ai.onnx ======= This page lists all operators in the **ai.onnx** domain. .. toctree:: :hidden: ai_onnx/Abs ai_onnx/Acos ai_onnx/Acosh ai_onnx/Add ai_onnx/And ai_onnx/ArgMax ai_onnx/ArgMin ai_onnx/Asin ai_onnx/Asinh ai_onnx/AveragePool ai_onnx/BlackmanWindow ai_onnx/Cast ai_onnx/Concat ai_onnx/ConcatFromSequence ai_onnx/Constant ai_onnx/Cos ai_onnx/Cosh ai_onnx/Div ai_onnx/Equal ai_onnx/GRU ai_onnx/Gemm ai_onnx/Greater ai_onnx/If ai_onnx/ImageDecoder ai_onnx/LSTM ai_onnx/Less ai_onnx/MatMul ai_onnx/Mod ai_onnx/Mul ai_onnx/Not ai_onnx/Optional ai_onnx/OptionalGetElement ai_onnx/OptionalHasElement ai_onnx/Or ai_onnx/Pow ai_onnx/QuantizeLinear ai_onnx/RNN ai_onnx/ReduceL1 ai_onnx/ReduceL2 ai_onnx/ReduceLogSum ai_onnx/ReduceLogSumExp ai_onnx/ReduceMax ai_onnx/ReduceMean ai_onnx/ReduceMin ai_onnx/ReduceProd ai_onnx/ReduceSum ai_onnx/ReduceSumSquare ai_onnx/RegexFullMatch ai_onnx/RoiAlign ai_onnx/SequenceAt ai_onnx/SequenceConstruct ai_onnx/SequenceEmpty ai_onnx/SequenceErase ai_onnx/SequenceInsert ai_onnx/SequenceLength ai_onnx/SequenceMap ai_onnx/Sin ai_onnx/Sinh ai_onnx/SplitToSequence ai_onnx/StringConcat ai_onnx/StringNormalizer ai_onnx/StringSplit ai_onnx/Sub ai_onnx/Xor ai_onnx/Abs-1 ai_onnx/Abs-6 ai_onnx/Acos-7 ai_onnx/Acosh-9 ai_onnx/Add-1 ai_onnx/Add-6 ai_onnx/Add-7 ai_onnx/Add-13 ai_onnx/And-1 ai_onnx/ArgMax-1 ai_onnx/ArgMax-11 ai_onnx/ArgMax-12 ai_onnx/ArgMin-1 ai_onnx/ArgMin-11 ai_onnx/ArgMin-12 ai_onnx/Asin-7 ai_onnx/Asinh-9 ai_onnx/AveragePool-1 ai_onnx/AveragePool-7 ai_onnx/AveragePool-10 ai_onnx/AveragePool-11 ai_onnx/AveragePool-19 ai_onnx/Cast-1 ai_onnx/Cast-6 ai_onnx/Cast-9 ai_onnx/Cast-13 ai_onnx/Cast-19 ai_onnx/Cast-21 ai_onnx/Cast-23 ai_onnx/Cast-24 ai_onnx/Concat-1 ai_onnx/Concat-4 ai_onnx/Concat-11 ai_onnx/Constant-1 ai_onnx/Constant-9 ai_onnx/Constant-11 ai_onnx/Constant-12 ai_onnx/Constant-13 ai_onnx/Constant-19 ai_onnx/Constant-21 ai_onnx/Constant-23 ai_onnx/Constant-24 ai_onnx/Cos-7 ai_onnx/Cosh-9 ai_onnx/Div-1 ai_onnx/Div-6 ai_onnx/Div-7 ai_onnx/Div-13 ai_onnx/Equal-1 ai_onnx/Equal-7 ai_onnx/Equal-11 ai_onnx/Equal-13 ai_onnx/GRU-1 ai_onnx/GRU-3 ai_onnx/GRU-7 ai_onnx/GRU-14 ai_onnx/Gemm-1 ai_onnx/Gemm-6 ai_onnx/Gemm-7 ai_onnx/Gemm-9 ai_onnx/Gemm-11 ai_onnx/Greater-1 ai_onnx/Greater-7 ai_onnx/Greater-9 ai_onnx/If-1 ai_onnx/If-11 ai_onnx/LSTM-1 ai_onnx/LSTM-7 ai_onnx/LSTM-14 ai_onnx/Less-1 ai_onnx/Less-7 ai_onnx/Less-9 ai_onnx/MatMul-1 ai_onnx/MatMul-9 ai_onnx/Mod-10 ai_onnx/Mul-1 ai_onnx/Mul-6 ai_onnx/Mul-7 ai_onnx/Mul-13 ai_onnx/OptionalGetElement-15 ai_onnx/OptionalHasElement-15 ai_onnx/Or-1 ai_onnx/Pow-1 ai_onnx/QuantizeLinear-10 ai_onnx/QuantizeLinear-13 ai_onnx/QuantizeLinear-19 ai_onnx/QuantizeLinear-21 ai_onnx/QuantizeLinear-23 ai_onnx/QuantizeLinear-24 ai_onnx/RNN-1 ai_onnx/RNN-7 ai_onnx/RNN-14 ai_onnx/ReduceL1-1 ai_onnx/ReduceL1-11 ai_onnx/ReduceL1-13 ai_onnx/ReduceL2-1 ai_onnx/ReduceL2-11 ai_onnx/ReduceL2-13 ai_onnx/ReduceLogSum-1 ai_onnx/ReduceLogSum-11 ai_onnx/ReduceLogSum-13 ai_onnx/ReduceLogSumExp-1 ai_onnx/ReduceLogSumExp-11 ai_onnx/ReduceLogSumExp-13 ai_onnx/ReduceMax-1 ai_onnx/ReduceMax-11 ai_onnx/ReduceMax-12 ai_onnx/ReduceMax-13 ai_onnx/ReduceMax-18 ai_onnx/ReduceMean-1 ai_onnx/ReduceMean-11 ai_onnx/ReduceMean-13 ai_onnx/ReduceMin-1 ai_onnx/ReduceMin-11 ai_onnx/ReduceMin-12 ai_onnx/ReduceMin-13 ai_onnx/ReduceMin-18 ai_onnx/ReduceProd-1 ai_onnx/ReduceProd-11 ai_onnx/ReduceProd-13 ai_onnx/ReduceSum-1 ai_onnx/ReduceSum-11 ai_onnx/ReduceSumSquare-1 