{"id":16271880,"url":"https://github.com/mukel/epfml17-segmentation","last_synced_at":"2025-08-22T08:13:42.650Z","repository":{"id":78353865,"uuid":"110259584","full_name":"mukel/epfml17-segmentation","owner":"mukel","description":"Project 2: Road extraction from satellite images","archived":false,"fork":false,"pushed_at":"2017-12-21T21:53:40.000Z","size":153323,"stargazers_count":3,"open_issues_count":0,"forks_count":3,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-04-05T19:34:19.716Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/mukel.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}},"created_at":"2017-11-10T15:04:02.000Z","updated_at":"2022-05-30T14:57:42.000Z","dependencies_parsed_at":"2023-04-28T12:03:50.188Z","dependency_job_id":null,"html_url":"https://github.com/mukel/epfml17-segmentation","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/mukel/epfml17-segmentation","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mukel%2Fepfml17-segmentation","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mukel%2Fepfml17-segmentation/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mukel%2Fepfml17-segmentation/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mukel%2Fepfml17-segmentation/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mukel","download_url":"https://codeload.github.com/mukel/epfml17-segmentation/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mukel%2Fepfml17-segmentation/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":271606595,"owners_count":24788979,"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","status":"online","status_checked_at":"2025-08-22T02:00:08.480Z","response_time":65,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":[],"created_at":"2024-10-10T18:15:05.344Z","updated_at":"2025-08-22T08:13:37.627Z","avatar_url":"https://github.com/mukel.png","language":"Jupyter Notebook","readme":"# EPFL Machine Learning Project 2: Road extraction from satellite images\n\n![landing_image](https://user-images.githubusercontent.com/1896283/34275777-066951f2-e69f-11e7-80a2-1151fcf8b63b.png)\n\n## Team: Chronic Machinelearnism\n\n## Code architecture\nThe code consists of two Python (**3**) files:\n* `run.py` : The ML pipeline. Fits the model and outputs the predictions for the submission dataset (submission_test.csv).\n* `helpers.py` : Definition of all the auxiliary methods (e.g. image manipulation).\n\n## External Dependencies\nKeras (\u003e= 2.0.9) + TensorFlow backend, OpenCV and imutils.\nInstall dependencies using pip:\n`pip install imutils opencv-python keras tensorflow-gpu`\n\n## Running\nThe user simply needs to **Python3-execute** the run.py file.\n\n*Note: All the above mentioned .py files needs to be in the same folder. This folder needs to contain a subfolder called 'data' with the training and submission folders \"extracted as is\" from Kaggle.*\n\n*Note: Running the code requires quite some memory. Having (at least) 40GB of RAM is highly recommended.*\n\n## Running time.\nThe model was trained on a single p2.8xlarge (AWS) instance in around 1 hour. On a laptop we expect the training time to be around 72 hours. We ran our run.py with all training data in multi-gpu mode (disabled on the deliverable). The data augmentation is very memory hungry, taking a considerable amount of memory; at least 128GB of RAM are required to train the model with the full dataset.\n\n## Authors\nAimee Montero, Alfonso Peterssen, Philipp Chervet  \n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmukel%2Fepfml17-segmentation","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmukel%2Fepfml17-segmentation","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmukel%2Fepfml17-segmentation/lists"}