{"id":24576102,"url":"https://github.com/arpanpramanik2003/object-detection-resnet50","last_synced_at":"2026-04-07T23:31:16.149Z","repository":{"id":273537566,"uuid":"919350120","full_name":"arpanpramanik2003/object-detection-resnet50","owner":"arpanpramanik2003","description":"This repository contains a deep learning project for CIFAR-10 image classification using the ResNet50 pre-trained model. The project includes data preprocessing, model training, evaluation, and visualization of results. Achieved high accuracy by fine-tuning the model and optimizing hyperparameters.","archived":false,"fork":false,"pushed_at":"2025-03-11T18:14:24.000Z","size":197,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-03-11T19:27:03.839Z","etag":null,"topics":["cifar-10","cifar10","cnn","deep-learning","keras","machine-learning","model-evaluation","object-detection","opencv","pre-trained-model","python","regression-models","resnet-50","streamlit","tensorflow2","transformer-models"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/arpanpramanik2003.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":"2025-01-20T08:27:52.000Z","updated_at":"2025-03-11T18:14:20.000Z","dependencies_parsed_at":"2025-01-21T14:29:12.331Z","dependency_job_id":"a26b77f5-e11e-4b85-af59-a39172fe84e3","html_url":"https://github.com/arpanpramanik2003/object-detection-resnet50","commit_stats":null,"previous_names":["arpanpramanik2003/object-detection-resnet50"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/arpanpramanik2003/object-detection-resnet50","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/arpanpramanik2003%2Fobject-detection-resnet50","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/arpanpramanik2003%2Fobject-detection-resnet50/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/arpanpramanik2003%2Fobject-detection-resnet50/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/arpanpramanik2003%2Fobject-detection-resnet50/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/arpanpramanik2003","download_url":"https://codeload.github.com/arpanpramanik2003/object-detection-resnet50/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/arpanpramanik2003%2Fobject-detection-resnet50/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31533823,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-07T16:28:08.000Z","status":"ssl_error","status_checked_at":"2026-04-07T16:28:06.951Z","response_time":105,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["cifar-10","cifar10","cnn","deep-learning","keras","machine-learning","model-evaluation","object-detection","opencv","pre-trained-model","python","regression-models","resnet-50","streamlit","tensorflow2","transformer-models"],"created_at":"2025-01-23T22:21:28.000Z","updated_at":"2026-04-07T23:31:16.126Z","avatar_url":"https://github.com/arpanpramanik2003.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# CIFAR-10 Image Classification using ResNet50\n\n## Introduction\nThis project focuses on classifying images from the CIFAR-10 dataset using a deep learning model based on the ResNet50 architecture. The CIFAR-10 dataset consists of 50,000 32x32 color images in 10 different classes, with 5,000 images per class. Leveraging the power of the pre-trained ResNet50 model, the project aims to achieve high accuracy through transfer learning.\n\n## Project Overview\nThe steps involved in the project are as follows:\n\n1. **Dataset Preparation**\n   - Download the CIFAR-10 dataset using Kaggle API.\n   - Extract the dataset and perform necessary preprocessing.\n   - Apply One-Hot Encoding to the labels.\n\n2. **Data Preprocessing**\n   - Load image data and convert them into numpy arrays.\n   - Normalize pixel values by scaling them to the range [0,1].\n   - Split the dataset into training and testing sets.\n\n3. **Model Development**\n   - Utilize the ResNet50 pre-trained model with `imagenet` weights.\n   - Add additional layers such as upsampling, dense, dropout, and batch normalization.\n   - Compile the model using RMSprop optimizer and categorical crossentropy loss function.\n\n4. **Model Training and Evaluation**\n   - Train the model with the training dataset and validate using a validation split.\n   - Evaluate model performance using accuracy and loss metrics.\n\n5. **Results Visualization**\n   - Plot training vs validation loss.\n   - Plot training vs validation accuracy.\n\n## Requirements\nTo run this project, you need the following dependencies:\n\n```bash\npip install numpy pandas matplotlib tensorflow keras opencv-python PIL scikit-learn kaggle\n```\n\n## Execution Steps\n1. Ensure you have the `kaggle.json` file configured to download the dataset.\n2. Run the Python script to download, preprocess, train, and evaluate the model.\n3. Observe the evaluation results and plots to analyze model performance.\n\n## Model Performance\nThe model achieved a good test accuracy, showing the effectiveness of transfer learning using ResNet50. Further improvements can be made by tuning hyperparameters and using data augmentation techniques.\n\n## Conclusion\nThis project demonstrates the application of deep learning for image classification using pre-trained models. ResNet50, with its powerful feature extraction capabilities, enhances the classification accuracy, making it suitable for practical applications.\n\n## Author\nArpan Pramanik\n\n## Acknowledgments\n- Kaggle for the CIFAR-10 dataset.\n- TensorFlow and Keras libraries for deep learning implementation.\n\n## License\nThis project is licensed under the Apache License.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Farpanpramanik2003%2Fobject-detection-resnet50","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Farpanpramanik2003%2Fobject-detection-resnet50","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Farpanpramanik2003%2Fobject-detection-resnet50/lists"}