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
169
170
171
172
173
174
175
|
// Tencent is pleased to support the open source community by making ncnn available.
//
// Copyright (C) 2018 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 "platform.h"
#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>
#if NCNN_VULKAN
#include "gpu.h"
#endif // NCNN_VULKAN
template<class T>
const T& clamp(const T& v, const T& lo, const T& hi)
{
assert(!(hi < lo));
return v < lo ? lo : hi < v ? hi : v;
}
struct Object
{
cv::Rect_<float> rect;
int label;
float prob;
};
static int detect_mobilenetv3(const cv::Mat& bgr, std::vector<Object>& objects)
{
ncnn::Net mobilenetv3;
#if NCNN_VULKAN
mobilenetv3.opt.use_vulkan_compute = true;
#endif // NCNN_VULKAN
// converted ncnn model from https://github.com/ujsyehao/mobilenetv3-ssd
if (mobilenetv3.load_param("./mobilenetv3_ssdlite_voc.param"))
exit(-1);
if (mobilenetv3.load_model("./mobilenetv3_ssdlite_voc.bin"))
exit(-1);
const int target_size = 300;
int img_w = bgr.cols;
int img_h = bgr.rows;
ncnn::Mat in = ncnn::Mat::from_pixels_resize(bgr.data, ncnn::Mat::PIXEL_BGR2RGB, bgr.cols, bgr.rows, target_size, target_size);
const float mean_vals[3] = {123.675f, 116.28f, 103.53f};
const float norm_vals[3] = {1.0f, 1.0f, 1.0f};
in.substract_mean_normalize(mean_vals, norm_vals);
ncnn::Extractor ex = mobilenetv3.create_extractor();
ex.input("input", in);
ncnn::Mat out;
ex.extract("detection_out", out);
// printf("%d %d %d\n", out.w, out.h, out.c);
objects.clear();
for (int i = 0; i < out.h; i++)
{
const float* values = out.row(i);
Object object;
object.label = values[0];
object.prob = values[1];
// filter out cross-boundary
float x1 = clamp(values[2] * target_size, 0.f, float(target_size - 1)) / target_size * img_w;
float y1 = clamp(values[3] * target_size, 0.f, float(target_size - 1)) / target_size * img_h;
float x2 = clamp(values[4] * target_size, 0.f, float(target_size - 1)) / target_size * img_w;
float y2 = clamp(values[5] * target_size, 0.f, float(target_size - 1)) / target_size * img_h;
object.rect.x = x1;
object.rect.y = y1;
object.rect.width = x2 - x1;
object.rect.height = y2 - y1;
objects.push_back(object);
}
return 0;
}
static void draw_objects(const cv::Mat& bgr, const std::vector<Object>& objects)
{
static const char* class_names[] = {"background",
"aeroplane", "bicycle", "bird", "boat",
"bottle", "bus", "car", "cat", "chair",
"cow", "diningtable", "dog", "horse",
"motorbike", "person", "pottedplant",
"sheep", "sofa", "train", "tvmonitor"
};
cv::Mat image = bgr.clone();
for (size_t i = 0; i < objects.size(); i++)
{
if (objects[i].prob > 0.6)
{
const Object& obj = objects[i];
fprintf(stderr, "%d = %.5f at %.2f %.2f %.2f x %.2f\n", obj.label, obj.prob,
obj.rect.x, obj.rect.y, obj.rect.width, obj.rect.height);
cv::rectangle(image, obj.rect, cv::Scalar(255, 0, 0));
char text[256];
sprintf(text, "%s %.1f%%", class_names[obj.label], obj.prob * 100);
int baseLine = 0;
cv::Size label_size = cv::getTextSize(text, cv::FONT_HERSHEY_SIMPLEX, 0.5, 1, &baseLine);
int x = obj.rect.x;
int y = obj.rect.y - label_size.height - baseLine;
if (y < 0)
y = 0;
if (x + label_size.width > image.cols)
x = image.cols - label_size.width;
cv::rectangle(image, cv::Rect(cv::Point(x, y), cv::Size(label_size.width, label_size.height + baseLine)),
cv::Scalar(255, 255, 255), -1);
cv::putText(image, text, cv::Point(x, y + label_size.height),
cv::FONT_HERSHEY_SIMPLEX, 0.5, cv::Scalar(0, 0, 0));
}
}
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<Object> objects;
detect_mobilenetv3(m, objects);
draw_objects(m, objects);
return 0;
}
|
