{"id":24605609,"url":"https://github.com/ramanks19/capstone-project-aiml","last_synced_at":"2025-09-08T16:47:57.544Z","repository":{"id":154104300,"uuid":"364291609","full_name":"ramanks19/Capstone-Project-AIML","owner":"ramanks19","description":"This project was done as part of Capstone Project for PGP in Artificial Intelligence and Machine Learning by Great Learning ","archived":false,"fork":false,"pushed_at":"2021-05-04T15:51:54.000Z","size":3695,"stargazers_count":6,"open_issues_count":0,"forks_count":2,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-06-03T14:51:51.928Z","etag":null,"topics":["capstone-project","computer-vision","eda","greatlearning","mobilenet","pneumonia-detection","resnet-50","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/ramanks19.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,"zenodo":null}},"created_at":"2021-05-04T14:54:13.000Z","updated_at":"2025-03-25T23:07:53.000Z","dependencies_parsed_at":null,"dependency_job_id":"b5700448-c223-4350-bea0-bdfc9c8125d7","html_url":"https://github.com/ramanks19/Capstone-Project-AIML","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ramanks19/Capstone-Project-AIML","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ramanks19%2FCapstone-Project-AIML","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ramanks19%2FCapstone-Project-AIML/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ramanks19%2FCapstone-Project-AIML/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ramanks19%2FCapstone-Project-AIML/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ramanks19","download_url":"https://codeload.github.com/ramanks19/Capstone-Project-AIML/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ramanks19%2FCapstone-Project-AIML/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":274218054,"owners_count":25243357,"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":"2025-09-08T02:00:09.813Z","response_time":121,"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":["capstone-project","computer-vision","eda","greatlearning","mobilenet","pneumonia-detection","resnet-50","unet"],"created_at":"2025-01-24T16:18:09.827Z","updated_at":"2025-09-08T16:47:57.530Z","avatar_url":"https://github.com/ramanks19.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Capstone-Project-AIML\nThis project was done as part of Capstone Project for PGP in Artificial Intelligence and Machine Learning by Great Learning \n\n## 📁 Getting Started\nThe project is built on Google Colab Jupyter Notebook and Kaggle. \n\n## 🤔 Problem Description\nIn this capstone project, the goal is to build a Pneumonia Detection System, to locate the position of inflammation in an image. In all, the project objective can be described as:\n* Build a reliable Pneumonia Detection Model which can have a robust backing.\n* Proper pre-processing and meaningful Exploratory Data Analysis.\n* The medical images dataset can be properly trained by a deep learning network with custom architectures\n* Use transfer learning to facilitate training with final layers of the deep network trainable\n* Learn to fine tune the model by trying different optimizers, loss functions, epochs, learning rate, batch size, check pointing, early stopping etc.\n* Read different research papers of given domain to obtain the knowledge of advanced models for the given problem.\n* Advocate a strong backing case for the reliability of the model finally obtained by proposing a use case confidence interval.\n\n## 📜 Approach\n### 📈 Step 1: Exploratory Data Analysis \u0026 Data Preparation\n* Understanding the data with a brief on train/test labels and respective class info\n* Look at the first five rows of both the csvs (train and test)\n* Identify how are classes and target distributed\n* Check the number of patients with 1, 2, ... bounding boxes\n* Read and extract metadata from dicom files\n* Perform analysis on some of the features from dicom files\n* Check some random images from the training dataset\n* Draw insights from the data at various stages of EDA\n* Visualize some random masks generated\n\n**Outcome**\n* [Jupyter Notebook Link](https://github.com/ramanks19/Capstone-Project-AIML/blob/main/Pneumonia_Detection%20-%20EDA%20and%20Data%20Prep.ipynb) containing the exploration steps.\n\n### ⚙️ Step 2: Model Building\n* Split the data\n* Use different models to train the data. Here we are using UNet to train our dataset with different backbone structures\n* Evaluate the models (ROC AUC, AP, F1 Score)\n\n**Outcome**\n* [Classification - Jupyter Notebook Link](https://github.com/ramanks19/Capstone-Project-AIML/blob/main/Pneumonia%20Detection%20-%20Classification%20and%20Localization.ipynb) with the UNet architecture with pretrained ImageNet weights. Evaluating the model on average precision, accuracy and ROC AUC.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Framanks19%2Fcapstone-project-aiml","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Framanks19%2Fcapstone-project-aiml","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Framanks19%2Fcapstone-project-aiml/lists"}