|
|
--- |
|
|
title: HW3 PART2 Image Identification |
|
|
emoji: 📚 |
|
|
colorFrom: red |
|
|
colorTo: blue |
|
|
sdk: gradio |
|
|
sdk_version: 5.47.2 |
|
|
app_file: app.py |
|
|
pinned: false |
|
|
license: mit |
|
|
short_description: Stop Sign Image Identification |
|
|
--- |
|
|
|
|
|
# Stop Sign Image Classifier |
|
|
|
|
|
**Author:** Your Name |
|
|
**Course:** 24679 - Designing and Deploying AI/ML Systems |
|
|
|
|
|
This app classifies traffic images into two categories using an AutoGluon-trained model: |
|
|
- **0 = Not a Stop Sign** |
|
|
- **1 = Stop Sign** |
|
|
|
|
|
The interface allows you to upload or drag-and-drop an image of a road scene. The model outputs the predicted class along with probability scores. |
|
|
|
|
|
--- |
|
|
|
|
|
## How to Use |
|
|
1. Upload an image (JPG/PNG). |
|
|
2. Click **Submit** to run the classifier. |
|
|
3. View the predicted label (`0` or `1`) and the probability distribution. |
|
|
|
|
|
--- |
|
|
|
|
|
## Deployment Details |
|
|
- **Frameworks:** [AutoGluon Image](https://auto.gluon.ai/stable/tutorials/image_prediction/index.html), [Gradio](https://gradio.app/) |
|
|
- **Hosting:** Hugging Face Spaces |
|
|
- **Model Loading:** Model is downloaded from the Hugging Face Hub and automatically unpacked on startup. |
|
|
|
|
|
--- |
|
|
|
|
|
## Requirements |
|
|
Dependencies are listed in `requirements.txt`. |
|
|
|
|
|
--- |
|
|
|
|
|
## Acknowledgments |
|
|
- Model trained by a classmate in Homework 2 |
|
|
- Deployment scaffold and documentation supported with AI assistance (ChatGPT, OpenAI) |
|
|
- Reference: Class-provided notebook *image gradio.ipynb* |
|
|
|
|
|
|
|
|
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference |
|
|
|
