File size: 1,567 Bytes
46e3370
caff61e
46e3370
 
a29d5e2
 
 
caff61e
46e3370
a29d5e2
caff61e
 
a29d5e2
46e3370
 
 
a29d5e2
46e3370
 
 
a29d5e2
 
 
46e3370
 
 
 
 
a29d5e2
46e3370
a29d5e2
 
 
46e3370
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
import gradio as gr
import torch
import cv2
import numpy as np
from PIL import Image
from torchvision.transforms import functional as F
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)
    h, w, _ = image.shape
    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()