ncnn框架是一个非常好的深度学习部署框架,基于ncnn,我们可以很方便的对训练好的深度学习模型部署到手机(Android或Ios)、linux和PC端上,而且ncnn还提供了各个框架模型转换成ncnn可读形式模型的工具,如图1所示。
图1 ncnn提供的模型转换工具
分别对应caffe、mxnet、pytorch、tensorflow,以及onnx转换,将这些框架训练好的深度学习模型,转换成ncnn框架可读的模型形式(.param和.bin文件),然后,基于ncnn框架,将模型进行部署。
在examples文件夹中,也提供了一些实例,像squeezenet、mobilenet-v1、mobilenet-v2、mobilefacenet,github上已经有资源了,这里,我做一个yolov2的笔记。
代码如下:
// 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 <stdio.h>
#include <vector>
#include <opencv2/core/core.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include "ncnn/net.h"
struct Object
{
cv::Rect_<float> rect;
int label;
float prob;
};
static int detect_yolov2(const cv::Mat& bgr, std::vector<Object>& objects)
{
ncnn::Net yolov2;
// original pretrained model from https://github.com/eric612/Caffe-YOLOv2-Windows
// yolov2_deploy.prototxt
// yolov2_deploy_iter_30000.caffemodel
// https://drive.google.com/file/d/17w7oZBbTHPI5TMuD9DKQzkPhSVDaTlC9/view?usp=sharing
yolov2.load_param("../model/mobilenet_yolo.param");
yolov2.load_model("../model/mobilenet_yolo.bin");
// https://github.com/eric612/MobileNet-YOLO
// https://github.com/eric612/MobileNet-YOLO/blob/master/models/yolov2/mobilenet_yolo_deploy%20.prototxt
// https://github.com/eric612/MobileNet-YOLO/blob/master/models/yolov2/mobilenet_yolo_deploy_iter_57000.caffemodel
// yolov2.load_param("mobilenet_yolo.param");
// yolov2.load_model("mobilenet_yolo.bin");
const int target_size = 416;
int img_w = bgr.cols;
int img_h = bgr.rows;
ncnn::Mat in = ncnn::Mat::from_pixels_resize(bgr.data, ncnn::Mat::PIXEL_BGR, bgr.cols, bgr.rows, target_size, target_size);
// the Caffe-YOLOv2-Windows style
// X' = X * scale - mean
const float mean_vals[3] = {0.5f, 0.5f, 0.5f};
const float norm_vals[3] = {0.007843f, 0.007843f, 0.007843f};
in.substract_mean_normalize(0, norm_vals);
in.substract_mean_normalize(mean_vals, 0);
ncnn::Extractor ex = yolov2.create_extractor();
ex.set_num_threads(4);
ex.input("data", 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];
object.rect.x = values[2] * img_w;
object.rect.y = values[3] * img_h;
object.rect.width = values[4] * img_w - object.rect.x;
object.rect.height = values[5] * img_h - object.rect.y;
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++)
{
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), CV_FILLED);
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)
{
const char* imagepath = "test.jpg";
cv::Mat m = cv::imread(imagepath, CV_LOAD_IMAGE_COLOR);
if (m.empty())
{
fprintf(stderr, "cv::imread %s failed\n", imagepath);
return -1;
}
std::vector<Object> objects;
detect_yolov2(m, objects);
draw_objects(m, objects);
return 0;
}
效果如图2所示。
图2 yolo v2效果图
最后,安利一波模型,这里用到的模型可以从这里下载:https://download.csdn.net/download/sinat_31425585/10737783
参考资料: