|
|
--- |
|
|
title: solar wind fault detection Ver2 |
|
|
emoji: 🐠 |
|
|
colorFrom: indigo |
|
|
colorTo: green |
|
|
sdk: streamlit |
|
|
sdk_version: 1.45.0 |
|
|
app_file: app.py |
|
|
pinned: false |
|
|
license: apache-2.0 |
|
|
--- |
|
|
|
|
|
# Thermal Anomaly Monitoring Dashboard |
|
|
|
|
|
A dashboard for real-time fault detection in solar panels and windmill turbines using drone or CCTV footage. Built with Streamlit and YOLOv5, deployed on Hugging Face Spaces. |
|
|
|
|
|
## Features |
|
|
- Live video feed with fault detection (bounding boxes and labels). |
|
|
- Live logs, metrics, and anomaly trends. |
|
|
- Predictive anomaly detection based on trends. |
|
|
- Videos stored in the `data` folder. |
|
|
|
|
|
## Setup |
|
|
1. Place `.mp4` videos in the `data` folder. |
|
|
2. Install dependencies: `pip install -r requirements.txt`. |
|
|
3. Run the app: `streamlit run app.py`. |
|
|
4. Deploy on Hugging Face Spaces. |
|
|
|
|
|
## Notes |
|
|
- Fine-tune YOLOv5 models for accurate fault detection. |
|
|
- Update class IDs in `detection_service.py` based on your model. |
|
|
|
|
|
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference |
