ai.onnx#
This page lists all operators in the ai.onnx domain.
Operator |
Since version |
Deprecated |
Short description |
|---|---|---|---|
13 |
No |
Absolute takes one input data (Tensor ) and produces one output data |
|
22 |
No |
Computes the Acos value of the input tensor element-wise. |
|
22 |
No |
Computes the Acosh value of the input tensor element-wise. |
|
14 |
No |
Performs element-wise binary addition (with Numpy-style broadcasting support). |
|
20 |
No |
Generates a 2D or 3D flow field (sampling grid), given a batch of affine matr… |
|
7 |
No |
Returns the tensor resulted from performing the And logical operation |
|
13 |
No |
Computes the indices of the max elements of the input tensor’s element along … |
|
13 |
No |
Computes the indices of the min elements of the input tensor’s element along … |
|
22 |
No |
Computes the Asin value of the input tensor element-wise. |
|
22 |
No |
Computes the Asinh value of the input tensor element-wise. |
|
22 |
No |
Computes the Atan value of the input tensor element-wise. |
|
22 |
No |
Computes the Atanh value of the input tensor element-wise. |
|
24 |
No |
Computes scaled dot product attention on query, key and value tensors, using … |
|
22 |
No |
AveragePool consumes an input tensor X and applies average pooling across |
|
15 |
No |
Carries out batch normalization as described in the paper |
|
22 |
No |
Draws binary random numbers (0 or 1) from a Bernoulli distribution. The input… |
|
26 |
No |
Reinterprets the binary representation of a tensor as a different data type, |
|
11 |
No |
Bitwise shift operator performs element-wise operation. For each input elemen… |
|
18 |
No |
Returns the tensor resulting from performing the bitwise BitwiseAnd operation |
|
18 |
No |
Returns the bitwise not of the input tensor element-wise. |
|
18 |
No |
Returns the tensor resulting from performing the bitwise BitwiseOr operation |
|
18 |
No |
Returns the tensor resulting from performing the bitwise BitwiseXor operation |
|
17 |
No |
Generates a Blackman window as described in the paper https://ieeexplore.ieee… |
|
25 |
No |
The operator casts the elements of a given input tensor to a data type |
|
25 |
No |
The operator casts the elements of a given input tensor (the first input) to |
|
27 |
No |
Stateful causal 1D depthwise convolution. |
|
13 |
No |
Ceil takes one input data (Tensor ) and produces one output data |
|
28 |
No |
Continuously Differentiable Exponential Linear Units: |
|
18 |
No |
Center crop or pad an input to given dimensions. |
|
13 |
No |
Clip operator limits the given input within an interval. The interval is |
|
18 |
No |
The operator rearranges column blocks back into a multidimensional image |
|
11 |
No |
Selects slices from an input tensor along a given axis value passed. |
|
13 |
No |
Concatenate a list of tensors into a single tensor. All input tensors must ha… |
|
11 |
No |
Concatenate a sequence of tensors into a single tensor. |
|
25 |
No |
This operator produces a constant tensor. Exactly one of the provided attribu… |
|
25 |
No |
Generate a tensor with given value and shape. |
|
22 |
No |
The convolution operator consumes an input tensor and a filter, and |
|
10 |
No |
The integer convolution operator consumes an input tensor, its zero-point, a … |
|
22 |
No |
The convolution transpose operator consumes an input tensor and a filter, |
|
22 |
No |
Computes the Cos value of the input tensor element-wise. |
|
22 |
No |
Computes the Cosh value of the input tensor element-wise. |
|
26 |
No |
Performs cumulative product of the input elements along the given axis. |
|
14 |
No |
Performs cumulative sum of the input elements along the given axis. |
|
20 |
No |
Computes the discrete Fourier Transform (DFT) of the input. |
|
22 |
No |
Performs deformable convolution as described in https://arxiv.org/abs/1703.06… |
|
13 |
No |
DepthToSpace rearranges (permutes) data from depth into blocks of spatial data. |
|
25 |
No |
The linear dequantization operator. It consumes a quantized tensor, a scale, … |
|
22 |
No |
Det calculates determinant of a square matrix or batches of square matrices. |
|
14 |
No |
Performs element-wise binary division (with Numpy-style broadcasting support). |
|
22 |
No |
||
11 |
No |
A Function to fuse calculation for Scale, Zero Point and FP32->8Bit conversio… |
|
12 |
No |
An einsum of the form term1, term2 -> output-term produces an output tensor u… |
|
22 |
No |
Elu takes one input data (Tensor ) and produces one output data |
|
19 |
