Spaces:
Running
Running
Upload README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
title: SmartVision AI
|
| 3 |
+
emoji: π
|
| 4 |
+
colorFrom: blue
|
| 5 |
+
colorTo: green
|
| 6 |
+
sdk: docker
|
| 7 |
+
pinned: false
|
| 8 |
+
license: mit
|
| 9 |
+
app_port: 7860
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# π SmartVision: Advanced Object Detection & Classification
|
| 13 |
+
|
| 14 |
+
This project is an end-to-end Computer Vision pipeline designed for training and comparing multiple Deep Learning architectures (VGG16, ResNet50, MobileNetV2, EfficientNet) and real-time detection via YOLOv8.
|
| 15 |
+
|
| 16 |
+
## π Project Features
|
| 17 |
+
* **Multi-Model Comparison:** Dynamic leaderboard comparing accuracy and inference latency.
|
| 18 |
+
* **YOLOv8 Integration:** Real-time object detection on 25 COCO-subset classes.
|
| 19 |
+
* **Automated Pipeline:** Scripts for dataset generation, model training, and evaluation.
|
| 20 |
+
|
| 21 |
+
## π Directory Structure
|
| 22 |
+
* `app.py`: Main Streamlit interface.
|
| 23 |
+
* `models/`: Contains the trained `.h5` and `.pt` weights.
|
| 24 |
+
* `pages/`: Additional dashboard pages for performance analytics.
|
| 25 |
+
* `training/`: Specialized scripts for each architecture.
|
| 26 |
+
|
| 27 |
+
## π οΈ Local Setup
|
| 28 |
+
1. Clone the repository.
|
| 29 |
+
2. Install dependencies: `pip install -r requirements.txt`
|
| 30 |
+
3. Run the app: `streamlit run app.py`
|