ai_onnx/ReduceSumSquare-11 ai_onnx/ReduceSumSquare-13 ai_onnx/RoiAlign-10 ai_onnx/RoiAlign-16 ai_onnx/Sin-7 ai_onnx/Sinh-9 ai_onnx/Sub-1 ai_onnx/Sub-6 ai_onnx/Sub-7 ai_onnx/Sub-13 ai_onnx/Xor-1 .. list-table:: :header-rows: 1 :widths: 30 10 10 50 :class: sphinx-datatable * - Operator - Since version - Deprecated - Short description * - :ref:`Abs ` - 13 - No - Absolute takes one input data (Tensor ) and produces one output data * - :ref:`Acos ` - 22 - No - Computes the Acos value of the input tensor element-wise. * - :ref:`Acosh ` - 22 - No - Computes the Acosh value of the input tensor element-wise. * - :ref:`Add ` - 14 - No - Performs element-wise binary addition (with Numpy-style broadcasting support). * - :ref:`And ` - 7 - No - Returns the tensor resulted from performing the And logical operation * - :ref:`ArgMax ` - 13 - No - Computes the indices of the max elements of the input tensor's element along ... * - :ref:`ArgMin ` - 13 - No - Computes the indices of the min elements of the input tensor's element along ... * - :ref:`Asin ` - 22 - No - Computes the Asin value of the input tensor element-wise. * - :ref:`Asinh ` - 22 - No - Computes the Asinh value of the input tensor element-wise. * - :ref:`AveragePool ` - 22 - No - AveragePool consumes an input tensor X and applies average pooling across * - :ref:`BlackmanWindow ` - 17 - No - Generates a Blackman window as described in the paper https://ieeexplore.ieee... * - :ref:`Cast ` - 25 - No - The operator casts the elements of a given input tensor to a data type * - :ref:`Concat ` - 13 - No - Concatenate a list of tensors into a single tensor. All input tensors must ha... * - :ref:`ConcatFromSequence ` - 11 - No - Concatenate a sequence of tensors into a single tensor. * - :ref:`Constant ` - 25 - No - This operator produces a constant tensor. Exactly one of the provided attribu... * - :ref:`Cos ` - 22 - No - Computes the Cos value of the input tensor element-wise. * - :ref:`Cosh ` - 22 - No - Computes the Cosh value of the input tensor element-wise. * - :ref:`Div ` - 14 - No - Performs element-wise binary division (with Numpy-style broadcasting support). * - :ref:`Equal ` - 19 - No - Returns the tensor resulted from performing the Equal logical operation * - :ref:`GRU ` - 22 - No - Computes an one-layer GRU. This operator is usually supported via some custom * - :ref:`Gemm ` - 13 - No - General Matrix multiplication: * - :ref:`Greater ` - 13 - No - Returns the tensor resulted from performing the Greater logical operation * - :ref:`If ` - 13 - No - If conditional * - :ref:`ImageDecoder ` - 20 - No - Loads and decodes and image from a file. If it can't decode for any reason (e... * - :ref:`LSTM ` - 22 - No - Computes an one-layer LSTM. This operator is usually supported via some * - :ref:`Less ` - 13 - No - Returns the tensor resulted from performing the Less logical operation * - :ref:`MatMul ` - 13 - No - Matrix product that behaves like [numpy.matmul](https://numpy.org/doc/stable/... * - :ref:`Mod ` - 13 - No - Performs an element-wise binary modulo operation. * - :ref:`Mul ` - 14 - No - Performs element-wise binary multiplication (with Numpy-style broadcasting su... * - :ref:`Not ` - 1 - No - Returns the negation of the input tensor element-wise. * - :ref:`Optional ` - 15 - No - Constructs an optional-type value containing either an empty optional of a ce... * - :ref:`OptionalGetElement ` - 18 - No - If the input is a tensor or