Hugging Face's logo

camenduru
/
ncnn

Model card Files
xet
Community
ncnn
File size: 4,773 Bytes
be903e2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
 
// Tencent is pleased to support the open source community by making ncnn available.
//
// Copyright (C) 2019 THL A29 Limited, a Tencent company. All rights reserved.
//
// Licensed under the BSD 3-Clause License (the "License"); you may not use this file except
// in compliance with the License. You may obtain a copy of the License at
//
// https://opensource.org/licenses/BSD-3-Clause
//
// Unless required by applicable law or agreed to in writing, software distributed
// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
// CONDITIONS OF ANY KIND, either express or implied. See the License for the
// specific language governing permissions and limitations under the License.

#include "net.h"

#include <algorithm>
#if defined(USE_NCNN_SIMPLEOCV)
#include "simpleocv.h"
#else
#include <opencv2/core/core.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#endif
#include <stdio.h>
#include <vector>

struct KeyPoint
{
    cv::Point2f p;
    float prob;
};

static int detect_posenet(const cv::Mat& bgr, std::vector<KeyPoint>& keypoints)
{
    ncnn::Net posenet;

    posenet.opt.use_vulkan_compute = true;

    // the simple baseline human pose estimation from gluon-cv
    // https://gluon-cv.mxnet.io/build/examples_pose/demo_simple_pose.html
    // mxnet model exported via
    //      pose_net.hybridize()
    //      pose_net.export('pose')
    // then mxnet2ncnn
    // the ncnn model https://github.com/nihui/ncnn-assets/tree/master/models
    if (posenet.load_param("pose.param"))
        exit(-1);
    if (posenet.load_model("pose.bin"))
        exit(-1);

    int w = bgr.cols;
    int h = bgr.rows;

    ncnn::Mat in = ncnn::Mat::from_pixels_resize(bgr.data, ncnn::Mat::PIXEL_BGR2RGB, w, h, 192, 256);

    // transforms.ToTensor(),
    // transforms.Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225)),
    // R' = (R / 255 - 0.485) / 0.229 = (R - 0.485 * 255) / 0.229 / 255
    // G' = (G / 255 - 0.456) / 0.224 = (G - 0.456 * 255) / 0.224 / 255
    // B' = (B / 255 - 0.406) / 0.225 = (B - 0.406 * 255) / 0.225 / 255
    const float mean_vals[3] = {0.485f * 255.f, 0.456f * 255.f, 0.406f * 255.f};
    const float norm_vals[3] = {1 / 0.229f / 255.f, 1 / 0.224f / 255.f, 1 / 0.225f / 255.f};
    in.substract_mean_normalize(mean_vals, norm_vals);

    ncnn::Extractor ex = posenet.create_extractor();

    ex.input("data", in);

    ncnn::Mat out;
    ex.extract("conv3_fwd", out);

    // resolve point from heatmap
    keypoints.clear();
    for (int p = 0; p < out.c; p++)
    {
        const ncnn::Mat m = out.channel(p);

        float max_prob = 0.f;
        int max_x = 0;
        int max_y = 0;
        for (int y = 0; y < out.h; y++)
        {
            const float* ptr = m.row(y);
            for (int x = 0; x < out.w; x++)
            {
                float prob = ptr[x];
                if (prob > max_prob)
                {
                    max_prob = prob;
                    max_x = x;
                    max_y = y;
                }
            }
        }

        KeyPoint keypoint;
        keypoint.p = cv::Point2f(max_x * w / (float)out.w, max_y * h / (float)out.h);
        keypoint.prob = max_prob;

        keypoints.push_back(keypoint);
    }

    return 0;
}

static void draw_pose(const cv::Mat& bgr, const std::vector<KeyPoint>& keypoints)
{
    cv::Mat image = bgr.clone();

    // draw bone
    static const int joint_pairs[16][2] = {
        {0, 1}, {1, 3}, {0, 2}, {2, 4}, {5, 6}, {5, 7}, {7, 9}, {6, 8}, {8, 10}, {5, 11}, {6, 12}, {11, 12}, {11, 13}, {12, 14}, {13, 15}, {14, 16}
    };

    for (int i = 0; i < 16; i++)
    {
        const KeyPoint& p1 = keypoints[joint_pairs[i][0]];
        const KeyPoint& p2 = keypoints[joint_pairs[i][1]];

        if (p1.prob < 0.2f || p2.prob < 0.2f)
            continue;

        cv::line(image, p1.p, p2.p, cv::Scalar(255, 0, 0), 2);
    }

    // draw joint
    for (size_t i = 0; i < keypoints.size(); i++)
    {
        const KeyPoint& keypoint = keypoints[i];

        fprintf(stderr, "%.2f %.2f = %.5f\n", keypoint.p.x, keypoint.p.y, keypoint.prob);

        if (keypoint.prob < 0.2f)
            continue;

        cv::circle(image, keypoint.p, 3, cv::Scalar(0, 255, 0), -1);
    }

    cv::imshow("image", image);
    cv::waitKey(0);
}

int main(int argc, char** argv)
{
    if (argc != 2)
    {
        fprintf(stderr, "Usage: %s [imagepath]\n", argv[0]);
        return -1;
    }

    const char* imagepath = argv[1];

    cv::Mat m = cv::imread(imagepath, 1);
    if (m.empty())
    {
        fprintf(stderr, "cv::imread %s failed\n", imagepath);
        return -1;
    }

    std::vector<KeyPoint> keypoints;
    detect_posenet(m, keypoints);

    draw_pose(m, keypoints);

    return 0;
}