{"id":23248317,"url":"https://github.com/hawmex/aut_ai_project","last_synced_at":"2026-04-30T09:38:52.809Z","repository":{"id":103175375,"uuid":"584323849","full_name":"Hawmex/aut_ai_project","owner":"Hawmex","description":"This repository contains the files of my project for the \"Artificial Intelligence\" course at AUT (Tehran Polytechnic).","archived":false,"fork":false,"pushed_at":"2024-03-28T10:59:13.000Z","size":9993,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-06T01:15:49.294Z","etag":null,"topics":["classification","cnn","computer-vision","machine-learning","python"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/Hawmex.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}},"created_at":"2023-01-02T08:30:18.000Z","updated_at":"2024-03-28T10:56:06.000Z","dependencies_parsed_at":null,"dependency_job_id":"76727e5c-c0e6-43dd-ab7e-0203fa962e8c","html_url":"https://github.com/Hawmex/aut_ai_project","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Hawmex/aut_ai_project","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Hawmex%2Faut_ai_project","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Hawmex%2Faut_ai_project/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Hawmex%2Faut_ai_project/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Hawmex%2Faut_ai_project/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Hawmex","download_url":"https://codeload.github.com/Hawmex/aut_ai_project/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Hawmex%2Faut_ai_project/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32460781,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-29T22:27:22.272Z","status":"online","status_checked_at":"2026-04-30T02:00:05.929Z","response_time":57,"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":["classification","cnn","computer-vision","machine-learning","python"],"created_at":"2024-12-19T08:13:24.232Z","updated_at":"2026-04-30T09:38:52.793Z","avatar_url":"https://github.com/Hawmex.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Defective Pump Impeller Detection Using a CNN\n\nThis repository contains the files of my project for the \"Artificial\nIntelligence\" course at Amirkabir University of Technology (Tehran Polytechnic).\n\n## Project Description\n\nThis project deals with a classification problem. Since we are trying to\nclassify images, we have decided to solve it with a convolutional neural network\ndue to its abilities in image processing.\n\n## Dataset\n\nThe data we used are available on\n[Kaggle](https://www.kaggle.com/ravirajsinh45/real-life-industrial-dataset-of-casting-product).\n\n### Examples\n\n#### Defective Pump Impeller\n\n![Defective Pump Impeller](./screenshots/defective_pump_impeller.png)\n\n#### Non-Defective Pump Impeller\n\n![Non-Defective Pump Impeller](./screenshots/non_defective_pump_impeller.png)\n\n## The Convolutional Neural Network\n\nWe created a CNN with the following architecture:\n\n- `Conv2D`: 64x64x8\n- `MaxPool`: 32x32x8\n- `Conv2D` 32x32x8\n- `MaxPool`: 16x16x8\n- `Flatten`: 2048\n- `Dense`: 16\n- `Dense`: 16\n- `Dense`: 1\n\nTotal params: 33,737\n\n![The Convolutional Neural Network](./screenshots/model.png)\n\n## Training and Validation\n\n### Accuracy\n\nWe used `binary_accuracy` as the performance metric of the network.\n\n![Accuracy](./screenshots/accuracies.png)\n\n### Loss\n\nWe used `binary_crossentropy` as the loss function of the network.\n\n![Loss](./screenshots/losses.png)\n\n## Results\n\nOur CNN model can classify images of pump impeller with an accuracy of **~96%**.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhawmex%2Faut_ai_project","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhawmex%2Faut_ai_project","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhawmex%2Faut_ai_project/lists"}