718c41634f
1.项目后端整体迁移至PaddleOCR-NCNN算法，已通过基本的兼容性测试 2.工程改为使用CMake组织，后续为了更好地兼容第三方库，不再提供QMake工程 3.重整权利声明文件，重整代码工程，确保最小化侵权风险 Log: 切换后端至PaddleOCR-NCNN，切换工程为CMake Change-Id: I4d5d2c5d37505a4a24b389b1a4c5d12f17bfa38c
421 lines
12 KiB
C++
421 lines
12 KiB
C++
// Tencent is pleased to support the open source community by making ncnn available.
|
|
//
|
|
// Copyright (C) 2020 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"
|
|
|
|
#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 <stdlib.h>
|
|
#include <float.h>
|
|
#include <stdio.h>
|
|
#include <vector>
|
|
|
|
struct Object
|
|
{
|
|
cv::Rect_<float> rect;
|
|
int label;
|
|
float prob;
|
|
};
|
|
|
|
static inline float intersection_area(const Object& a, const Object& b)
|
|
{
|
|
cv::Rect_<float> inter = a.rect & b.rect;
|
|
return inter.area();
|
|
}
|
|
|
|
static void qsort_descent_inplace(std::vector<Object>& faceobjects, int left, int right)
|
|
{
|
|
int i = left;
|
|
int j = right;
|
|
float p = faceobjects[(left + right) / 2].prob;
|
|
|
|
while (i <= j)
|
|
{
|
|
while (faceobjects[i].prob > p)
|
|
i++;
|
|
|
|
while (faceobjects[j].prob < p)
|
|
j--;
|
|
|
|
if (i <= j)
|
|
{
|
|
// swap
|
|
std::swap(faceobjects[i], faceobjects[j]);
|
|
|
|
i++;
|
|
j--;
|
|
}
|
|
}
|
|
|
|
#pragma omp parallel sections
|
|
{
|
|
#pragma omp section
|
|
{
|
|
if (left < j) qsort_descent_inplace(faceobjects, left, j);
|
|
}
|
|
#pragma omp section
|
|
{
|
|
if (i < right) qsort_descent_inplace(faceobjects, i, right);
|
|
}
|
|
}
|
|
}
|
|
|
|
static void qsort_descent_inplace(std::vector<Object>& faceobjects)
|
|
{
|
|
if (faceobjects.empty())
|
|
return;
|
|
|
|
qsort_descent_inplace(faceobjects, 0, faceobjects.size() - 1);
|
|
}
|
|
|
|
static void nms_sorted_bboxes(const std::vector<Object>& faceobjects, std::vector<int>& picked, float nms_threshold)
|
|
{
|
|
picked.clear();
|
|
|
|
const int n = faceobjects.size();
|
|
|
|
std::vector<float> areas(n);
|
|
for (int i = 0; i < n; i++)
|
|
{
|
|
areas[i] = faceobjects[i].rect.width * faceobjects[i].rect.height;
|
|
}
|
|
|
|
for (int i = 0; i < n; i++)
|
|
{
|
|
const Object& a = faceobjects[i];
|
|
|
|
int keep = 1;
|
|
for (int j = 0; j < (int)picked.size(); j++)
|
|
{
|
|
const Object& b = faceobjects[picked[j]];
|
|
|
|
// intersection over union
|
|
float inter_area = intersection_area(a, b);
|
|
float union_area = areas[i] + areas[picked[j]] - inter_area;
|
|
// float IoU = inter_area / union_area
|
|
if (inter_area / union_area > nms_threshold)
|
|
keep = 0;
|
|
}
|
|
|
|
if (keep)
|
|
picked.push_back(i);
|
|
}
|
|
}
|
|
|
|
static void generate_proposals(const ncnn::Mat& cls_pred, const ncnn::Mat& dis_pred, int stride, const ncnn::Mat& in_pad, float prob_threshold, std::vector<Object>& objects)
|
|
{
|
|
const int num_grid = cls_pred.h;
|
|
|
|
int num_grid_x;
|
|
int num_grid_y;
|
|
if (in_pad.w > in_pad.h)
|
|
{
|
|
num_grid_x = in_pad.w / stride;
|
|
num_grid_y = num_grid / num_grid_x;
|
|
}
|
|
else
|
|
{
|
|
num_grid_y = in_pad.h / stride;
|
|
num_grid_x = num_grid / num_grid_y;
|
|
}
|
|
|
|
const int num_class = cls_pred.w;
|
|
const int reg_max_1 = dis_pred.w / 4;
|
|
|
|
for (int i = 0; i < num_grid_y; i++)
|
|
{
|
|
for (int j = 0; j < num_grid_x; j++)
|
|
{
|
|
const int idx = i * num_grid_x + j;
