* gru/rnn sequences * update gru/rnn sequences ops, add unit tests * enable sequence transformations for cpu plugin * ngraph codestyle * update tensor iterator to rnn/gru/lstm sequence transformations, add unit tests * ngraph codestyle * add visitors for ngraph ie ops, fix a bug with incorrect axis, fix ngraph to ngraph ie conversion * update GRUSequence/GRUSequenceIE according to plugin format * fix ngraph ie implementations according to plugins restricrictions * fix naming issue * adapt unit tests to accordance to new changes * strict checks, additional unit tests * add descriptions for transformations, fix unit tests * enable ti to sequnece and unroll transformations in plugins for testing * disable tensor iterator ngraph reader tests * delete unnecessary cmake file * fix includes * clean up, resolve review comments * move ti to sequence transformation to ti folder * validate_and_infer_types() implementation * input parameter validation for LSTM, GRU and RNN * style-check applied * Add LSTMSequence dynamic shape validation and test props for RNNCell, GRUCell, LSTMCell and LSTMSequence. * recurrent_sequence.hpp moved to ngraph/core/include/ngraph/op/util/ * style check applied * removed unused variable from LSTMSequence::validate_and_infer_types * Add missing newline mark at the end of file. * Add supression macro for FusedOp deprecation. * Add element type initialization * transpose,rnn cell reference implementations * Apply PR review remarks * reference implementations for cells op, single layer tests, align lstm cell/sequence according to the spec * lstm/gru/rnn cell decompostion transformations * ngraph codestyle * clean up * ngraph code style * change inheritance of Cells, fix build * fix build * fix build again * remove Peepholes from LSTMSeq, fix copy_runtime_info in transformations * Rewrite tests to use gtest exception assertions. * resolve tests issues * ngraph codestyle * add missed files * fix typeprop tests * fix lstm sequence checks * fix arm build * fix arm again * delete unnecessary file * add convert weghts format function, enable lstm test, resolve review comments * add ngraph builders * ngraph codestyle * fix unit tests * revert transpose reference implementation * move ti to sequences transformation to another branch, resolve review comments * resolve review comments * revert fix in ie_layer_validators * revert LSTM Cell v0, add LSTMCell v1, update transformation lstm_cell_to_cell_ie * v1 version of LSTMCell op * LSTMSequence v1 operation, exclude LSTMSeq from opset4 * fix python api tests * resolve review comments, tests for decomposition transformations, switch lstm cell to opset4 in mo * references impl for RNN/GRU/LSTM Sequences, single layer tests, bidirectional transformation * fix unit tests * process dynamic ranks of rnn/gru/lstm ops * remove sequences specifications from opset4 * resolve review comments * fix validate_and_infer_types of GRU/RNN sequences Co-authored-by: Szymon Durawa <szymon.durawa@intel.com>
5.9 KiB
5.9 KiB
Operation Set opset4 Specification
This specification document describes opset4 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 nGraph operation classes
declared in namespace opset4.
Table of Contents
- Abs
- Acos
- Acosh
- Add
- Asin
- Asinh
- Assign
- Atan
- Atanh
- AvgPool
- BatchNormInference
- BatchToSpace
- BinaryConvolution
- Broadcast
- Bucketize
- CTCGreedyDecoder
- CTCLoss
- Ceiling
- Clamp
- Concat
- Constant
- Convert
- ConvertLike
- Convolution
- ConvolutionBackpropData
- Cos
- Cosh
- CumSum
- DeformableConvolution
- DeformablePSROIPooling
- DepthToSpace
- DetectionOutput
- Divide
- Elu
- EmbeddingBagOffsetsSum
- EmbeddingBagPackedSum
- EmbeddingSegmentsSum
- Equal
- Erf
- Exp
- ExtractImagePatches
- FakeQuantize
- Floor
- FloorMod
- Gather
- GatherTree
- Gelu
- Greater
- GreaterEqual
- GRN
- GroupConvolution
- GroupConvolutionBackpropData
- GRUCell
- HardSigmoid
- HSwish
- Interpolate
- Less
- LessEqual
- Log
- LogicalAnd
- LogicalNot
- LogicalOr
- LogicalXor
- LRN
- LSTMCell
- MatMul
- MaxPool
- Maximum
- Minimum
- Mish
- Mod
- MVN
- Multiply
- Negative
- NonMaxSuppression
- NonZero
- NormalizeL2
- NotEqual
- OneHot
- Pad
- Parameter
- Power
- PReLU
- PriorBoxClustered
- PriorBox
- Proposal
- PSROIPooling
- Range
- ReLU
- ReadValue
- ReduceL1
- ReduceL2
- ReduceLogicalAnd
- ReduceLogicalOr
- ReduceMax
- ReduceMean
- ReduceMin
- ReduceProd
- ReduceSum
- RegionYolo
- ReorgYolo
- Reshape
- Result
- Reverse
- ReverseSequence
- RNNCell
- ROIAlign
- ROIPooling
- ScatterElementsUpdate
- ScatterNDUpdate
- ScatterUpdate
- Select
- Selu
- ShapeOf
- ShuffleChannels
- Sigmoid
- Sign
- Sin
- Sinh
- SoftMax
- SoftPlus
- SpaceToBatch
- SpaceToDepth
- Split
- Sqrt
- SquaredDifference
- Squeeze
- StridedSlice
- Subtract
- Swish
- Tan
- Tanh
- TensorIterator
- Tile
- TopK
- Transpose
- Unsqueeze
- VariadicSplit