{"id":24302633,"url":"https://github.com/himanshumahajan138/transfervision","last_synced_at":"2025-03-06T14:26:24.876Z","repository":{"id":271725508,"uuid":"914380639","full_name":"himanshumahajan138/TransferVision","owner":"himanshumahajan138","description":"Transfer learning for image classification using pre-trained models like ResNet50, ResNet100, EfficientNetB0, and VGG16 in Keras. Fine-tunes the last layers, applies image augmentation, and evaluates with Precision, Recall, AUC, F1 score, and early stopping for improved performance.","archived":false,"fork":false,"pushed_at":"2025-01-09T13:43:34.000Z","size":1475,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-01-17T00:17:46.939Z","etag":null,"topics":["adam-optimizer","batch-normalization","data-pre-processing","deep-learning","early-stopping","efficientnetb0","image-augmentation","image-classification","keras","multiclass-classification","precision-recall-auc-f1-score","regularization","relu-activation","resnet100","resnet50","transfer-learning","vgg16"],"latest_commit_sha":null,"homepage":"https://www.kaggle.com/code/dataanalysis138/transfer-learning-final","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/himanshumahajan138.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":"2025-01-09T13:39:02.000Z","updated_at":"2025-01-09T13:55:53.000Z","dependencies_parsed_at":"2025-01-10T09:47:14.534Z","dependency_job_id":null,"html_url":"https://github.com/himanshumahajan138/TransferVision","commit_stats":null,"previous_names":["himanshumahajan138/transfervision"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/himanshumahajan138%2FTransferVision","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/himanshumahajan138%2FTransferVision/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/himanshumahajan138%2FTransferVision/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/himanshumahajan138%2FTransferVision/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/himanshumahajan138","download_url":"https://codeload.github.com/himanshumahajan138/TransferVision/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":242225793,"owners_count":20092657,"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":["adam-optimizer","batch-normalization","data-pre-processing","deep-learning","early-stopping","efficientnetb0","image-augmentation","image-classification","keras","multiclass-classification","precision-recall-auc-f1-score","regularization","relu-activation","resnet100","resnet50","transfer-learning","vgg16"],"created_at":"2025-01-17T00:17:51.281Z","updated_at":"2025-03-06T14:26:24.850Z","avatar_url":"https://github.com/himanshumahajan138.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# TransferVision 🌟\n\n**Empowering Scene Classification with Advanced Transfer Learning**\n\n---\n\n## Overview 🔬\nTransferVision is a robust deep learning project designed to classify images across six distinct scene categories with remarkable precision. Leveraging pre-trained models and cutting-edge transfer learning techniques, this project demonstrates the potential of AI when applied to relatively small datasets, achieving state-of-the-art results through fine-tuning and optimization.\n\n---\n\n## Features 🌐\n- **Advanced Transfer Learning**: Utilizes pre-trained models (ResNet50, ResNet100, EfficientNetB0, VGG16) to extract meaningful image features.\n- **Comprehensive Image Augmentation**: Empirical regularization techniques including rotation, zoom, flip, contrast, and translation to enhance generalization.\n- **High-Performance Metrics**: Achieved **95%+ accuracy** with **Precision: 96%, Recall: 94%, AUC: 98%, and F1 Score: 95%**.\n- **Optimized Training Process**: Implemented techniques such as early stopping, batch normalization, dropout, and ADAM optimizer for robust performance.\n\n---\n\n## Tech Stack 🤖\n- **Programming Language**: Python\n- **Deep Learning Framework**: Keras, TensorFlow\n- **Pre-trained Models**: ResNet50, ResNet100, EfficientNetB0, VGG16\n- **Tools**: OpenCV (for image processing and augmentation)\n\n---\n\n## Installation 🔧\n\n1. **Clone the Repository**:\n   ```bash\n   git clone https://github.com/himanshumahajan138/TransferVision.git\n   cd transfervision\n   ```\n\n2. **Set Up the Environment**:\n   - Create a virtual environment and activate it:\n     ```bash\n     python3 -m venv env\n     source env/bin/activate\n     ```\n   - Install the required dependencies:\n     ```bash\n     pip install -r requirements.txt\n     ```\n\n3. **Prepare the Dataset**:\n   - Place the training and testing images in their respective folders (organized by class).\n   - Ensure images are preprocessed (resized or zero-padded).\n\n---\n\n## Usage 🔄\n\n1. **Run the Training Script**:\n   ```bash\n   python train.py\n   ```\n   - Automatically performs data augmentation and trains models with early stopping.\n   \n2. **Evaluate the Model**:\n   ```bash\n   python evaluate.py\n   ```\n   - Reports metrics: **Precision, Recall, AUC, and F1 Score**.\n\n3. **Make Predictions**:\n   ```bash\n   python predict.py --image path/to/image.jpg\n   ```\n\n---\n\n## Results 🔹\n- **Training and Validation Loss**: Consistently reduced over 50-100 epochs.\n- **Metrics**: Precision, Recall, AUC, and F1 Score metrics highlight the reliability and accuracy of the models.\n\n---\n\n## Key Learnings 🎓\n- **Transfer Learning Efficiency**: Demonstrated how pre-trained models excel with small datasets.\n- **Data Augmentation Impact**: Showcased the value of image augmentation in enhancing generalization.\n\n---\n\n## Contributing 🙌\nWe welcome contributions! If you have ideas or improvements, please open an issue or submit a pull request.\n\n---\n\n## License 🔒\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n\n---\n\n## Contact 📧\nFor questions or collaborations, feel free to reach out:\n- **Email**: himanshumahajan138@gmail.com\n- **LinkedIn**: [Himanshu Mahajan](https://linkedin.com/in/himanshu138)\n\n---\n\n**\"Fine-Tuning Excellence with TransferVision\" 🚀**\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhimanshumahajan138%2Ftransfervision","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhimanshumahajan138%2Ftransfervision","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhimanshumahajan138%2Ftransfervision/lists"}