|
|
|
|
const float* scores = cls_pred.row(idx);
|
|
|
|
// find label with max score
|
|
int label = -1;
|
|
float score = -FLT_MAX;
|
|
for (int k = 0; k < num_class; k++)
|
|
{
|
|
if (scores[k] > score)
|
|
{
|
|
label = k;
|
|
score = scores[k];
|
|
}
|
|
}
|
|
|
|
if (score >= prob_threshold)
|
|
{
|
|
ncnn::Mat bbox_pred(reg_max_1, 4, (void*)dis_pred.row(idx));
|
|
{
|
|
ncnn::Layer* softmax = ncnn::create_layer("Softmax");
|
|
|
|
ncnn::ParamDict pd;
|
|
pd.set(0, 1); // axis
|
|
pd.set(1, 1);
|
|
softmax->load_param(pd);
|
|
|
|
ncnn::Option opt;
|
|
opt.num_threads = 1;
|
|
opt.use_packing_layout = false;
|
|
|
|
softmax->create_pipeline(opt);
|
|
|
|
softmax->forward_inplace(bbox_pred, opt);
|
|
|
|
softmax->destroy_pipeline(opt);
|
|
|
|
delete softmax;
|
|
}
|
|
|
|
float pred_ltrb[4];
|
|
for (int k = 0; k < 4; k++)
|
|
{
|
|
float dis = 0.f;
|
|
const float* dis_after_sm = bbox_pred.row(k);
|
|
for (int l = 0; l < reg_max_1; l++)
|
|
{
|
|
dis += l * dis_after_sm[l];
|
|
}
|
|
|
|
pred_ltrb[k] = dis * stride;
|
|
}
|
|
|
|
float pb_cx = (j + 0.5f) * stride;
|
|
float pb_cy = (i + 0.5f) * stride;
|
|
|
|
float x0 = pb_cx - pred_ltrb[0];
|
|
float y0 = pb_cy - pred_ltrb[1];
|
|
float x1 = pb_cx + pred_ltrb[2];
|
|
float y1 = pb_cy + pred_ltrb[3];
|
|
|
|
Object obj;
|
|
obj.rect.x = x0;
|
|
obj.rect.y = y0;
|
|
obj.rect.width = x1 - x0;
|
|
obj.rect.height = y1 - y0;
|
|
obj.label = label;
|
|
obj.prob = score;
|
|
|
|
objects.push_back(obj);
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
static int detect_nanodet(const cv::Mat& bgr, std::vector<Object>& objects)
|
|
{
|
|
ncnn::Net nanodet;
|
|
|
|
nanodet.opt.use_vulkan_compute = true;
|
|
// nanodet.opt.use_bf16_storage = true;
|
|
|
|
// original pretrained model from https://github.com/RangiLyu/nanodet
|
|
// the ncnn model https://github.com/nihui/ncnn-assets/tree/master/models
|
|
nanodet.load_param("nanodet_m.param");
|
|
nanodet.load_model("nanodet_m.bin");
|
|
|
|
int width = bgr.cols;
|
|
int height = bgr.rows;
|
|
|
|
const int target_size = 320;
|
|
const float prob_threshold = 0.4f;
|
|
const float nms_threshold = 0.5f;
|
|
|
|
// pad to multiple of 32
|
|
int w = width;
|
|
int h = height;
|
|
float scale = 1.f;
|
|
if (w > h)
|
|
{
|
|
scale = (float)target_size / w;
|
|
w = target_size;
|
|
h = h * scale;
|
|
}
|
|
else
|
|
{
|
|
scale = (float)target_size / h;
|
|
h = target_size;
|
|
w = w * scale;
|
|
}
|
|
|
|
ncnn::Mat in = ncnn::Mat::from_pixels_resize(bgr.data, ncnn::Mat::PIXEL_BGR, width, height, w, h);
|
|
|
|
// pad to target_size rectangle
|
|
int wpad = (w + 31) / 32 * 32 - w;
|
|
int hpad = (h + 31) / 32 * 32 - h;
|
|
ncnn::Mat in_pad;
|
|
ncnn::copy_make_border(in, in_pad, hpad / 2, hpad - hpad / 2, wpad / 2, wpad - wpad / 2, ncnn::BORDER_CONSTANT, 0.f);
|
|
|
|
const float mean_vals[3] = {103.53f, 116.28f, 123.675f};
|
|
const float norm_vals[3] = {0.017429f, 0.017507f, 0.017125f};
|
|
in_pad.substract_mean_normalize(mean_vals, norm_vals);
|
|
|
|
ncnn::Extractor ex = nanodet.create_extractor();
|
|
|
|
ex.input("input.1", in_pad);
|
|
|
|
std::vector<Object> proposals;
|
|
|
|
// stride 8
|
|
{
|
|
ncnn::Mat cls_pred;
|
|
ncnn::Mat dis_pred;
|
|
ex.extract("792", cls_pred);
|
|
ex.extract("795", dis_pred);
|
|
|
|
