Update app.py

app.py

@@ -1,24 +1,51 @@
 import torch
 import numpy as np
 import gradio as gr
+import cv2
+import time
 from PIL import Image
 
-device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+# Check device availability
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
-model = torch.hub.load('ultralytics/yolov5', 'yolov5x', pretrained=True).to(device)
+# Load YOLOv5 model
+model = torch.hub.load("ultralytics/yolov5", "yolov5x", pretrained=True).to(device)
 
-if device.type == 'cuda':
-    model.half()
+if device.type == "cuda":
+    model.half()  # Use FP16 for performance boost
+
+# Print available object classes
+print(f"Model loaded with {len(model.names)} classes: {model.names}")
+
+# Assign random colors to each class for bounding boxes
+colors = {i: [int(c) for c in np.random.randint(0, 255, 3)] for i in range(len(model.names))}
 
 def detect_objects(image):
+    start_time = time.time()  # Start FPS measurement
+
     image_pil = Image.fromarray(image)
-    
+
     with torch.no_grad():
-        results = model(image_pil)
-    
-    rendered_images = results.render()
-    
-    return np.array(rendered_images[0]) if rendered_images else image
+        results = model(image_pil, conf=0.3, iou=0.3)  # Apply NMS with IoU = 0.3
+
+    rendered_images = results.render()  # Get rendered image with default YOLOv5 visualization
+
+    # Get bounding boxes and draw color-coded boxes
+    img_cv = np.array(rendered_images[0]) if rendered_images else image
+
+    for det in results.xyxy[0]:  # Bounding box format: x1, y1, x2, y2, conf, cls
+        x1, y1, x2, y2, conf, cls = map(int, det[:6])
+        label = f"{model.names[cls]}: {conf:.2f}"
+
+        cv2.rectangle(img_cv, (x1, y1), (x2, y2), colors[cls], 2)
+        cv2.putText(img_cv, label, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, colors[cls], 2)
+
+    # FPS Calculation
+    end_time = time.time()
+    fps = 1 / (end_time - start_time)
+    print(f"FPS: {fps:.2f}")
+
+    return img_cv
 
 # Gradio interface
 iface = gr.Interface(
@@ -26,9 +53,9 @@ iface = gr.Interface(
     inputs=gr.Image(type="numpy", label="Upload Image"),
     outputs=gr.Image(type="numpy", label="Detected Objects"),
     title="Object Detection with YOLOv5",
-    description="Use webcam or upload an image to detect objects.",
+    description="Use webcam or upload an image to detect objects. Optimized for speed and accuracy!",
     allow_flagging="never",
-    examples=["spring_street_after.jpg", "pexels-hikaique-109919.jpg"]
+    examples=["spring_street_after.jpg", "pexels-hikaique-109919.jpg"],
 )
 
-iface.launch()
+iface.launch()