{"id":16269632,"url":"https://github.com/hiyouga/image-segmentation-pytorch","last_synced_at":"2026-04-01T23:01:57.186Z","repository":{"id":56172620,"uuid":"202113635","full_name":"hiyouga/Image-Segmentation-PyTorch","owner":"hiyouga","description":"U-Net for image segmentation, PyTorch implementation.","archived":false,"fork":false,"pushed_at":"2020-11-22T23:05:47.000Z","size":100662,"stargazers_count":16,"open_issues_count":3,"forks_count":4,"subscribers_count":1,"default_branch":"master","last_synced_at":"2026-03-28T00:58:04.024Z","etag":null,"topics":["cv","deep-learning","image-segmentation","pytorch","unet","unet-pytorch"],"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/hiyouga.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":"2019-08-13T09:46:01.000Z","updated_at":"2025-05-25T11:58:49.000Z","dependencies_parsed_at":"2022-08-15T14:01:01.887Z","dependency_job_id":null,"html_url":"https://github.com/hiyouga/Image-Segmentation-PyTorch","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/hiyouga/Image-Segmentation-PyTorch","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hiyouga%2FImage-Segmentation-PyTorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hiyouga%2FImage-Segmentation-PyTorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hiyouga%2FImage-Segmentation-PyTorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hiyouga%2FImage-Segmentation-PyTorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hiyouga","download_url":"https://codeload.github.com/hiyouga/Image-Segmentation-PyTorch/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hiyouga%2FImage-Segmentation-PyTorch/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31292784,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-01T21:15:39.731Z","status":"ssl_error","status_checked_at":"2026-04-01T21:15:34.046Z","response_time":53,"last_error":"SSL_read: 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":["cv","deep-learning","image-segmentation","pytorch","unet","unet-pytorch"],"created_at":"2024-10-10T18:08:43.715Z","updated_at":"2026-04-01T23:01:57.147Z","avatar_url":"https://github.com/hiyouga.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Image-Segmentation-PyTorch\n\n\u003e [PyTorch](https://pytorch.org/) implementation of the [U-Net](https://arxiv.org/abs/1505.04597) for image segmentation.\n\n[![LICENSE](https://img.shields.io/packagist/l/doctrine/orm.svg)](LICENSE)\n\n## Requirement\n\n- Python 3\n- numpy\n- matplotlib\n- Pillow\n- torch\n- torchvision\n- pydensecrf\n\n## Dataset\n\nBased on the shoe dataset [[Google Drive]](https://drive.google.com/open?id=1UCKqFsGubgqkJgJB7cLS5GURRLH7fxzP) provided by our teacher.\n\n![example](assets/example.jpg)\n\n## Usage\n\n### Training\n\n```sh\npython train.py\n```\n\n### Inference\n\n```sh\npython train.py --inference True --checkpoint [*.pt]\n```\n\nThe checkpoint files can be found in the `state_dict` folder.\n\n### Show help message\n\n```sh\npython train.py -h\n```\n\n## Implemented model\n\nRonneberger, O., Fischer, P., and Brox, T. 2015. U-Net: Convolutional Networks for Biomedical Image Segmentation. In Medical Image Computing and Computer-Assisted Intervention (MICCAI). [[pdf]](https://arxiv.org/pdf/1505.04597)\n\n![unet](assets/unet.png)\n\n## Notes\n\nThe model was trained from scratch on Tesla V100 32GB*4. Training the model takes 3.6GB of memory and predicting images takes 1.3GB. If you don't have enough GPU memory, consider using bilinear up-sampling rather than transposed convolution in the model.\n\n## Acknowledgements\n\n* Some of the code is borrowed from [milesial](https://github.com/milesial/Pytorch-UNet).\n* This is a personal homework for \"Machine Learning Theory and Application\" in BUAA Summer School.\n\n## License\n\nMIT\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhiyouga%2Fimage-segmentation-pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhiyouga%2Fimage-segmentation-pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhiyouga%2Fimage-segmentation-pytorch/lists"}