Source added

README.md

@@ -1,12 +1,93 @@
+# 🏗️ YOLOv8 Object Detection App – Blueprint Door & Window Detector
+
+Welcome to my deployed computer vision project using **YOLOv8 + Gradio**, designed to detect **doors and windows** in architectural **construction blueprints**.
+
+![demo](https://github.com/ultralytics/assets/raw/main/yolov8/banner-yolov8.png)
+
+---
+
+## 🔍 About the App
+
+This application showcases a deep learning model trained on blueprint images to identify:
+- 🚪 **Doors**
+- 🪟 **Windows**
+
+The goal was to automate detection in architectural layouts and assist with digitizing or verifying blueprint components.
+
+---
+
+## 💡 How it Works
+
+- The app is powered by a **custom-trained YOLOv8** model.
+- You can **upload a blueprint image** via the Gradio interface.
+- The model will return:
+  - ✅ An **annotated image** showing detections
+  - ✅ A **JSON output** with detection details in this format:
+
+```json
+{
+  "detections": [
+    {"label": "door", "confidence": 0.91, "bbox": [x, y, w, h]},
+    {"label": "window", "confidence": 0.84, "bbox": [x, y, w, h]}
+  ]
+}
+```
+
 ---
-title: WinDoorDetection YOLO
-emoji: 📊
-colorFrom: green
-colorTo: blue
-sdk: gradio
-sdk_version: 5.31.0
-app_file: app.py
-pinned: false
+
+## 🚀 How to Use
+
+1. Upload a construction blueprint image.
+2. View the image with annotated bounding boxes.
+3. Review the detection results in JSON format.
+
+✅ Try it online: *(add your Hugging Face space URL here)*  
+✅ Or run it locally:
+
+```bash
+git clone https://huggingface.co/spaces/YOUR_USERNAME/yolov8-gradio-demo
+cd yolov8-gradio-demo
+pip install -r requirements.txt
+python app.py
+```
+
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+## 🧠 Tech Stack
+
+| Tool        | Purpose                              |
+|-------------|--------------------------------------|
+| YOLOv8      | Object detection                     |
+| Ultralytics | Model training & inference framework |
+| Gradio      | Web interface for inference          |
+| Hugging Face Spaces | App hosting platform         |
+
+---
+
+## 📦 Model Info
+
+- **Framework**: [Ultralytics YOLOv8](https://docs.ultralytics.com/)
+- **Trained On**: Custom blueprint dataset with annotated door and window classes
+- **Performance**: Optimized for fast inference on 2D plan layouts
+
+---
+
+## 🎯 Recruiter Notes
+
+This project demonstrates:
+- Custom model training and fine-tuning
+- Practical use of object detection in architecture
+- Real-world deployment using Hugging Face Spaces
+- Building user-friendly ML apps with Gradio
+
+---
+
+## 🙋‍♂️ Author
+
+**Your Name**  
+[GitHub](https://github.com/yourusername) | [LinkedIn](https://linkedin.com/in/yourprofile)
+
+---
+
+> ⭐ Feel free to connect with me to discuss AI in construction tech or computer vision applications!
+

Space.yaml

@@ -0,0 +1,3 @@
+sdk: gradio
+app_file: app.py
+python_version: 3.10

app.py

@@ -0,0 +1,37 @@
+import gradio as gr
+from ultralytics import YOLO
+from PIL import Image
+import numpy as np
+
+model = YOLO("model/my_model.pt")
+
+def detect_objects(image: Image.Image):
+    results = model(image)
+    im_bgr = results[0].plot()
+    im_rgb = Image.fromarray(im_bgr[..., ::-1])
+
+    detections = []
+    for box in results[0].boxes:
+        cls_id = int(box.cls[0])
+        label = model.names[cls_id]
+        conf = float(box.conf[0])
+        x1, y1, x2, y2 = box.xyxy[0].tolist()
+        w, h = x2 - x1, y2 - y1
+        detections.append({
+            "label": label,
+            "confidence": round(conf, 2),
+            "bbox": [round(x1, 2), round(y1, 2), round(w, 2), round(h, 2)]
+        })
+
+    return im_rgb, {"detections": detections}
+
+gr.Interface(
+    fn=detect_objects,
+    inputs=gr.Image(type="pil"),
+    outputs=[
+        gr.Image(type="pil", label="Detected Image"),
+        gr.JSON(label="Detection Results")
+    ],
+    title="YOLOv8 Object Detection",
+    description="Upload an image to detect objects using a YOLOv8 model."
+).launch()

requirements.txt

@@ -0,0 +1,3 @@
+gradio
+ultralytics
+pillow