Added application file

app.py

@@ -0,0 +1,92 @@
+import warnings
+warnings.filterwarnings('ignore')
+warnings.simplefilter('ignore')
+
+import torch
+import cv2
+import numpy as np
+import torchvision.transforms as transforms
+from pytorch_grad_cam import EigenCAM
+from pytorch_grad_cam.utils.image import show_cam_on_image, scale_cam_image
+from PIL import Image
+import gradio as gr
+
+# Global Color Palette
+COLORS = np.random.uniform(0, 255, size=(80, 3))
+
+# Function to parse YOLO detections
+def parse_detections(results):
+    detections = results.pandas().xyxy[0].to_dict()
+    boxes, colors, names = [], [], []
+    for i in range(len(detections["xmin"])):
+        confidence = detections["confidence"][i]
+        if confidence < 0.2:
+            continue
+        xmin, ymin = int(detections["xmin"][i]), int(detections["ymin"][i])
+        xmax, ymax = int(detections["xmax"][i]), int(detections["ymax"][i])
+        name, category = detections["name"][i], int(detections["class"][i])
+        boxes.append((xmin, ymin, xmax, ymax))
+        colors.append(COLORS[category])
+        names.append(name)
+    return boxes, colors, names
+
+# Draw bounding boxes and labels
+def draw_detections(boxes, colors, names, img):
+    for box, color, name in zip(boxes, colors, names):
+        xmin, ymin, xmax, ymax = box
+        cv2.rectangle(img, (xmin, ymin), (xmax, ymax), color, 2)
+        cv2.putText(img, name, (xmin, ymin - 5),
+                    cv2.FONT_HERSHEY_SIMPLEX, 0.8, color, 2,
+                    lineType=cv2.LINE_AA)
+    return img
+
+# Main function for Grad-CAM visualization
+def process_image(image):
+    image = np.array(image)
+    image = cv2.resize(image, (640, 640))
+    rgb_img = image.copy()
+    img_float = np.float32(image) / 255
+    
+    # Image transformation
+    transform = transforms.ToTensor()
+    tensor = transform(img_float).unsqueeze(0)
+
+    # Load YOLOv5 model
+    model = torch.hub.load('ultralytics/yolov5', 'yolov5s', pretrained=True)
+    model.eval()
+    model.cpu()
+    target_layers = [model.model.model.model[-2]]
+
+    # Run YOLO detection
+    results = model([rgb_img])
+    boxes, colors, names = parse_detections(results)
+    detections_img = draw_detections(boxes, colors, names, rgb_img.copy())
+
+    # Grad-CAM visualization
+    cam = EigenCAM(model, target_layers)
+    grayscale_cam = cam(tensor)[0, :, :]
+    cam_image = show_cam_on_image(img_float, grayscale_cam, use_rgb=True)
+
+    # Renormalize Grad-CAM inside bounding boxes
+    renormalized_cam = np.zeros(grayscale_cam.shape, dtype=np.float32)
+    for x1, y1, x2, y2 in boxes:
+        renormalized_cam[y1:y2, x1:x2] = scale_cam_image(grayscale_cam[y1:y2, x1:x2].copy())
+    renormalized_cam = scale_cam_image(renormalized_cam)
+    renormalized_cam_image = show_cam_on_image(img_float, renormalized_cam, use_rgb=True)
+
+    # Concatenate images
+    final_image = np.hstack((rgb_img, cam_image, renormalized_cam_image))
+
+    return Image.fromarray(final_image)
+
+# Gradio Interface
+interface = gr.Interface(
+    fn=process_image,
+    inputs=gr.Image(type="pil", label="Upload an Image"),
+    outputs=gr.Image(type="pil", label="Result"),
+    title="YOLOv5 Object Detection with Grad-CAM",
+    description="Upload an image to visualize object detection (YOLOv5) and Grad-CAM explanations."
+)
+
+if __name__ == "__main__":
+    interface.launch()