DNN (深度神经网络) 模块

#include < opencv2/dnn/dnn.hpp >

#include < opencv2/dnn/dnn.hpp >

Enum of computation backends supported by layers.

另请参阅

Net::setPreferableBackend

#include < opencv2/dnn/dnn.hpp >

Enum of target devices for computations.

另请参阅

Net::setPreferableTarget

#include < opencv2/dnn/dnn.hpp >

Creates 4-dimensional blob from image. Optionally resizes and crops image from center, subtract mean values, scales values by scalefactor , swap Blue and Red channels.

Parameters

image	input image (with 1-, 3- or 4-channels).
size	spatial size for output image
mean	scalar with mean values which are subtracted from channels. Values are intended to be in (mean-R, mean-G, mean-B) order if image has BGR ordering and swapRB 为 true。
scalefactor	multiplier for image values.
swapRB	flag which indicates that swap first and last channels in 3-channel image is necessary.
crop	flag which indicates whether image will be cropped after resize or not
ddepth	Depth of output blob. Choose CV_32F or CV_8U.

if crop is true, input image is resized so one side after resize is equal to corresponding dimension in size and another one is equal or larger. Then, crop from the center is performed. If crop is false, direct resize without cropping and preserving aspect ratio is performed.

返回

4-dimensional Mat with NCHW dimensions order.

范例：

samples/dnn/classification.cpp , samples/dnn/colorization.cpp , samples/dnn/object_detection.cpp , samples/dnn/openpose.cpp , samples/dnn/segmentation.cpp ，和 samples/dnn/text_detection.cpp .

#include < opencv2/dnn/dnn.hpp >

Creates 4-dimensional blob from image.

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

#include < opencv2/dnn/dnn.hpp >

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.

Parameters

images	input images (all with 1-, 3- or 4-channels).
size	spatial size for output image
mean	scalar with mean values which are subtracted from channels. Values are intended to be in (mean-R, mean-G, mean-B) order if image has BGR ordering and swapRB 为 true。
scalefactor	multiplier for images values.
swapRB	flag which indicates that swap first and last channels in 3-channel image is necessary.
crop	flag which indicates whether image will be cropped after resize or not
ddepth	Depth of output blob. Choose CV_32F or CV_8U.

if crop is true, input image is resized so one side after resize is equal to corresponding dimension in size and another one is equal or larger. Then, crop from the center is performed. If crop is false, direct resize without cropping and preserving aspect ratio is performed.

返回

4-dimensional Mat with NCHW dimensions order.

#include < opencv2/dnn/dnn.hpp >

Creates 4-dimensional blob from series of images.

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

#include < opencv2/dnn/dnn.hpp >

#include < opencv2/dnn/dnn.hpp >

#include < opencv2/dnn/dnn.hpp >

Parse a 4D blob and output the images it contains as 2D arrays through a simpler data structure (std::vector<cv::Mat>).

Parameters

[in]	blob_	4 dimensional array (images, channels, height, width) in floating point precision (CV_32F) from which you would like to extract the images.
[out]	images_	array of 2D Mat containing the images extracted from the blob in floating point precision (CV_32F). They are non normalized neither mean added. The number of returned images equals the first dimension of the blob (batch size). Every image has a number of channels equals to the second dimension of the blob (depth).

#include < opencv2/dnn/dnn.hpp >

Performs non maximum suppression given boxes and corresponding scores.

Parameters

bboxes	a set of bounding boxes to apply NMS.
scores	a set of corresponding confidences.
score_threshold	a threshold used to filter boxes by score.
nms_threshold	a threshold used in non maximum suppression.
indices	the kept indices of bboxes after NMS.
eta	a coefficient in adaptive threshold formula: \(nms\_threshold_{i+1}=eta\cdot nms\_threshold_i\).
top_k	if >0 , keep at most top_k picked indices.

范例：

samples/dnn/object_detection.cpp ，和 samples/dnn/text_detection.cpp .

#include < opencv2/dnn/dnn.hpp >

#include < opencv2/dnn/dnn.hpp >

#include < opencv2/dnn/dnn.hpp >

Read deep learning network represented in one of the supported formats.

