DeepVision represents the pinnacle of image classification, leveraging state-of-the-art deep learning frameworks—TensorFlow and Keras—to deliver robust and accurate predictions. Built on the powerful MobileNetV2 architecture and trained on the renowned CIFAR-10 dataset, this project is engineered to classify a wide spectrum of objects efficiently.
- Deep Learning Excellence: Implements TensorFlow and Keras for scalable model deployment.
- Advanced Architecture: MobileNetV2 ensures a perfect balance between performance and speed.
- Diverse Dataset: Trained on 60,000 32x32 color images from the CIFAR-10 dataset, spanning 10 distinct classes.
- Customizable Training: Train over 5 epochs with adjustable hyperparameters to fine-tune performance.
- Comprehensive Evaluation: Track metrics like test accuracy and loss for precise performance insights.
- Python 3.x
- TensorFlow
- Matplotlib (optional for visualizations)
-
Clone the repository:
git clone https://github.com/niladridas/deepvision.git
-
Navigate to the project directory:
cd deepvision -
Install dependencies:
pip install -r requirements.txt
-
Run the classification script:
python src.py
-
Monitor training progress and review test accuracy and optional visualizations.
- Training Accuracy: ~75%
- Validation Accuracy: ~73%
- Test Accuracy: ~74%
This project is open-source and licensed under the MIT License.
- Heartfelt thanks to the incredible TensorFlow and Keras communities.
- CIFAR-10 dataset: Access Here
Contributions are welcome! If you have any suggestions, bug reports, or feature requests, please open an issue or submit a pull request. For major changes, please discuss them in an issue first to ensure they align with the project's goals.
- Fork the repository
- Create a new branch (
git checkout -b feature-branch) - Commit your changes (
git commit -m 'Add some feature') - Push to the branch (
git push origin feature-branch) - Open a pull request
🌟 Contributions are welcome! Feel free to report issues, suggest improvements, or fork the repository to take this project to the next level.