This project uses a pre-trained MobileNetV2 model to classify images into the top 3 categories from the ImageNet dataset. The model is wrapped in a Gradio interface, making it easy to use and interact with. Simply upload an image, and the model will return the top 3 predicted labels along with their confidence scores.
Pre-trained Model: Utilizes MobileNetV2, a state-of-the-art convolutional neural network pre-trained on the ImageNet dataset. Gradio Interface: Provides a user-friendly web interface for image classification. Real-time Predictions: Upload an image and get instant predictions with confidence scores. Top 3 Predictions: Displays the top 3 categories the model predicts for the uploaded image.
You can try out the application live here: https://huggingface.co/spaces/keerthi-balaji/image-classification
Python 3.6 or higher TensorFlow Gradio Requests NumPy
- Clone the repository:
git clone https://github.com/your-username/image-classification-mobilenetv2.git
cd image-classification-mobilenetv2
- Create and activate a virtual environment (optional):
python -m venv venv
source venv/bin/activate # On Windows, use venv\Scripts\activate
- Install the required packages:
pip install -r requirements.txt
- Run the application:
python app.py
-
Open your web browser and go to the URL provided by Gradio (usually http://127.0.0.1:7860).
-
Upload an image to see the top 3 predicted labels along with their confidence scores.