sequence type, it returns the input. * - :ref:`OptionalHasElement ` - 18 - No - Returns true if (1) the input is an optional-type and contains an element, * - :ref:`Or ` - 7 - No - Returns the tensor resulted from performing the Or logical operation * - :ref:`Pow ` - 7 - No - Performs element-wise exponentiation. * - :ref:`QuantizeLinear ` - 25 - No - The linear quantization operator consumes a high-precision tensor, a scale, a... * - :ref:`RNN ` - 22 - No - Computes an one-layer simple RNN. This operator is usually supported * - :ref:`ReduceL1 ` - 18 - No - Computes the L1 norm of the input tensor's elements along the provided axes. * - :ref:`ReduceL2 ` - 18 - No - Computes the L2 norm of the input tensor's elements along the provided axes. * - :ref:`ReduceLogSum ` - 18 - No - Computes the log sum of the input tensor's elements along the provided axes. * - :ref:`ReduceLogSumExp ` - 18 - No - Computes the log sum exponent of the input tensor's elements along the provid... * - :ref:`ReduceMax ` - 20 - No - Computes the max of the input tensor's elements along the provided axes. * - :ref:`ReduceMean ` - 18 - No - Computes the mean of the input tensor's elements along the provided axes. * - :ref:`ReduceMin ` - 20 - No - Computes the min of the input tensor's elements along the provided axes. * - :ref:`ReduceProd ` - 18 - No - Computes the product of the input tensor's elements along the provided axes. * - :ref:`ReduceSum ` - 13 - No - Computes the sum of the input tensor's elements along the provided axes. * - :ref:`ReduceSumSquare ` - 18 - No - Computes the sum square of the input tensor's elements along the provided axes. * - :ref:`RegexFullMatch ` - 20 - No - RegexFullMatch performs a full regex match on each element of the input tenso... * - :ref:`RoiAlign ` - 22 - No - Region of Interest (RoI) align operation described in the * - :ref:`SequenceAt ` - 11 - No - Outputs a tensor copy from the tensor at 'position' in 'input_sequence'. * - :ref:`SequenceConstruct ` - 11 - No - Construct a tensor sequence containing 'inputs' tensors. * - :ref:`SequenceEmpty ` - 11 - No - Construct an empty tensor sequence, with given data type. * - :ref:`SequenceErase ` - 11 - No - Outputs a tensor sequence that removes the tensor at 'position' from 'input_s... * - :ref:`SequenceInsert ` - 11 - No - Outputs a tensor sequence that inserts 'tensor' into 'input_sequence' at 'pos... * - :ref:`SequenceLength ` - 11 - No - Produces a scalar(tensor of empty shape) containing the number of tensors in ... * - :ref:`SequenceMap ` - 17 - No - Applies a sub-graph to each sample in the input sequence(s). * - :ref:`Sin ` - 22 - No - Computes the Sin value of the input tensor element-wise. * - :ref:`Sinh ` - 22 - No - Computes the Sinh value of the input tensor element-wise. * - :ref:`SplitToSequence ` - 11 - No - Split a tensor into a sequence of tensors, along the specified 'axis'. * - :ref:`StringConcat ` - 20 - No - StringConcat concatenates string tensors elementwise (with NumPy-style broadc... * - :ref:`StringNormalizer ` - 10 - No - StringNormalization performs string operations for basic cleaning. * - :ref:`StringSplit ` - 20 - No - StringSplit splits a string tensor's elements into substrings based on a deli... * - :ref:`Sub ` - 14 - No - Performs element-wise binary subtraction (with Numpy-style broadcasting suppo... * - :ref:`Xor ` - 7 - No - Returns the tensor resulted from performing the Xor logical operation