opset2

This specification document describes opset2 operation set supported in OpenVINO. Support for each particular operation from the list below depends on the capabilities available in a inference plugin and may vary among different hardware platforms and devices. Examples of operation instances are expressed as IR V10 xml snippets. Such IR is generated by the Model Optimizer. The semantics match corresponding OpenVINO operation classes declared in namespace opset2.

Table of Contents

• Abs

• Acos

• Add

• Asin

• Atan

• AvgPool

• BatchNormInference

• BatchToSpace

• BinaryConvolution

• Broadcast

• CTCGreedyDecoder

• Ceiling

• Clamp

• Concat

• Constant

• Convert

• ConvertLike

• Convolution

• ConvolutionBackpropData

• Cos

• Cosh

• DeformableConvolution

• DeformablePSROIPooling

• DepthToSpace

• DetectionOutput

• Divide

• Elu

• Equal

• Erf

• Exp

• FakeQuantize

• Floor

• FloorMod

• Gather

• GatherTree

• Gelu

• Greater

• GreaterEqual

• GRN

• GroupConvolution

• GroupConvolutionBackpropData

• HardSigmoid

• Interpolate

• Less

• LessEqual

• Log

• LogicalAnd

• LogicalNot

• LogicalOr

• LogicalXor

• LRN

• LSTMCell

• LSTMSequence

• MatMul

• MaxPool

• Maximum

• Minimum

• Mod

• MVN

• Multiply

• Negative

• NonMaxSuppression

• NormalizeL2

• NotEqual

• OneHot

• Pad

• Parameter

• Power

• PReLU

• PriorBoxClustered

• PriorBox

• Proposal

• PSROIPooling

• Range

• ReLU

• ReduceLogicalAnd

• ReduceLogicalOr

• ReduceMax

• ReduceMean

• ReduceMin

• ReduceProd

• ReduceSum

• RegionYolo

• ReorgYolo

• Reshape

• Result

• ReverseSequence

• ROIPooling

• Select

• Selu

• ShapeOf

• Sigmoid

• Sign

• Sin

• Sinh

• SoftMax

• SpaceToBatch

• SpaceToDepth

• Split

• Sqrt

• SquaredDifference

• Squeeze

• StridedSlice

• Subtract

• Tan

• Tanh

• TensorIterator

• Tile

• TopK

• Transpose

• Unsqueeze

• VariadicSplit