OpenCV3.4的神经网络功能主要提供了以下三种：
- ml模块中的多层感知机（Artificial Neural Networks - Multi-Layer Perceptrons），提供了MLP的创建、训练、参数设置等函数。如：
static Ptr< ANN_MLP > create ()
Creates empty model.
static Ptr< ANN_MLP > load (const String &filepath)
Loads and creates a serialized ANN from a file.
void setAnnealFinalT (double val)
void setAnnealInitialT (double val)
void setAnnealItePerStep (int val)
virtual void setBackpropMomentumScale (double val)=0
virtual void setBackpropWeightScale (double val)=0
virtual void setLayerSizes (InputArray _layer_sizes)=0
virtual void setRpropDW0 (double val)=0
virtual void setRpropDWMax (double val)=0
enum ActivationFunctions {
IDENTITY = 0,
SIGMOID_SYM = 1,
GAUSSIAN = 2,
RELU = 3,
LEAKYRELU = 4
}
enum TrainFlags {
UPDATE_WEIGHTS = 1,
NO_INPUT_SCALE = 2,
NO_OUTPUT_SCALE = 4
}
enum TrainingMethods {
BACKPROP =0,
RPROP = 1,
ANNEAL = 2
}
```
请参看[帮助文档](https://docs.opencv.org/3.4.0/d0/dce/classcv_1_1ml_1_1ANN__MLP.html)。
2. DNN模块，提供了很多用于创建、加载、训练深度网络和参数设置以及加载TensorFlow、Caffe、Torch模型的方法和类，如：
class cv::dnn::BackendNode
Derivatives of this class encapsulates functions of certain backends.
class cv::dnn::BackendWrapper
Derivatives of this class wraps cv::Mat for different backends and targets.
class cv::dnn::Dict
This class implements name-value dictionary, values are instances of DictValue.
struct cv::dnn::DictValue
This struct stores the scalar value (or array) of one of the following type: double, cv::String or int64.
class cv::dnn::Layer
This interface class allows to build new Layers - are building blocks of networks.
class cv::dnn::LayerParams
This class provides all data needed to initialize layer.
class cv::dnn::Net
This class allows to create and manipulate comprehensive artificial neural networks.
Mat cv::dnn::blobFromImages (const std::vector< Mat > &images, double scalefactor=1.0, Size size=Size(), const Scalar &mean=Scalar(), bool swapRB=true, bool crop=true)
Creates 4-dimensional blob from series of images. Optionally resizes and crops images from center, subtract mean values, scales values by scalefactor, swap Blue and Red channels.
void cv::dnn::NMSBoxes (const std::vector< Rect > &bboxes, const std::vector< float > &scores, const float score_threshold, const float nms_threshold, std::vector< int > &indices, const float eta=1.f, const int top_k=0)
Performs non maximum suppression given boxes and corresponding scores.
Net cv::dnn::readNetFromCaffe (const String &prototxt, const String &caffeModel=String())
Reads a network model stored in Caffe framework's format.
Net cv::dnn::readNetFromDarknet (const String &cfgFile, const String &darknetModel=String())
Reads a network model stored in Darknet model files.
Net cv::dnn::readNetFromTensorflow (const String &model, const String &config=String())
Reads a network model stored in TensorFlow framework's format.
Net cv::dnn::readNetFromTorch (const String &model, bool isBinary=true)
参看[帮助文档](https://docs.opencv.org/3.4.0/d6/d0f/group__dnn.html)。
3. 第三方深度网络工具，详情请查看帮助文档。
下面给出示例。
1.基于MLP的识别。该程序人工生成四类动物数据，通过MLP网络训练模型并检测测试数据类型。
#exam1.py
import cv2
import numpy as np
from random import randint
#创建MLP网络，并设置训练方法、激活函数、层大小和迭代终止条件。
animals_net = cv2.ml.ANN_MLP_create()
animals_net.setTrainMethod(cv2.ml.ANN_MLP_RPROP | cv2.ml.ANN_MLP_UPDATE_WEIGHTS)
animals_net.setActivationFunction(cv2.ml.ANN_MLP_SIGMOID_SYM)
animals_net.setLayerSizes(np.array([3, 6, 4]))
animals_net.setTermCriteria(( cv2.TERM_CRITERIA_EPS | cv2.TERM_CRITERIA_COUNT, 10, 1 ))
#生成四类动物数据及类标记
def dog_sample():
return [randint(10, 20), 1, randint(38, 42)]
def dog_class():
return [1, 0, 0, 0]
def condor_sample():
return [randint(3,10), randint(3,5), 0]
def condor_class():
return [0, 1, 0, 0]
def dolphin_sample():
return [randint(30, 190), randint(5, 15), randint(80, 100)]
def dolphin_class():
