app.py

import os
import torch
import gradio as gr
import cv2
import numpy as np
from PIL import Image
from torchvision.transforms import functional as F

# Clone yolov5 if not present
if not os.path.exists("yolov5"):
    os.system("git clone https://github.com/ultralytics/yolov5.git")
    os.system("pip install -r yolov5/requirements.txt")

from yolov5.utils.general import non_max_suppression

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = torch.hub.load('ultralytics/yolov5', 'yolov5s', pretrained=True).to(device)
model.eval()

def preprocess_image(image):
    image = image.convert("RGB")
    image_tensor = F.to_tensor(image).unsqueeze(0).to(device)
    return image_tensor

def draw_boxes(image, outputs, threshold=0.3):
    image = np.array(image)
    for box in outputs:
        score, label, x1, y1, x2, y2 = box[4].item(), int(box[5].item()), box[0].item(), box[1].item(), box[2].item(), box[3].item()
        if score > threshold:
            x1, y1, x2, y2 = int(x1), int(y1), int(x2), int(y2)
            cv2.rectangle(image, (x1, y1), (x2, y2), (255, 0, 0), 2)
            text = f"{model.names[label]}: {score:.2f}"
            cv2.putText(image, text, (x1, y1 - 5), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 0, 0), 2)
    return Image.fromarray(image)

def detect_objects(image):
    image_tensor = preprocess_image(image)
    outputs = model(image_tensor)
    outputs = non_max_suppression(outputs)[0]
    return draw_boxes(image, outputs)

iface = gr.Interface(fn=detect_objects, inputs=gr.Image(type="pil"), outputs=gr.Image(type="pil"),
                     title="YOLO Object Detector", description="Upload an image to detect objects using YOLOv5.")

if __name__ == "__main__":
    iface.launch()