app.py

import torch
import cv2
import numpy as np
import gradio as gr
from PIL import Image

# Load YOLOv5 model from Ultralytics' official repo
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = torch.hub.load('ultralytics/yolov5', 'yolov5x', pretrained=True).to(device)  # Load YOLOv5x model

# Load COCO class labels
CLASS_NAMES = model.names  # YOLOv5's built-in class names

def preprocess_image(image):
    image = Image.fromarray(image)
    image = image.convert("RGB")
    return image

def detect_objects(image):
    image = preprocess_image(image)

    # Run inference using YOLOv5
    results = model(image)

    # Convert results to bounding box format
    image = np.array(image)
    
    for *box, conf, cls in results.xyxy[0]:  # YOLOv5 format: [x1, y1, x2, y2, conf, class]
        x1, y1, x2, y2 = map(int, box)
        class_name = CLASS_NAMES[int(cls)]  # Get class name
        confidence = conf.item() * 100  # Convert confidence to percentage

        # Draw a bolder bounding box
        cv2.rectangle(image, (x1, y1), (x2, y2), (0, 255, 0), 4)  # Increased thickness

        # Larger text for class label
        label = f"{class_name} ({confidence:.1f}%)"
        cv2.putText(image, label, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 
                    1, (0, 255, 0), 3, cv2.LINE_AA)  # Larger text

    return image

# Gradio UI with Submit button
iface = gr.Interface(
    fn=detect_objects,
    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.",
    allow_flagging="never",
    examples=["spring_street_after.jpg", "pexels-hikaique-109919.jpg"]
)

iface.launch()