please follow their own `README.md` in [configs](configs).\n\n## Quick Start\n\n### Inference with Pre-trained Models\n\n1. Pick a model and its config file, for example, `fcos_R_50_1x.yaml`.\n2. Download the model `wget https://huggingface.co/tianzhi/AdelaiDet-FCOS/resolve/main/FCOS_R_50_1x.pth?download=true -O fcos_R_50_1x.pth`\n3. Run the demo with\n```\npython demo/demo.py \\\n    --config-file configs/FCOS-Detection/R_50_1x.yaml \\\n    --input input1.jpg input2.jpg \\\n    --opts MODEL.WEIGHTS fcos_R_50_1x.pth\n```\n\n### Train Your Own Models\n\nTo train a model with \"train_net.py\", first\nsetup the corresponding datasets following\n[datasets/README.md](https://github.com/facebookresearch/detectron2/blob/master/datasets/README.md),\nthen run:\n\n```\nOMP_NUM_THREADS=1 python tools/train_net.py \\\n    --config-file configs/FCOS-Detection/R_50_1x.yaml \\\n    --num-gpus 8 \\\n    OUTPUT_DIR training_dir/fcos_R_50_1x\n```\nTo evaluate the model after training, run:\n\n```\nOMP_NUM_THREADS=1 python tools/train_net.py \\\n    --config-file configs/FCOS-Detection/R_50_1x.yaml \\\n    --eval-only \\\n    --num-gpus 8 \\\n    OUTPUT_DIR training_dir/fcos_R_50_1x \\\n    MODEL.WEIGHTS training_dir/fcos_R_50_1x/model_final.pth\n```\nNote that:\n- The configs are made for 8-GPU training. To train on another number of GPUs, change the `--num-gpus`.\n- If you want to measure the inference time, please change `--num-gpus` to 1.\n- We set `OMP_NUM_THREADS=1` by default, which achieves the best speed on our machines, please change it as needed.\n- This quick start is made for FCOS. If you are using other projects, please check the projects' own `README.md` in [configs](configs). \n\n\n## Acknowledgements\n\nThe authors are grateful to\nNvidia, Huawei Noah's Ark Lab, ByteDance, Adobe who generously donated GPU computing in the past a few years.\n\n## Citing AdelaiDet\n\nIf you use this toolbox in your research or wish to refer to the baseline results published here, please use the following BibTeX entries:\n\n```BibTeX\n\n@misc{tian2019adelaidet,\n  author =       {Tian, Zhi and Chen, Hao and Wang, Xinlong and Liu, Yuliang and Shen, Chunhua},\n  title =        {{AdelaiDet}: A Toolbox for Instance-level Recognition Tasks},\n  howpublished = {\\url{https://git.io/adelaidet}},\n  year =         {2019}\n}\n```\nand relevant publications:\n```BibTeX\n\n@inproceedings{tian2019fcos,\n  title     =  {{FCOS}: Fully Convolutional One-Stage Object Detection},\n  author    =  {Tian, Zhi and Shen, Chunhua and Chen, Hao and He, Tong},\n  booktitle =  {Proc. Int. Conf. Computer Vision (ICCV)},\n  year      =  {2019}\n}\n\n@article{tian2021fcos,\n  title   =  {{FCOS}: A Simple and Strong Anchor-free Object Detector},\n  author  =  {Tian, Zhi and Shen, Chunhua and Chen, Hao and He, Tong},\n  journal =  {IEEE T. Pattern Analysis and Machine Intelligence (TPAMI)},\n  year    =  {2021}\n}\n\n@inproceedings{chen2020blendmask,\n  title     =  {{BlendMask}: Top-Down Meets Bottom-Up for Instance Segmentation},\n  author    =  {Chen, Hao and Sun, Kunyang and Tian, Zhi and Shen, Chunhua and Huang, Yongming and Yan, Youliang},\n  booktitle =  {Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR)},\n  year      =  {2020}\n}\n\n@inproceedings{zhang2020MEInst,\n  title     =  {Mask Encoding for Single Shot Instance Segmentation},\n  author    =  {Zhang, Rufeng and Tian, Zhi and Shen, Chunhua and You, Mingyu and Yan, Youliang},\n  booktitle =  {Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR)},\n  year      =  {2020}\n}\n\n@inproceedings{liu2020abcnet,\n  title     =  {{ABCNet}: Real-time Scene Text Spotting with Adaptive {B}ezier-Curve Network},\n  author    =  {Liu, Yuliang and Chen, Hao and Shen, Chunhua and He, Tong and Jin, Lianwen and Wang, Liangwei},\n  booktitle =  {Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR)},\n  year      =  {2020}\n}\n\n@ARTICLE{9525302,\n  author={Liu, Yuliang and Shen, Chunhua and Jin, Lianwen and He, Tong and Chen, Peng and Liu, Chongyu and Chen, Hao},\n  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, \n  title={ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting}, \n  year={2021},\n  volume={},\n  number={},\n  pages={1-1},\n  doi={10.1109/TPAMI.2021.3107437}\n}\n\n@inproceedings{wang2020solo,\n  title     =  {{SOLO}: Segmenting Objects by Locations},\n  author    =  {Wang, Xinlong and Kong, Tao and Shen, Chunhua and Jiang, Yuning and Li, Lei},\n  booktitle =  {Proc. Eur. Conf. Computer Vision (ECCV)},\n  year      =  {2020}\n}\n\n@inproceedings{wang2020solov2,\n  title     =  {{SOLOv2}: Dynamic and Fast Instance Segmentation},\n  author    =  {Wang, Xinlong and Zhang, Rufeng and Kong, Tao and Li, Lei and Shen, Chunhua},\n  booktitle =  {Proc. Advances in Neural Information Processing Systems (NeurIPS)},\n  year      =  {2020}\n}\n\n@article{wang2021solo,\n  title   =  {{SOLO}: A Simple Framework for Instance Segmentation},\n  author  =  {Wang, Xinlong and Zhang, Rufeng and Shen, Chunhua and Kong, Tao and Li, Lei},\n  journal =  {IEEE T. Pattern Analysis and Machine Intelligence (TPAMI)},\n  year    =  {2021}\n}\n\n@article{tian2019directpose,\n  title   =  {{DirectPose}: Direct End-to-End Multi-Person Pose Estimation},\n  author  =  {Tian, Zhi and Chen, Hao and Shen, Chunhua},\n  journal =  {arXiv preprint arXiv:1911.07451},\n  year    =  {2019}\n}\n\n@inproceedings{tian2020conditional,\n  title     =  {Conditional Convolutions for Instance Segmentation},\n  author    =  {Tian, Zhi and Shen, Chunhua and Chen, Hao},\n  booktitle =  {Proc. Eur. Conf. Computer Vision (ECCV)},\n  year      =  {2020}\n}\n\n@article{CondInst2022Tian,\n  title   = {Instance and Panoptic Segmentation Using Conditional Convolutions},\n  author  = {Tian, Zhi and Zhang, Bowen and Chen, Hao and Shen, Chunhua},\n  journal = {IEEE T. Pattern Analysis and Machine Intelligence (TPAMI)},\n  year    = {2022}\n}\n\n@inproceedings{tian2021boxinst,\n  title     =  {{BoxInst}: High-Performance Instance Segmentation with Box Annotations},\n  author    =  {Tian, Zhi and Shen, Chunhua and Wang, Xinlong and Chen, Hao},\n  booktitle =  {Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR)},\n  year      =  {2021}\n}\n\n@inproceedings{wang2021densecl,\n  title     =   {Dense Contrastive Learning for Self-Supervised Visual Pre-Training},\n  author    =   {Wang, Xinlong and Zhang, Rufeng and Shen, Chunhua and Kong, Tao and Li, Lei},\n  booktitle =   {Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR)},\n  year      =   {2021}\n}\n\n@inproceedings{Mao2021pose,\n  title     =   {{FCPose}: Fully Convolutional Multi-Person Pose Estimation With Dynamic Instance-Aware Convolutions},\n  author    =   {Mao, Weian and  Tian, Zhi  and Wang, Xinlong  and Shen, Chunhua},\n  booktitle =   {Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR)},\n  year      =   {2021}\n}\n```\n\n## License\n\nFor academic use, this project is licensed under the 2-clause BSD License - see the LICENSE file for details. For commercial use, please contact [Chunhua Shen](mailto:chhshen@gmail.com).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faim-uofa%2Fadelaidet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faim-uofa%2Fadelaidet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faim-uofa%2Fadelaidet/lists"}