return [0, 0, 1, 0]
def dragon_sample():
return [randint(1200, 1800), randint(30, 40), randint(160, 180)]
def dragon_class():
return [0, 0, 0, 1]
#将动物数据和类标记组成一个记录（样本）
def record(sample, classification):
return (np.array([sample], dtype=np.float32), np.array([classification], dtype=np.float32))
#获取5000个样本数据
records = []
RECORDS = 5000
for x in range(0, RECORDS):
records.append(record(dog_sample(), dog_class()))
records.append(record(condor_sample(), condor_class()))
records.append(record(dolphin_sample(), dolphin_class()))
records.append(record(dragon_sample(), dragon_class()))
#训练MLP网络
EPOCHS = 2
for e in range(0, EPOCHS):
print("Epoch %d:" % e)
for t, c in records:
animals_net.train(t, cv2.ml.ROW_SAMPLE, c)
#预测测试样本类别
TESTS = 100
dog_results = 0
for x in range(0, TESTS):
clas = int(animals_net.predict(np.array([dog_sample()], dtype=np.float32))[0])
print("class: %d" % clas)
if (clas) == 0:
dog_results += 1
condor_results = 0
for x in range(0, TESTS):
clas = int(animals_net.predict(np.array([condor_sample()], dtype=np.float32))[0])
print("class: %d" % clas)
if (clas) == 1:
condor_results += 1
dolphin_results = 0
for x in range(0, TESTS):
clas = int(animals_net.predict(np.array([dolphin_sample()], dtype=np.float32))[0])
print("class: %d" % clas)
if (clas) == 2:
dolphin_results += 1
dragon_results = 0
for x in range(0, TESTS):
clas = int(animals_net.predict(np.array([dragon_sample()], dtype=np.float32))[0])
print("class: %d" % clas)
if (clas) == 3:
dragon_results += 1
#输出测试准确率
print("Dog accuracy: %f%%" % (dog_results))
print("condor accuracy: %f%%" % (condor_results))
print("dolphin accuracy: %f%%" % (dolphin_results))
print("dragon accuracy: %f%%" % (dragon_results))
2.基于DNN的识别。该程序加载预先训练的caffe模型在摄像头获取的图像上检测人脸。
import numpy as np import argparse import cv2 as cv #若出现ImportError，请配置环境变量PYTHONPATH为Python可执行文件的地址。 #若不能解决，请更新相关包（或卸载后重新安装）。 try: import cv2 as cv except ImportError: raise ImportError('Can't find OpenCV Python module. If you've built it from sources without installation, ' 'configure environemnt variable PYTHONPATH to "opencv_build_dir/lib" directory (with "python3" subdirectory if required)') #导入DNN模块 from cv2 import dnn inWidth = 300 inHeight = 300 confThreshold = 0.5 #该文件包含在opencv3.4\sources\samples\dnn\face_detector目录中，该目录的上级目录为OpenCV3.4的下载或安装目录 prototxt = 'face_detector/deploy.prototxt' #该caffe模型文件需先下载，请参看opencv3.4\sources\samples\dnn\face_detector目录中的文本文件 caffemodel = 'face_detector/res10_300x300_ssd_iter_140000.caffemodel' #加载caffe模型并从摄像头获取图像 if name == 'main': net = dnn.readNetFromCaffe(prototxt, caffemodel) cap = cv.VideoCapture(0) while True: ret, frame = cap.read() cols = frame.shape[1] rows = frame.shape[0] #将获取的图像设置为网络输入，设置网络传播方向，检测人脸 net.setInput(dnn.blobFromImage(frame, 1.0, (inWidth, inHeight), (104.0, 177.0, 123.0), False, False)) detections = net.forward() perf_stats = net.getPerfProfile() print('Inference time, ms: %.2f' % (perf_stats[0] / cv.getTickFrequency() * 1000)) for i in range(detections.shape[2]): confidence = detections[0, 0, i, 2] if confidence > confThreshold: xLeftBottom = int(detections[0, 0, i, 3] * cols) yLeftBottom = int(detections[0, 0, i, 4] * rows) xRightTop = int(detections[0, 0, i, 5] * cols) yRightTop = int(detections[0, 0, i, 6] * rows) cv.rectangle(frame, (xLeftBottom, yLeftBottom), (xRightTop, yRightTop), (0, 255, 0)) label = "face: %.4f" % confidence labelSize, baseLine = cv.getTextSize(label, cv.FONT_HERSHEY_SIMPLEX, 0.5, 1) cv.rectangle(frame, (xLeftBottom, yLeftBottom - labelSize[1]), (xLeftBottom + labelSize[0], yLeftBottom + baseLine), (255, 255, 255), cv.FILLED) cv.putText(frame, label, (xLeftBottom, yLeftBottom), cv.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0)) cv.imshow("detections", frame) if cv.waitKey(1) != -1: break
