Implementation of ML Model for Image Classification

This project is a simple and interactive Streamlit app that allows users to classify images using two pre-trained models: MobileNetV2 and a custom CIFAR-10 model. Users can upload images and get predictions with confidence scores, making it both educational and practical.

---

Key Features

1. Dual Model Support

• MobileNetV2 (ImageNet): A powerful model trained on the ImageNet dataset to recognize 1,000 different classes, such as animals, objects, and vehicles.
• Custom CIFAR-10 Model: Focuses on classifying images into 10 specific categories like airplanes, cars, and birds.

2. User-Friendly Interface

• Navigation Bar: Easily switch between models using a sidebar menu.
• Real-Time Results: Upload an image, and the app instantly displays predictions with confidence scores.

3. Perfect for Learning

• Great for understanding how deep learning models work.
• Can be used for hands-on exploration of image classification.

---

How to Use

1. Clone this repository to your local machine:

   git clone https://github.com/UJESH2K/AICTE---p1.git

2. Navigate to the project folder:

   cd Implementation-of-ML-model-for-image-classification

3. Install the required Python packages:

   pip install -r requirements.txt

4. Run the app:

   streamlit run app.py

5. Open the app in your browser (Streamlit will provide a link).

---

Technologies Used

• Python
• Streamlit: For creating the user interface.
• TensorFlow/Keras: For deep learning models.
• MobileNetV2: Pre-trained model on ImageNet.
• CIFAR-10 Model: Custom-trained for this project.

---

Acknowledgments

• Streamlit Docs: For guidance on building apps.
• TensorFlow: For providing the pre-trained MobileNetV2 model.
• CIFAR-10 Dataset: For the custom model training.

---

Feel free to share feedback or contribute to improve this project! 😊

---