Upload 3 files

README.md

@@ -1,12 +1,41 @@
----
-title: Ai
-emoji: 🏆
-colorFrom: red
-colorTo: yellow
-sdk: gradio
-sdk_version: 5.36.2
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+# 🤖 Netrava UI Detection
+
+This Hugging Face Space hosts the Netrava AI Assistant's UI detection model.
+
+## Usage
+
+1. Upload a screenshot
+2. The model will detect and highlight UI elements
+3. Download the annotated image
+
+## Supported Elements
+
+- Buttons
+- Text boxes
+- Dropdowns
+- Checkboxes
+- Icons
+- Menus
+- Windows
+- Dialogs
+- Links
+- Images
+- Labels
+- Tabs
+- Toolbars
+- Status bars
+- Scroll bars
+
+## API Usage
+
+You can also use this space via API:
+
+```python
+import requests
+
+response = requests.post(
+    "https://your-username-netrava-ui-detection.hf.space/api/predict",
+    files={"data": open("screenshot.png", "rb")}
+)
+```

app.py

@@ -1,58 +1,58 @@
-
-import gradio as gr
-import torch
-from ultralytics import YOLO
-import cv2
-import numpy as np
-from PIL import Image
-
-# Load model
-model = YOLO('netrava_ui_model.pt')
-
-def detect_ui_elements(image):
-    """Detect UI elements in uploaded image"""
-    try:
-        # Convert PIL to OpenCV format
-        img_array = np.array(image)
-        img_bgr = cv2.cvtColor(img_array, cv2.COLOR_RGB2BGR)
-        
-        # Run detection
-        results = model(img_bgr)
-        
-        # Draw results
-        for result in results:
-            boxes = result.boxes
-            if boxes is not None:
-                for box in boxes:
-                    # Get coordinates
-                    x1, y1, x2, y2 = box.xyxy[0].cpu().numpy()
-                    conf = box.conf[0].cpu().numpy()
-                    cls = int(box.cls[0].cpu().numpy())
-                    
-                    # Draw bounding box
-                    cv2.rectangle(img_bgr, (int(x1), int(y1)), (int(x2), int(y2)), (0, 255, 0), 2)
-                    
-                    # Add label
-                    label = f'{model.names[cls]}: {conf:.2f}'
-                    cv2.putText(img_bgr, label, (int(x1), int(y1)-10), 
-                               cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 1)
-        
-        # Convert back to RGB
-        result_img = cv2.cvtColor(img_bgr, cv2.COLOR_BGR2RGB)
-        return Image.fromarray(result_img)
-        
-    except Exception as e:
-        return f"Error: {str(e)}"
-
-# Create Gradio interface
-interface = gr.Interface(
-    fn=detect_ui_elements,
-    inputs=gr.Image(type="pil"),
-    outputs=gr.Image(type="pil"),
-    title="🤖 Netrava UI Element Detection",
-    description="Upload a screenshot to detect UI elements like buttons, textboxes, etc.",
-    examples=["example1.png", "example2.png"]
-)
-
-if __name__ == "__main__":
-    interface.launch()
+
+import gradio as gr
+import torch
+from ultralytics import YOLO
+import cv2
+import numpy as np
+from PIL import Image
+
+# Load model
+model = YOLO('netrava_ui_model.pt')
+
+def detect_ui_elements(image):
+    """Detect UI elements in uploaded image"""
+    try:
+        # Convert PIL to OpenCV format
+        img_array = np.array(image)
+        img_bgr = cv2.cvtColor(img_array, cv2.COLOR_RGB2BGR)
+        
+        # Run detection
+        results = model(img_bgr)
+        
+        # Draw results
+        for result in results:
+            boxes = result.boxes
+            if boxes is not None:
+                for box in boxes:
+                    # Get coordinates
+                    x1, y1, x2, y2 = box.xyxy[0].cpu().numpy()
+                    conf = box.conf[0].cpu().numpy()
+                    cls = int(box.cls[0].cpu().numpy())
+                    
+                    # Draw bounding box
+                    cv2.rectangle(img_bgr, (int(x1), int(y1)), (int(x2), int(y2)), (0, 255, 0), 2)
+                    
+                    # Add label
+                    label = f'{model.names[cls]}: {conf:.2f}'
+                    cv2.putText(img_bgr, label, (int(x1), int(y1)-10), 
+                               cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 1)
+        
+        # Convert back to RGB
+        result_img = cv2.cvtColor(img_bgr, cv2.COLOR_BGR2RGB)
+        return Image.fromarray(result_img)
+        
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+# Create Gradio interface
+interface = gr.Interface(
+    fn=detect_ui_elements,
+    inputs=gr.Image(type="pil"),
+    outputs=gr.Image(type="pil"),
+    title="🤖 Netrava UI Element Detection",
+    description="Upload a screenshot to detect UI elements like buttons, textboxes, etc.",
+    examples=["example1.png", "example2.png"]
+)
+
+if __name__ == "__main__":
+    interface.launch()

requirements.txt

@@ -0,0 +1,7 @@
+
+ultralytics
+torch
+torchvision
+opencv-python
+Pillow
+gradio