File size: 3,270 Bytes
516d9b1
 
 
 
 
 
 
 
5ab0afc
516d9b1
bef99af
 
516d9b1
 
bef99af
516d9b1
 
 
08ba7c3
550f163
bef99af
 
516d9b1
 
 
 
70eacb3
 
bfe786b
70eacb3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2c61af9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
from __future__ import annotations
import pathlib
import cv2
import gradio as gr
import huggingface_hub
import insightface
import numpy as np
import onnxruntime as ort
from PIL import Image

TITLE = "insightface Person Detection"
DESCRIPTION = "https://github.com/deepinsight/insightface/tree/master/examples/person_detection"

def load_model():
    path = huggingface_hub.hf_hub_download("public-data/insightface", "models/scrfd_person_2.5g.onnx")
    options = ort.SessionOptions()
    options.intra_op_num_threads = 8
    options.inter_op_num_threads = 8
    session = ort.InferenceSession(
        path, sess_options=options, providers=["CPUExecutionProvider"]
    )
    model = insightface.model_zoo.retinaface.RetinaFace(model_file=path, session=session)
    return model

def detect_person(
    img: np.ndarray, detector: insightface.model_zoo.retinaface.RetinaFace
) -> tuple[np.ndarray, np.ndarray]:
    bboxes, kpss = detector.detect(img)
    bboxes = np.round(bboxes[:, :4]).astype(int)
    kpss = np.round(kpss).astype(int)
    kpss[:, :, 0] = np.clip(kpss[:, :, 0], 0, img.shape[1])
    kpss[:, :, 1] = np.clip(kpss[:, :, 1], 0, img.shape[0])
    vbboxes = bboxes.copy()
    vbboxes[:, 0] = kpss[:, 0, 0]
    vbboxes[:, 1] = kpss[:, 0, 1]
    vbboxes[:, 2] = kpss[:, 4, 0]
    vbboxes[:, 3] = kpss[:, 4, 1]
    return bboxes, vbboxes

def visualize(image: np.ndarray, bboxes: np.ndarray, vbboxes: np.ndarray) -> np.ndarray:
    res = image.copy()
    for i in range(bboxes.shape[0]):
        bbox = bboxes[i]
        vbbox = vbboxes[i]
        x1, y1, x2, y2 = bbox
        vx1, vy1, vx2, vy2 = vbbox
        cv2.rectangle(res, (x1, y1), (x2, y2), (0, 255, 0), 1)
        alpha = 0.8
        color = (255, 0, 0)
        for c in range(3):
            res[vy1:vy2, vx1:vx2, c] = res[vy1:vy2, vx1:vx2, c] * alpha + color[c] * (1.0 - alpha)
        cv2.circle(res, (vx1, vy1), 1, color, 2)
        cv2.circle(res, (vx1, vy2), 1, color, 2)
        cv2.circle(res, (vx2, vy1), 1, color, 2)
        cv2.circle(res, (vx2, vy2), 1, color, 2)
    return res

def extract_persons(image: np.ndarray, bboxes: np.ndarray) -> list[Image.Image]:
    person_images = []
    for bbox in bboxes:
        x1, y1, x2, y2 = bbox
        person_image = image[y1:y2, x1:x2]  # Crop the detected person
        person_pil_image = Image.fromarray(person_image)
        person_images.append(person_pil_image)
    return person_images

detector = load_model()
detector.prepare(-1, nms_thresh=0.5, input_size=(640, 640))

def detect(image: np.ndarray) -> tuple[Image.Image, list[Image.Image]]:
    image = image[:, :, ::-1]  # RGB -> BGR
    bboxes, vbboxes = detect_person(image, detector)
    res = visualize(image, bboxes, vbboxes)
    person_images = extract_persons(res, bboxes)
    return Image.fromarray(res[:, :, ::-1], 'RGB'), person_images  # BGR -> RGB

examples = sorted(pathlib.Path("images").glob("*.jpg"))

demo = gr.Interface(
    fn=detect,
    inputs=gr.Image(label="Input", type="numpy"),
    outputs=[gr.Image(label="Processed Image", type="numpy"), gr.Gallery(label="Detected Persons", type="numpy")],
    examples=examples,
    examples_per_page=30,
    title=TITLE,
    description=DESCRIPTION,
)

if __name__ == "__main__":
    demo.queue(max_size=10).launch()