| Class | Description |
|---|---|
| _Range | |
| AbsLayer | |
| AccumLayer | |
| AcoshLayer | |
| AcosLayer | |
| ActivationLayer | |
| ActivationLayerInt8 | |
| ArgLayer |
\brief ArgMax/ArgMin layer
\note returns indices as floats, which means the supported range is [-2^24; 2^24]
|
| AsinhLayer | |
| AsinLayer | |
| AtanhLayer | |
| AtanLayer | |
| AttentionLayer | |
| BackendNode |
\brief Derivatives of this class encapsulates functions of certain backends.
|
| BackendWrapper |
\brief Derivatives of this class wraps cv::Mat for different backends and targets.
|
| BaseConvolutionLayer | |
| BatchNormLayer | |
| BatchNormLayerInt8 | |
| BlankLayer |
\addtogroup dnn
\{
|
| BNLLLayer | |
| CeilLayer | |
| CeluLayer | |
| ChannelsPReLULayer | |
| ClassificationModel |
\brief This class represents high-level API for classification models.
|
| CompareLayer | |
| ConcatLayer | |
| ConstLayer |
Constant layer produces the same data blob at an every forward pass.
|
| ConvolutionLayer | |
| ConvolutionLayerInt8 | |
| CorrelationLayer | |
| CoshLayer | |
| CosLayer | |
| CropAndResizeLayer | |
| CropLayer | |
| CumSumLayer | |
| DataAugmentationLayer | |
| DeconvolutionLayer | |
| DepthToSpaceLayer | |
| DequantizeLayer | |
| DetectionModel |
\brief This class represents high-level API for object detection networks.
|
| DetectionOutputLayer |
\brief Detection output layer.
|
| Dict |
\brief This class implements name-value dictionary, values are instances of DictValue.
|
| DictValue |
\addtogroup dnn
\{
|
| DnnNetAccessor | |
| EinsumLayer |
\brief This function performs array summation based
on the Einstein summation convention.
|
| EltwiseLayer |
\brief Element wise operation on inputs
|
| EltwiseLayerInt8 | |
| ELULayer | |
| ErfLayer | |
| ExpandLayer | |
| ExpLayer | |
| FlattenLayer | |
| FloorLayer | |
| FlowWarpLayer | |
| GatherElementsLayer |
\brief GatherElements layer
GatherElements takes two inputs data and indices of the same rank r >= 1 and an optional attribute axis and works such that:
output[i][j][k] = data[index[i][j][k]][j][k] if axis = 0 and r = 3
output[i][j][k] = data[i][index[i][j][k]][k] if axis = 1 and r = 3
output[i][j][k] = data[i][j][index[i][j][k]] if axis = 2 and r = 3
Gather, on the other hand, takes a data tensor of rank r >= 1, and indices tensor of rank q, and works such that:
it gathers the enteries along axis dimension of the input data indexed by indices and concatenates them in an output tensor of rank q + (r - 1)
e.g.
|
| GatherLayer |
\brief Gather layer
|
| GeluApproximationLayer | |
| GeluLayer | |
| GemmLayer | |
| GroupNormLayer | |
| GRULayer |
\brief GRU recurrent one-layer
Accepts input sequence and computes the final hidden state for each element in the batch.
|
| HardSigmoidLayer | |
| HardSwishLayer | |
| Image2BlobParams |
\brief Processing params of image to blob.
|
| InnerProductLayer |
InnerProduct, MatMul and Gemm operations are all implemented by Fully Connected Layer. |
| InnerProductLayerInt8 | |
| InstanceNormLayer | |
| InterpLayer |
\brief Bilinear resize layer from https://github.com/cdmh/deeplab-public-ver2
It differs from \ref ResizeLayer in output shape and resize scales computations.
|
| IntFloatPair | |
| KeypointsModel |
\brief This class represents high-level API for keypoints models
KeypointsModel allows to set params for preprocessing input image.
|
| Layer |
\brief This interface class allows to build new Layers - are building blocks of networks.
|
| LayerFactory |
\addtogroup dnn
\{
\defgroup dnnLayerFactory Utilities for New Layers Registration
\{
|
| LayerFactory.Constructor |
Each Layer class must provide this function to the factory
|
| LayerNormLayer | |
| LayerParams |
\brief This class provides all data needed to initialize layer.
|
| LogLayer | |
| LRNLayer | |
| LSTMLayer |
LSTM recurrent layer
|
| MatMulLayer | |
| MatPointerVector | |
| MatPointerVector.Iterator | |
| MatShapeVector | |
| MatShapeVector.Iterator | |
| MatShapeVectorVector | |
| MatShapeVectorVector.Iterator | |
| MaxUnpoolLayer | |
| MishLayer | |
| Model |
\brief This class is presented high-level API for neural networks.
|
| Model.Impl | |
| MVNLayer | |
| NaryEltwiseLayer | |
| Net |
\brief This class allows to create and manipulate comprehensive artificial neural networks.
|
| Net.Impl | |
| NormalizeBBoxLayer |
\brief
L_p - normalization layer. |
| NotLayer | |
| PaddingLayer |
\brief Adds extra values for specific axes.
|
| PermuteLayer | |
| PoolingLayer | |
| PoolingLayerInt8 | |
| PowerLayer | |
| PriorBoxLayer | |
| ProposalLayer | |
| QuantizeLayer | |
| RangeVectorVector | |
| ReciprocalLayer | |
| ReduceLayer | |
| RegionLayer | |
| ReLU6Layer | |
| ReLULayer | |
| ReorgLayer | |
| RequantizeLayer | |
| ReshapeLayer | |
| ResizeLayer |
\brief Resize input 4-dimensional blob by nearest neighbor or bilinear strategy.
|
| RNNLayer |
\brief Classical recurrent layer
|
| RoundLayer | |
| ScaleLayer | |
| ScaleLayerInt8 | |
| ScatterLayer | |
| ScatterNDLayer | |
| SegmentationModel |
\brief This class represents high-level API for segmentation models
SegmentationModel allows to set params for preprocessing input image.
|
| SeluLayer | |
| ShiftLayer | |
| ShiftLayerInt8 | |
| ShrinkLayer | |
| ShuffleChannelLayer |
Permute channels of 4-dimensional input blob.
|
| SigmoidLayer | |
| SignLayer | |
| SinhLayer | |
| SinLayer | |
| SliceLayer |
Slice layer has several modes:
1.
|
| SoftmaxLayer | |
| SoftmaxLayerInt8 | |
| SoftplusLayer | |
| SoftsignLayer | |
| SpaceToDepthLayer | |
| SplitLayer | |
| SqrtLayer | |
| SwishLayer | |
| TanHLayer | |
| TanLayer | |
| TextDetectionModel |
\brief Base class for text detection networks
|
| TextDetectionModel_DB |
\brief This class represents high-level API for text detection DL networks compatible with DB model.
|
| TextDetectionModel_EAST |
\brief This class represents high-level API for text detection DL networks compatible with EAST model.
|
| TextRecognitionModel |
\brief This class represents high-level API for text recognition networks.
|
| ThresholdedReluLayer | |
| TileLayer | |
| TopKLayer |
Copyright © 2025. All rights reserved.