{"id":17894094,"url":"https://github.com/blainerothrock/airbus-ship-detection","last_synced_at":"2025-04-03T04:25:51.288Z","repository":{"id":97095111,"uuid":"244685792","full_name":"blainerothrock/airbus-ship-detection","owner":"blainerothrock","description":null,"archived":false,"fork":false,"pushed_at":"2020-03-16T21:45:37.000Z","size":61713,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-02-08T18:30:45.659Z","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/blainerothrock.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":"2020-03-03T16:26:49.000Z","updated_at":"2020-03-16T21:45:39.000Z","dependencies_parsed_at":null,"dependency_job_id":"5055e5ba-9b99-4667-b837-9e371914ebe3","html_url":"https://github.com/blainerothrock/airbus-ship-detection","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/blainerothrock%2Fairbus-ship-detection","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/blainerothrock%2Fairbus-ship-detection/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/blainerothrock%2Fairbus-ship-detection/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/blainerothrock%2Fairbus-ship-detection/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/blainerothrock","download_url":"https://codeload.github.com/blainerothrock/airbus-ship-detection/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246935513,"owners_count":20857437,"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":[],"created_at":"2024-10-28T15:00:00.836Z","updated_at":"2025-04-03T04:25:51.264Z","avatar_url":"https://github.com/blainerothrock.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Airbus Ship Detection\n\nEE 435: Deep Learning Foundations from Scratch \\\nNorthwestern Univertiy Winter 2020\n\n## Memebers\n* Blaine Rothrock\n* Ilan Ponsky\n* Will Dong\n\n## Overview\n\nOur group is interested in applying knowledge from this course to training TensorFlow models and getting a better understanding of deep artificial neural networks involved in image processing. In order to learn about this process in an organized and efficient way, we utilized a closed Kaggle competition that centered around our topic of image processing with neural networks. The competition we used was the [Airbus Ship Detection Challenge](https://www.kaggle.com/c/airbus-ship-detection). The goal of the Kaggle competition was for participants to be able to build a model that could “detect all ships in satellite images as quickly as possible.”\n\nThe specific goals we wanted to hit for our Deep Learning from Scratch final project were to: \n* Build a binary classifier model to gain a basic understanding of Tensorflow and how to build models in TensorFlow.\n    - The objective of the binary classifier model is to output whether an image contained a ship or not utilizing optimization techniques in TensorFlow.\n* Explore and implement a U-net model for image segmentation. \n    - U-Net models are the current state-of-art for image segmentation and where most started for this competition.\n    - This is a hefty goal given the data size of ~40GB of images and the time it takes to training this complex model. Our goal is to build a model, attempt at training, and gain a understanding of the U-Net architecture.\n    - To accomplish this, we utilized the notebook of Kevin Mader on Kaggle which served as an excellent foundation to get started with implementing the mentioned goals\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fblainerothrock%2Fairbus-ship-detection","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fblainerothrock%2Fairbus-ship-detection","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fblainerothrock%2Fairbus-ship-detection/lists"}