{"id":25284393,"url":"https://github.com/salwaelkaddaoui/unet","last_synced_at":"2026-04-30T07:41:46.037Z","repository":{"id":271417653,"uuid":"913399564","full_name":"salwaElkaddaoui/unet","owner":"salwaElkaddaoui","description":"Implementation of the paper  \"U-Net: Convolutional Networks for Biomedical Image Segmentation\" By Olaf Ronneberger, Philipp Fischer, Thomas Brox, 2015 in Tensorflow 2.x low level API.","archived":false,"fork":false,"pushed_at":"2025-03-21T21:33:10.000Z","size":84,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-21T22:27:47.443Z","etag":null,"topics":["deep-learning","neural-networks","semantic-segmentation","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/salwaElkaddaoui.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":"2025-01-07T15:58:53.000Z","updated_at":"2025-03-21T21:33:12.000Z","dependencies_parsed_at":"2025-02-15T23:20:49.086Z","dependency_job_id":"5fc8d098-a6ca-4e26-9817-4d479b3b4b32","html_url":"https://github.com/salwaElkaddaoui/unet","commit_stats":null,"previous_names":["salwaelkaddaoui/unet"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/salwaElkaddaoui%2Funet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/salwaElkaddaoui%2Funet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/salwaElkaddaoui%2Funet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/salwaElkaddaoui%2Funet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/salwaElkaddaoui","download_url":"https://codeload.github.com/salwaElkaddaoui/unet/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247496754,"owners_count":20948291,"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","neural-networks","semantic-segmentation","tensorflow"],"created_at":"2025-02-12T20:38:23.524Z","updated_at":"2026-04-30T07:41:41.018Z","avatar_url":"https://github.com/salwaElkaddaoui.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# U-Net Implementation\nThis project provides a configurable U-Net for image segmentation, implemented using the TensorFlow 2.x low-level API. It is based on:\n\n- U-Net: \"U-Net: Convolutional Networks for Biomedical Image Segmentation\" By Olaf Ronneberger, Philipp Fischer, Thomas Brox, 2015\n- Residual connections (optional): He et al., 2016 (ResNet)\n\n### Features\n\n- **Connection type**: Choose between basic or residual connections.\n- **Network depth**: Configurable by setting the number of blocks.\n- **Initial filters**: Start from 64 (default) or any other value.\n- **Batch Normalization** and **Dropout** are optional.\n\nAll parameters are set in **config/config.yaml**, making it easy to experiment with different architectures.\n\n### Data Format\n\n- Training and test images: RGB JPEG images.\n- Masks: RGB PNG images, where each class is assigned a specific color.\n- Dataset listing:\n    - The list of training images must be stored in a text file, with each line containing the absolute path to an image.\n    - A separate text file should contain the absolute paths to the corresponding masks, one per line.\n    - The paths to the training and test sets must be specified in the **config/config.yaml** file.\n- Label Map:\n    - A JSON file defining the class mappings.\n    - The class with index 0 is the background.\n    - The path to this label map should be set in **config/config.yaml**.\n- Color Map:\n    - A JSON file defining the color of each class (for visualization purposes).\n    - The path to this label map should be set in **config/config.yaml**.\n\n### Requirements installation\n\nA GPU is required. Install dependencies with:\n```\npip install -r requirements.txt\n```\n### Usage\n\n- **Training:** Run \n```\npython src/train.py\n```\n- **Prediction:** To generate segmentations **from a checkpoint on a set of images**, run \n```\npython src/predict.py\n``` \nThe checkpoint's name and path should be set in **config/config.yaml**.\n\n### Monitoring Training with TensorBoard\n\n- Evaluation metrics and errors can be visualized during training using TensorBoard.\n- The logs directory path should be defined in **config/config.yaml**.\n- To launch TensorBoard, run:\n```\ntensorboard --logdir=\u003cyourlogdir\u003e\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsalwaelkaddaoui%2Funet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsalwaelkaddaoui%2Funet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsalwaelkaddaoui%2Funet/lists"}