README.md

metadata

title: ImageNet1k
emoji: 🚀 🌟
colorFrom: red
colorTo: gray
sdk: gradio
sdk_version: 5.9.1
app_file: app.py
pinned: false

ImageNet1k Classification Demo

This is a Gradio web application that demonstrates image classification using a ResNet50 model trained on the ImageNet1k dataset. The model can classify images into 1000 different categories.

Features

• Upload and classify any image
• Get top 5 predictions with confidence scores
• Real-time inference
• User-friendly interface
• Example images included

Technical Details

Model Architecture

• Base Model: ResNet50
• Training Dataset: ImageNet1k (1000 classes)
• Input Size: 224x224 pixels
• Preprocessing: Standard ImageNet normalization (mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])

Dependencies

• gradio: Web interface framework
• torch: PyTorch deep learning framework
• torchvision: Computer vision utilities
• Pillow: Image processing

Usage

1. Upload an image using the interface
2. The model will process the image and return:
   • Top 5 predicted classes
   • Confidence scores for each prediction

Tips for Best Results

• Use clear, well-lit images
• Ensure the main subject is centered and clearly visible
• The model works best with common objects, animals, and scenes
• Both color and black & white images are supported
• Images will be automatically resized to 224x224

Local Setup

1. Clone the repository
2. Install dependencies:

   pip install -r requirements.txt
   

3. Place your trained model weights as model_best.pth.tar in the root directory
4. Run the application:

   python app.py
   

Model Weights

The model weights (model_best.pth.tar) should be placed in the same directory as app.py. The weights file contains a ResNet50 model trained on ImageNet1k.

Links

• GitHub Repository
• Hugging Face Space