{"id":13936595,"url":"https://github.com/CharlesShang/FastMaskRCNN","last_synced_at":"2025-07-19T22:31:05.027Z","repository":{"id":40432303,"uuid":"86167728","full_name":"CharlesShang/FastMaskRCNN","owner":"CharlesShang","description":"Mask RCNN in TensorFlow ","archived":false,"fork":false,"pushed_at":"2021-01-05T04:08:12.000Z","size":510,"stargazers_count":3098,"open_issues_count":142,"forks_count":1101,"subscribers_count":222,"default_branch":"master","last_synced_at":"2024-11-21T06:37:16.360Z","etag":null,"topics":["coco","detection","fasterrcnn","maskrcnn","pfn","rcnn","segmentation","tensorflow"],"latest_commit_sha":null,"homepage":null,"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/CharlesShang.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":"2017-03-25T15:33:21.000Z","updated_at":"2024-11-03T01:22:36.000Z","dependencies_parsed_at":"2022-08-19T15:10:24.558Z","dependency_job_id":null,"html_url":"https://github.com/CharlesShang/FastMaskRCNN","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/CharlesShang%2FFastMaskRCNN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CharlesShang%2FFastMaskRCNN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CharlesShang%2FFastMaskRCNN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CharlesShang%2FFastMaskRCNN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CharlesShang","download_url":"https://codeload.github.com/CharlesShang/FastMaskRCNN/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":226686729,"owners_count":17666928,"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":["coco","detection","fasterrcnn","maskrcnn","pfn","rcnn","segmentation","tensorflow"],"created_at":"2024-08-07T23:02:49.585Z","updated_at":"2024-11-27T04:31:14.012Z","avatar_url":"https://github.com/CharlesShang.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# Mask RCNN\nMask RCNN in TensorFlow\n\nThis repo attempts to reproduce this amazing work by Kaiming He et al. : \n[Mask R-CNN](https://arxiv.org/abs/1703.06870)\n\n## Requirements\n\n- [Tensorflow (\u003e= 1.0.0)](https://www.tensorflow.org/install/install_linux)\n- [Numpy](https://github.com/numpy/numpy/blob/master/INSTALL.rst.txt)\n- [COCO dataset](http://mscoco.org/dataset/#download)\n- [Resnet50](http://download.tensorflow.org/models/resnet_v1_50_2016_08_28.tar.gz)\n\n## How-to\n1. Go to `./libs/datasets/pycocotools` and run `make`\n2. Download [COCO](http://mscoco.org/dataset/#download) dataset, place it into `./data`, then run `python download_and_convert_data.py` to build tf-records. It takes a while.\n3. Download pretrained resnet50 model, `wget http://download.tensorflow.org/models/resnet_v1_50_2016_08_28.tar.gz`, unzip it, place it into `./data/pretrained_models/`\n4. Go to `./libs` and run `make`\n5. run `python train/train.py` for training\n6. There are certainly some bugs, please report them back, and let's solve them together.\n\n## TODO:\n- [x] ROIAlign\n- [x] COCO Data Provider\n- [x] Resnet50\n- [x] Feature Pyramid Network\n- [x] Anchor and ROI layer\n- [x] Mask layer\n- [x] Speedup anchor layer with cython\n- [x] Combining all modules together.\n- [x] Testing and debugging (in progress)\n- [ ] Training / evaluation on COCO\n- [ ] Add image summary to show some results\n- [ ] Converting ResneXt\n- [ ] Training \u003e2 images\n\n## Call for contributions\n- Anything helps this repo, including **discussion**, **testing**, **promotion** and of course **your awesome code**.\n\n## Acknowledgment\nThis repo borrows tons of code from \n- [TFFRCNN](https://github.com/CharlesShang/TFFRCNN)\n- [py-faster-rcnn](https://github.com/rbgirshick/py-faster-rcnn) \n- [faster_rcnn](https://github.com/ShaoqingRen/faster_rcnn)\n- [tf-models](https://github.com/tensorflow/models)\n\n## License\nSee [LICENSE](https://github.com/CharlesShang/FastMaskRCNN/blob/master/LICENSE) for details.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FCharlesShang%2FFastMaskRCNN","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FCharlesShang%2FFastMaskRCNN","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FCharlesShang%2FFastMaskRCNN/lists"}