Parameters

[in]	model	Binary file contains trained weights. The following file extensions are expected for models from different frameworks: *.caffemodel (Caffe, http://caffe.berkeleyvision.org/ ) *.pb (TensorFlow, https://www.tensorflow.org/ ) *.t7 | *.net (Torch, http://torch.ch/ ) *.weights (Darknet, https://pjreddie.com/darknet/ ) *.bin (DLDT, https://software.intel.com/openvino-toolkit ) *.onnx (ONNX, https://onnx.ai/ )
[in]	config	Text file contains network configuration. It could be a file with the following extensions: *.prototxt (Caffe, http://caffe.berkeleyvision.org/ ) *.pbtxt (TensorFlow, https://www.tensorflow.org/ ) *.cfg (Darknet, https://pjreddie.com/darknet/ ) *.xml (DLDT, https://software.intel.com/openvino-toolkit )
[in]	framework	Explicit framework name tag to determine a format.

返回

Net 对象。

This function automatically detects an origin framework of trained model and calls an appropriate function such readNetFromCaffe , readNetFromTensorflow , readNetFromTorch 或 readNetFromDarknet . An order of model and config arguments does not matter.

范例：

samples/dnn/classification.cpp , samples/dnn/object_detection.cpp , samples/dnn/openpose.cpp , samples/dnn/segmentation.cpp ，和 samples/dnn/text_detection.cpp .

#include < opencv2/dnn/dnn.hpp >

Read deep learning network represented in one of the supported formats.

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

Parameters

[in]	framework	Name of origin framework.
[in]	bufferModel	A buffer with a content of binary file with weights
[in]	bufferConfig	A buffer with a content of text file contains network configuration.

返回

Net 对象。

#include < opencv2/dnn/dnn.hpp >

Reads a network model stored in Caffe framework's format.

Parameters

prototxt	path to the .prototxt file with text description of the network architecture.
caffeModel	path to the .caffemodel file with learned network.

返回

Net 对象。

范例：

samples/dnn/colorization.cpp .

#include < opencv2/dnn/dnn.hpp >

Reads a network model stored in Caffe model in memory.

Parameters

bufferProto	buffer containing the content of the .prototxt file
bufferModel	buffer containing the content of the .caffemodel file

返回

Net 对象。

#include < opencv2/dnn/dnn.hpp >

Reads a network model stored in Caffe model in memory.

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

Parameters

bufferProto	buffer containing the content of the .prototxt file
lenProto	length of bufferProto
bufferModel	buffer containing the content of the .caffemodel file
lenModel	length of bufferModel

返回

Net 对象。

#include < opencv2/dnn/dnn.hpp >

Reads a network model stored in Darknet model files.

Parameters

cfgFile	path to the .cfg file with text description of the network architecture.
darknetModel	path to the .weights file with learned network.

返回

Network object that ready to do forward, throw an exception in failure cases.

Net 对象。

#include < opencv2/dnn/dnn.hpp >

Reads a network model stored in Darknet model files.

Parameters

bufferCfg	A buffer contains a content of .cfg file with text description of the network architecture.
bufferModel	A buffer contains a content of .weights file with learned network.

返回

Net 对象。

#include < opencv2/dnn/dnn.hpp >

Reads a network model stored in Darknet model files.

Parameters

bufferCfg	A buffer contains a content of .cfg file with text description of the network architecture.
lenCfg	Number of bytes to read from bufferCfg
bufferModel	A buffer contains a content of .weights file with learned network.
lenModel	Number of bytes to read from bufferModel

返回

Net 对象。

#include < opencv2/dnn/dnn.hpp >

Load a network from Intel's Model Optimizer intermediate representation.

Parameters

[in]	xml	XML configuration file with network's topology.
[in]	bin	Binary file with trained weights.

返回

Net object. Networks imported from Intel's Model Optimizer are launched in Intel's Inference Engine backend.

#include < opencv2/dnn/dnn.hpp >

Load a network from Intel's Model Optimizer intermediate representation.

Parameters

[in]	bufferModelConfig	Buffer contains XML configuration with network's topology.
[in]	bufferWeights	Buffer contains binary data with trained weights.

返回

Net object. Networks imported from Intel's Model Optimizer are launched in Intel's Inference Engine backend.

#include < opencv2/dnn/dnn.hpp >

Load a network from Intel's Model Optimizer intermediate representation.

