Shallow Convolutional Neural Network for Image Classification 🖼️🧠

This repository contains an implementation of a shallow convolutional neural network (CNN) used for image classification, demonstrating the model's ability to learn and predict from image data across different datasets like MNIST, Fashion-MNIST, and CIFAR-10.

Features 🌟

• Implements shallow CNN architectures for rapid training and inference.
• Includes dataset-specific preprocessing and normalization for MNIST, Fashion-MNIST, and CIFAR-10.
• Offers configurable training settings and model parameters.
• Provides visualization of training progress, accuracy metrics, and confusion matrices.

Setup and Installation 🛠️

1. Clone the repository.
2. Ensure Python and PyTorch are installed with the required version.
3. Set up a virtual environment and install dependencies from requirements.txt.

Datasets 📁

The implementation supports multiple datasets:

• MNIST: Handwritten digits.
• Fashion-MNIST: Clothing images.
• CIFAR-10: Various object images.

Training the Model 🚀

• Configure the training settings according to the dataset and desired hyperparameters.
• Execute the training script to train the model, save checkpoints, and log the training process.

Evaluation and Results 📊

• Evaluate the trained model using the test dataset to obtain metrics like accuracy, precision, and recall.
• View confusion matrices and classification reports to assess model performance.

Contributing 🤝

We welcome contributions to improve the project. Please follow the standard GitHub pull request process to suggest changes.

License 📜

This project is licensed under the MIT License. See the LICENSE file for more details.

Acknowledgements 🙌

• Dataset providers for MNIST, Fashion-MNIST, and CIFAR-10.
• PyTorch team for providing a comprehensive deep learning framework.

For more details, please visit the project repository.