{"id":20094499,"url":"https://github.com/byrkbrk/unet-implementation","last_synced_at":"2026-05-17T15:05:15.278Z","repository":{"id":129211804,"uuid":"603756111","full_name":"byrkbrk/unet-implementation","owner":"byrkbrk","description":"PyTorch implementation of U-Net for segmentation of neural structures in electron microscopic stacks","archived":false,"fork":false,"pushed_at":"2023-10-08T14:53:09.000Z","size":18273,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-01-13T03:31:59.938Z","etag":null,"topics":["deep-learning","google-colab","image-segmentation","medical-imaging","pytorch","unet"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/byrkbrk.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2023-02-19T13:42:56.000Z","updated_at":"2023-03-09T21:30:51.000Z","dependencies_parsed_at":"2024-11-13T17:02:51.174Z","dependency_job_id":null,"html_url":"https://github.com/byrkbrk/unet-implementation","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/byrkbrk%2Funet-implementation","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/byrkbrk%2Funet-implementation/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/byrkbrk%2Funet-implementation/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/byrkbrk%2Funet-implementation/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/byrkbrk","download_url":"https://codeload.github.com/byrkbrk/unet-implementation/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":241533628,"owners_count":19977826,"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":["deep-learning","google-colab","image-segmentation","medical-imaging","pytorch","unet"],"created_at":"2024-11-13T16:50:59.566Z","updated_at":"2025-10-24T02:52:05.155Z","avatar_url":"https://github.com/byrkbrk.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# U-Net implementation using PyTorch on Google Colab\n\nWe implement the well-known image segmentatation architecture, [U-Net](https://arxiv.org/abs/1505.04597) for segmentation of neural structures in electron microscopic stacks.\nBecause [the segmentation challenge website](brainiac2.mit.edu/isbi_challenge/) indicated in \n[the website](https://lmb.informatik.uni-freiburg.de/people/ronneber/u-net/) \nof the authors (of the U-Net article) is (apparently) no longer accessible, we use the datasets (i.e., `volumes-train.tif`, `labels-train.tif`, `volumes-test.tif`) shared in [the repository](https://github.com/zhixuhao/unet/tree/master/data/membrane).\n\nOur U-Net architecture is inspired by the Coursera course [Apply GANs](https://www.coursera.org/learn/apply-generative-adversarial-networks-gans/home/week/2).\n\n---\n\n## Requirements\nThis repository is designed to train the model and make inferences entirely on Google Colab. So, for successful training and inference, it suffices to\n\n- open the notebook [`unet_cell_data.ipynb`](https://github.com/byrkbrk/unet-implementation/blob/22248e94a769afd2894ad695b7c64d89cfaaeadc/unet_cell_data.ipynb) \non Colab (by using either this [link](https://colab.research.google.com/github/byrkbrk/unet-implementation/blob/main/unet_cell_data.ipynb) or the link *Open in Colab* at the top left of the notebook)\n- sign in your Google account (if you haven't yet)\n- run the cells (having short explanatory comments) one by one\n\n## Training dataset\n\nOur training dataset consists of 30 (512-by-512) input-label image pairs (i.e., `volumes-train.tif`, `labels-train.tif`) and one example of them is as follows:\n\n![input-label-pair](./images-for-readme/input-label-pair.png)\n\n## Test dataset and predictions\n\nIn like manner, our test dataset (viz., `volumes-test.tif`) comprises a total of 30 (512-by-512) images. Presented below are certain exemplars drawn from the test dataset, together with the corresponding predictions (of our trained U-Net):\n\n![test-images](./images-for-readme/test-images.png)\n\n![predictions](./images-for-readme/predictions.png)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbyrkbrk%2Funet-implementation","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbyrkbrk%2Funet-implementation","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbyrkbrk%2Funet-implementation/lists"}