Update app.py

app.py

@@ -1,21 +1,7 @@
 # !pip install timm
 # !pip install transformers
 # !pip install pillow
-from PIL import Image 
-import gradio as gr
-
-# Use a pipeline as a high-level helper
-
-
-# object_detector = pipeline("object-detection", model="facebook/detr-resnet-50")
-
-# raw_image = Image .open("/content/dogwithman.jpg")
-
-# output = object_detector(raw_image)
-# print(output)
-
-
-from PIL import Image
+from PIL import Image, ImageDraw, ImageFont
 import gradio as gr
 from transformers import pipeline
 
@@ -25,26 +11,45 @@ object_detector = pipeline("object-detection", model="facebook/detr-resnet-50")
 def detect_objects(image):
     # Perform object detection on the input image
     results = object_detector(image)
-    
-    # Prepare the output string
-    output = []
+
+    # Create a draw object
+    draw = ImageDraw.Draw(image)
+
+    # Load a custom font
+    font = ImageFont.truetype("Arial.ttf", size=20)
+
+    # Draw bounding boxes around detected objects
     for result in results:
         label = result['label']
         score = result['score']
         box = result['box']
-        output.append(f"Label: {label}, Score: {score:.2f}, Box: {box}")
-    
-    return "\n".join(output)
+        
+        # Draw the bounding box
+        draw.rectangle(
+            [(box['xmin'], box['ymin']), (box['xmax'], box['ymax'])],
+            outline="red", width=2
+        )
+        
+        # Draw the label and score with custom font
+        text = f"{label} {score:.2f}"
+        text_size = draw.textsize(text, font=font)
+        text_location = (box['xmin'], box['ymin'] - text_size[1])
+        draw.rectangle(
+            [(text_location[0], text_location[1]), (text_location[0] + text_size[0], text_location[1] + text_size[1])],
+            fill="red"
+        )
+        draw.text((box['xmin'], box['ymin'] - text_size[1]), text, font=font, fill="white")
+
+    return image
 
 # Create the Gradio interface
 interface = gr.Interface(
-    fn=detect_objects, 
-    inputs=gr.Image(type="pil"), 
-    outputs="text",
+    fn=detect_objects,
+    inputs=gr.Image(type="pil"),
+    outputs=gr.Image(type="pil"),
     title="Image Object Detector",
     description="Upload an image to detect objects using the DETR model."
 )
- 
 
 # Launch the app
 interface.launch()