Parameters

[in]	bufferModelConfigPtr	Pointer to buffer which contains XML configuration with network's topology.
[in]	bufferModelConfigSize	Binary size of XML configuration data.
[in]	bufferWeightsPtr	Pointer to buffer which contains binary data with trained weights.
[in]	bufferWeightsSize	Binary size of trained weights data.

返回

Net object. Networks imported from Intel's Model Optimizer are launched in Intel's Inference Engine backend.

#include < opencv2/dnn/dnn.hpp >

Reads a network model ONNX .

Parameters

onnxFile

path to the .onnx file with text description of the network architecture.

返回

Network object that ready to do forward, throw an exception in failure cases.

#include < opencv2/dnn/dnn.hpp >

Reads a network model from ONNX in-memory buffer.

Parameters

buffer	memory address of the first byte of the buffer.
sizeBuffer	size of the buffer.

返回

Network object that ready to do forward, throw an exception in failure cases.

#include < opencv2/dnn/dnn.hpp >

Reads a network model from ONNX in-memory buffer.

Parameters

buffer

in-memory buffer that stores the ONNX model bytes.

返回

Network object that ready to do forward, throw an exception in failure cases.

#include < opencv2/dnn/dnn.hpp >

Reads a network model stored in TensorFlow framework's format.

Parameters

model	path to the .pb file with binary protobuf description of the network architecture
config	path to the .pbtxt file that contains text graph definition in protobuf format. Resulting Net object is built by text graph using weights from a binary one that let us make it more flexible.

返回

Net 对象。

#include < opencv2/dnn/dnn.hpp >

Reads a network model stored in TensorFlow framework's format.

Parameters

bufferModel	buffer containing the content of the pb file
bufferConfig	buffer containing the content of the pbtxt file

返回

Net 对象。

#include < opencv2/dnn/dnn.hpp >

Reads a network model stored in TensorFlow framework's format.

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

Parameters

bufferModel	buffer containing the content of the pb file
lenModel	length of bufferModel
bufferConfig	buffer containing the content of the pbtxt file
lenConfig	length of bufferConfig

#include < opencv2/dnn/dnn.hpp >

Reads a network model stored in Torch7 framework's format.

Parameters

model	path to the file, dumped from Torch by using torch.save() function.
isBinary	specifies whether the network was serialized in ascii mode or binary.
evaluate	specifies testing phase of network. If true, it's similar to evaluate() method in Torch.

返回

Net 对象。

注意

Ascii mode of Torch serializer is more preferable, because binary mode extensively use long type of C language, which has various bit-length on different systems.

The loading file must contain serialized nn.Module object with importing network. Try to eliminate a custom objects from serialazing data to avoid importing errors.

List of supported layers (i.e. object instances derived from Torch nn.Module class):

• nn.Sequential
• nn.Parallel
• nn.Concat
• nn.Linear
• nn.SpatialConvolution
• nn.SpatialMaxPooling, nn.SpatialAveragePooling
• nn.ReLU, nn.TanH, nn.Sigmoid
• nn.Reshape
• nn.SoftMax, nn.LogSoftMax

Also some equivalents of these classes from cunn, cudnn, and fbcunn may be successfully imported.

#include < opencv2/dnn/dnn.hpp >

Creates blob from .pb file.

Parameters

path	to the .pb file with input tensor.

返回

Mat .

#include < opencv2/dnn/dnn.hpp >

Loads blob which was serialized as torch.Tensor object of Torch7 framework.

Warning

This function has the same limitations as readNetFromTorch() .

#include < opencv2/dnn/dnn.hpp >

Convert all weights of Caffe network to half precision floating point.

Parameters

src	Path to origin model from Caffe framework contains single precision floating point weights (usually has .caffemodel extension).
dst	Path to destination model with updated weights.
layersTypes	Set of layers types which parameters will be converted. By default, converts only Convolutional and Fully-Connected layers' weights.

注意

Shrinked model has no origin float32 weights so it can't be used in origin Caffe framework anymore. However the structure of data is taken from NVidia's Caffe fork: https://github.com/NVIDIA/caffe . So the resulting model may be used there.

#include < opencv2/dnn/dnn.hpp >

Create a text representation for a binary network stored in protocol buffer format.

Parameters

[in]	model	A path to binary network.
[in]	output	A path to output text file to be created.

注意

To reduce output file size, trained weights are not included.