std::vector<Object> objects8;
|
|
generate_proposals(cls_pred, dis_pred, 8, in_pad, prob_threshold, objects8);
|
|
|
|
proposals.insert(proposals.end(), objects8.begin(), objects8.end());
|
|
}
|
|
|
|
// stride 16
|
|
{
|
|
ncnn::Mat cls_pred;
|
|
ncnn::Mat dis_pred;
|
|
ex.extract("814", cls_pred);
|
|
ex.extract("817", dis_pred);
|
|
|
|
std::vector<Object> objects16;
|
|
generate_proposals(cls_pred, dis_pred, 16, in_pad, prob_threshold, objects16);
|
|
|
|
proposals.insert(proposals.end(), objects16.begin(), objects16.end());
|
|
}
|
|
|
|
// stride 32
|
|
{
|
|
ncnn::Mat cls_pred;
|
|
ncnn::Mat dis_pred;
|
|
ex.extract("836", cls_pred);
|
|
ex.extract("839", dis_pred);
|
|
|
|
std::vector<Object> objects32;
|
|
generate_proposals(cls_pred, dis_pred, 32, in_pad, prob_threshold, objects32);
|
|
|
|
proposals.insert(proposals.end(), objects32.begin(), objects32.end());
|
|
}
|
|
|
|
// sort all proposals by score from highest to lowest
|
|
qsort_descent_inplace(proposals);
|
|
|
|
// apply nms with nms_threshold
|
|
std::vector<int> picked;
|
|
nms_sorted_bboxes(proposals, picked, nms_threshold);
|
|
|
|
int count = picked.size();
|
|
|
|
objects.resize(count);
|
|
for (int i = 0; i < count; i++)
|
|
{
|
|
objects[i] = proposals[picked[i]];
|
|
|
|
// adjust offset to original unpadded
|
|
float x0 = (objects[i].rect.x - (wpad / 2)) / scale;
|
|
float y0 = (objects[i].rect.y - (hpad / 2)) / scale;
|
|
float x1 = (objects[i].rect.x + objects[i].rect.width - (wpad / 2)) / scale;
|
|
float y1 = (objects[i].rect.y + objects[i].rect.height - (hpad / 2)) / scale;
|
|
|
|
// clip
|
|
x0 = std::max(std::min(x0, (float)(width - 1)), 0.f);
|
|
y0 = std::max(std::min(y0, (float)(height - 1)), 0.f);
|
|
x1 = std::max(std::min(x1, (float)(width - 1)), 0.f);
|
|
y1 = std::max(std::min(y1, (float)(height - 1)), 0.f);
|
|
|
|
objects[i].rect.x = x0;
|
|
objects[i].rect.y = y0;
|
|
objects[i].rect.width = x1 - x0;
|
|
objects[i].rect.height = y1 - y0;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void draw_objects(const cv::Mat& bgr, const std::vector<Object>& objects)
|
|
{
|
|
static const char* class_names[] = {
|
|
"person", "bicycle", "car", "motorcycle", "airplane", "bus", "train", "truck", "boat", "traffic light",
|
|
"fire hydrant", "stop sign", "parking meter", "bench", "bird", "cat", "dog", "horse", "sheep", "cow",
|
|
"elephant", "bear", "zebra", "giraffe", "backpack", "umbrella", "handbag", "tie", "suitcase", "frisbee",
|
|
"skis", "snowboard", "sports ball", "kite", "baseball bat", "baseball glove", "skateboard", "surfboard",
|
|
"tennis racket", "bottle", "wine glass", "cup", "fork", "knife", "spoon", "bowl", "banana", "apple",
|
|
"sandwich", "orange", "broccoli", "carrot", "hot dog", "pizza", "donut", "cake", "chair", "couch",
|
|
"potted plant", "bed", "dining table", "toilet", "tv", "laptop", "mouse", "remote", "keyboard", "cell phone",
|
|
"microwave", "oven", "toaster", "sink", "refrigerator", "book", "clock", "vase", "scissors", "teddy bear",
|
|
"hair drier", "toothbrush"
|
|
};
|
|
|
|
cv::Mat image = bgr.clone();
|
|
|
|
for (size_t i = 0; i < objects.size(); i++)
|
|
{
|
|
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_nanodet(m, objects);
|
|
|
|
draw_objects(m, objects);
|
|
|
|
return 0;
|
|
}
|