File size: 6,212 Bytes
ce28923
 
 
 
 
 
 
 
 
 
 
c6644c1
f0ac01e
 
 
 
 
c6644c1
 
 
 
 
 
 
 
 
edcfc33
ce28923
c6644c1
 
60c396d
 
c6644c1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ce28923
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9869cb3
ce28923
 
 
 
 
 
 
 
 
 
 
 
 
c6644c1
 
 
ce28923
 
 
 
 
edcfc33
c6644c1
 
ce28923
 
 
 
 
 
 
 
 
 
 
 
 
5ac585d
 
ce28923
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
edcfc33
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
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
# This file is part of OpenCV Zoo project.
# It is subject to the license terms in the LICENSE file found in the same directory.
#
# Copyright (C) 2021, Shenzhen Institute of Artificial Intelligence and Robotics for Society, all rights reserved.
# Third party copyrights are property of their respective owners.

import argparse

import numpy as np
import cv2 as cv

# Check OpenCV version
opencv_python_version = lambda str_version: tuple(map(int, (str_version.split("."))))
assert opencv_python_version(cv.__version__) >= opencv_python_version("4.10.0"), \
       "Please install latest opencv-python for benchmark: python3 -m pip install --upgrade opencv-python"

from yunet import YuNet

# Valid combinations of backends and targets
backend_target_pairs = [
    [cv.dnn.DNN_BACKEND_OPENCV, cv.dnn.DNN_TARGET_CPU],
    [cv.dnn.DNN_BACKEND_CUDA,   cv.dnn.DNN_TARGET_CUDA],
    [cv.dnn.DNN_BACKEND_CUDA,   cv.dnn.DNN_TARGET_CUDA_FP16],
    [cv.dnn.DNN_BACKEND_TIMVX,  cv.dnn.DNN_TARGET_NPU],
    [cv.dnn.DNN_BACKEND_CANN,   cv.dnn.DNN_TARGET_NPU]
]

parser = argparse.ArgumentParser(description='YuNet: A Fast and Accurate CNN-based Face Detector (https://github.com/ShiqiYu/libfacedetection).')
parser.add_argument('--input', '-i', type=str,
                    help='Usage: Set input to a certain image, omit if using camera.')
parser.add_argument('--model', '-m', type=str, default='face_detection_yunet_2023mar.onnx',
                    help="Usage: Set model type, defaults to 'face_detection_yunet_2023mar.onnx'.")
parser.add_argument('--backend_target', '-bt', type=int, default=0,
                    help='''Choose one of the backend-target pair to run this demo:
                        {:d}: (default) OpenCV implementation + CPU,
                        {:d}: CUDA + GPU (CUDA),
                        {:d}: CUDA + GPU (CUDA FP16),
                        {:d}: TIM-VX + NPU,
                        {:d}: CANN + NPU
                    '''.format(*[x for x in range(len(backend_target_pairs))]))
parser.add_argument('--conf_threshold', type=float, default=0.9,
                    help='Usage: Set the minimum needed confidence for the model to identify a face, defauts to 0.9. Smaller values may result in faster detection, but will limit accuracy. Filter out faces of confidence < conf_threshold.')
parser.add_argument('--nms_threshold', type=float, default=0.3,
                    help='Usage: Suppress bounding boxes of iou >= nms_threshold. Default = 0.3.')
parser.add_argument('--top_k', type=int, default=5000,
                    help='Usage: Keep top_k bounding boxes before NMS.')
parser.add_argument('--save', '-s', action='store_true',
                    help='Usage: Specify to save file with results (i.e. bounding box, confidence level). Invalid in case of camera input.')
parser.add_argument('--vis', '-v', action='store_true',
                    help='Usage: Specify to open a new window to show results. Invalid in case of camera input.')
args = parser.parse_args()

def visualize(image, results, box_color=(0, 255, 0), text_color=(0, 0, 255), fps=None):
    output = image.copy()
    landmark_color = [
        (255,   0,   0), # right eye
        (  0,   0, 255), # left eye
        (  0, 255,   0), # nose tip
        (255,   0, 255), # right mouth corner
        (  0, 255, 255)  # left mouth corner
    ]

    if fps is not None:
        cv.putText(output, 'FPS: {:.2f}'.format(fps), (0, 15), cv.FONT_HERSHEY_SIMPLEX, 0.5, text_color)

    for det in results:
        bbox = det[0:4].astype(np.int32)
        cv.rectangle(output, (bbox[0], bbox[1]), (bbox[0]+bbox[2], bbox[1]+bbox[3]), box_color, 2)

        conf = det[-1]
        cv.putText(output, '{:.4f}'.format(conf), (bbox[0], bbox[1]+12), cv.FONT_HERSHEY_DUPLEX, 0.5, text_color)

        landmarks = det[4:14].astype(np.int32).reshape((5,2))
        for idx, landmark in enumerate(landmarks):
            cv.circle(output, landmark, 2, landmark_color[idx], 2)

    return output

if __name__ == '__main__':
    backend_id = backend_target_pairs[args.backend_target][0]
    target_id = backend_target_pairs[args.backend_target][1]

    # Instantiate YuNet
    model = YuNet(modelPath=args.model,
                  inputSize=[320, 320],
                  confThreshold=args.conf_threshold,
                  nmsThreshold=args.nms_threshold,
                  topK=args.top_k,
                  backendId=backend_id,
                  targetId=target_id)

    # If input is an image
    if args.input is not None:
        image = cv.imread(args.input)
        h, w, _ = image.shape

        # Inference
        model.setInputSize([w, h])
        results = model.infer(image)

        # Print results
        print('{} faces detected.'.format(results.shape[0]))
        for idx, det in enumerate(results):
            print('{}: {:.0f} {:.0f} {:.0f} {:.0f} {:.0f} {:.0f} {:.0f} {:.0f} {:.0f} {:.0f} {:.0f} {:.0f} {:.0f} {:.0f}'.format(
                idx, *det[:-1])
            )

        # Draw results on the input image
        image = visualize(image, results)

        # Save results if save is true
        if args.save:
            print('Resutls saved to result.jpg\n')
            cv.imwrite('result.jpg', image)

        # Visualize results in a new window
        if args.vis:
            cv.namedWindow(args.input, cv.WINDOW_AUTOSIZE)
            cv.imshow(args.input, image)
            cv.waitKey(0)
    else: # Omit input to call default camera
        deviceId = 0
        cap = cv.VideoCapture(deviceId)
        w = int(cap.get(cv.CAP_PROP_FRAME_WIDTH))
        h = int(cap.get(cv.CAP_PROP_FRAME_HEIGHT))
        model.setInputSize([w, h])

        tm = cv.TickMeter()
        while cv.waitKey(1) < 0:
            hasFrame, frame = cap.read()
            if not hasFrame:
                print('No frames grabbed!')
                break

            # Inference
            tm.start()
            results = model.infer(frame) # results is a tuple
            tm.stop()

            # Draw results on the input image
            frame = visualize(frame, results, fps=tm.getFPS())

            # Visualize results in a new Window
            cv.imshow('YuNet Demo', frame)

            tm.reset()