Hugging Face's logo

opencv
/
opencv_zoo

ONNX
Model card Files
xet
Community
opencv_zoo
File size: 4,987 Bytes 
9e6c549
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
# 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

from pphumanseg import PPHumanSeg

def str2bool(v):
    if v.lower() in ['on', 'yes', 'true', 'y', 't']:
        return True
    elif v.lower() in ['off', 'no', 'false', 'n', 'f']:
        return False
    else:
        raise NotImplementedError

parser = argparse.ArgumentParser(description='PPHumanSeg (https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.2/contrib/PP-HumanSeg)')
parser.add_argument('--input', '-i', type=str, help='Path to the input image. Omit for using default camera.')
parser.add_argument('--model', '-m', type=str, default='human_segmentation_pphumanseg.onnx', help='Path to the model.')
parser.add_argument('--save', '-s', type=str, default=False, help='Set true to save results. This flag is invalid when using camera.')
parser.add_argument('--vis', '-v', type=str2bool, default=True, help='Set true to open a window for result visualization. This flag is invalid when using camera.')
args = parser.parse_args()

def get_color_map_list(num_classes):
    """
    Returns the color map for visualizing the segmentation mask,
    which can support arbitrary number of classes.

    Args:
        num_classes (int): Number of classes.

    Returns:
        (list). The color map.
    """

    num_classes += 1
    color_map = num_classes * [0, 0, 0]
    for i in range(0, num_classes):
        j = 0
        lab = i
        while lab:
            color_map[i * 3] |= (((lab >> 0) & 1) << (7 - j))
            color_map[i * 3 + 1] |= (((lab >> 1) & 1) << (7 - j))
            color_map[i * 3 + 2] |= (((lab >> 2) & 1) << (7 - j))
            j += 1
            lab >>= 3
    color_map = color_map[3:]
    return color_map

def visualize(image, result, weight=0.6, fps=None):
    """
    Convert predict result to color image, and save added image.

    Args:
        image (str): The input image.
        result (np.ndarray): The predict result of image.
        weight (float): The image weight of visual image, and the result weight is (1 - weight). Default: 0.6
        fps (str): The FPS to be drawn on the input image.

    Returns:
        vis_result (np.ndarray): The visualized result.
    """
    color_map = get_color_map_list(256)
    color_map = [color_map[i:i + 3] for i in range(0, len(color_map), 3)]
    color_map = np.array(color_map).astype(np.uint8)
    # Use OpenCV LUT for color mapping
    c1 = cv.LUT(result, color_map[:, 0])
    c2 = cv.LUT(result, color_map[:, 1])
    c3 = cv.LUT(result, color_map[:, 2])
    pseudo_img = np.dstack((c1, c2, c3))

    vis_result = cv.addWeighted(image, weight, pseudo_img, 1 - weight, 0)

    if fps is not None:
        cv.putText(vis_result, 'FPS: {:.2f}'.format(fps), (0, 15), cv.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0))

    return vis_result


if __name__ == '__main__':
    # Instantiate PPHumanSeg
    model = PPHumanSeg(modelPath=args.model)

    if args.input is not None:
        # Read image and resize to 192x192
        image = cv.imread(args.input)
        h, w, _ = image.shape
        image = cv.cvtColor(image, cv.COLOR_BGR2RGB)
        _image = cv.resize(image, dsize=(192, 192))

        # Inference
        result = model.infer(_image)
        result = cv.resize(result[0, :, :], dsize=(w, h), interpolation=cv.INTER_NEAREST)

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

        # Save results if save is true
        if args.save:
            print('Results 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))

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

            _frame = cv.cvtColor(frame, cv.COLOR_BGR2RGB)
            _frame = cv.resize(_frame, dsize=(192, 192))

            # Inference
            tm.start()
            result = model.infer(_frame)
            tm.stop()
            result = cv.resize(result[0, :, :], dsize=(w, h), interpolation=cv.INTER_NEAREST)

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

            # Visualize results in a new window
            cv.imshow('PPHumanSeg Demo', frame)

            tm.reset()