No |
Returns the tensor resulted from performing the Equal logical operation |
|
13 |
No |
Computes the Erf value of the input tensor element-wise. |
|
13 |
No |
Computes the Exp value of the input tensor element-wise. |
|
13 |
No |
Broadcast the input tensor following the given shape and the broadcast rule. |
|
22 |
No |
Generate a 2D tensor (matrix) with ones on the diagonal and zeros everywhere … |
|
25 |
No |
Flattens the input tensor into a 2D matrix. If input tensor has shape |
|
13 |
No |
Floor takes one input data (Tensor ) and produces one output data |
|
22 |
No |
Computes an one-layer GRU. This operator is usually supported via some custom |
|
13 |
No |
Given data tensor of rank r >= 1, and indices tensor of rank q, gather |
|
13 |
No |
GatherElements takes two inputs data and indices of the same rank r >= 1 |
|
13 |
No |
Given data tensor of rank r >= 1, indices tensor of rank q >= 1, and batch_di… |
|
20 |
No |
Gelu takes one input data (Tensor ) and produces one |
|
13 |
No |
General Matrix multiplication: |
|
22 |
No |
GlobalAveragePool consumes an input tensor X and applies average pooling across |
|
22 |
No |
GlobalLpPool consumes an input tensor X and applies lp pool pooling across |
|
22 |
No |
GlobalMaxPool consumes an input tensor X and applies max pooling across |
|
13 |
No |
Returns the tensor resulted from performing the Greater logical operation |
|
16 |
No |
Returns the tensor resulted from performing the GreaterOrEqual logical operation |
|
22 |
No |
Given an input X and a flow-field grid, computes the output Y using X values … |
|
21 |
No |
A GroupNormalization function. Carries out group normalization as described in |
|
17 |
No |
Generates a Hamming window as described in the paper https://ieeexplore.ieee…. |
|
17 |
No |
Generates a Hann window as described in the paper https://ieeexplore.ieee.org… |
|
22 |
No |
HardSigmoid takes one input data (Tensor ) and produces one output data |
|
22 |
No |
HardSwish takes one input data (Tensor ) and produces one output data (Tensor… |
|
13 |
No |
The operator computes the hardmax values for the given input. |
|
25 |
No |
Identity operator |
|
13 |
No |
If conditional |
|
20 |
No |
Loads and decodes and image from a file. If it can’t decode for any reason (e… |
|
22 |
No |
Carries out instance normalization as described in the paper |
|
20 |
No |
Map infinity to true and other values to false. |
|
20 |
No |
Returns which elements of the input are NaN. |
|
13 |
No |
Local Response Normalization proposed in the [AlexNet paper](https://papers.n… |
|
22 |
No |
Computes an one-layer LSTM. This operator is usually supported via some |
|
17 |
No |
This is layer normalization defined in ONNX as function. |
|
16 |
No |
LeakyRelu takes input data (Tensor ) and an argument alpha, and produces one |
|
13 |
No |
Returns the tensor resulted from performing the Less logical operation |
|
16 |
No |
Returns the tensor resulted from performing the LessOrEqual logical operation |
|
27 |
No |
Unified linear attention operator for autoregressive decoding (T=1) and prefi… |
|
13 |
No |
Computes the Log value of the input tensor element-wise. |
|
13 |
No |
The operator computes the log of softmax values for the given input: |
|
13 |
No |
Generic Looping construct. This loop has multiple termination conditions: |
|
22 |
No |
Given a matrix, apply Lp-normalization along the provided axis. |
|
22 |
No |
LpPool consumes an input tensor X and applies Lp pooling across |
|
13 |
No |
Matrix product that behaves like [numpy.matmul](https://numpy.org/doc/stable/… |
|
10 |
No |
Matrix product that behaves like [numpy.matmul](https://numpy.org/doc/stable/… |
|
13 |
No |
Element-wise max of each of the input tensors (with Numpy-style broadcasting … |
|
22 |
No |
MaxPool consumes an input tensor X and applies max pooling across |
|
22 |
No |
ROI max pool consumes an input tensor X and regions of interest (RoIs) to |
|
22 |
No |
MaxUnpool essentially computes the partial inverse of the MaxPool op. |
|
13 |
No |
Element-wise mean of each of the input tensors (with Numpy-style broadcasting… |
|
13 |
No |
A MeanVarianceNormalization Function: Perform mean variance normalization |
|
17 |
No |
Generate a MelWeightMatrix that can be used to re-weight a Tensor containing … |
|
13 |
No |
Element-wise min of each of the input tensors (with Numpy-style broadcasting … |
|
22 |
No |
Mish: A Self Regularized Non-Monotonic Neural Activation Function. |
|
13 |
No |
Performs an element-wise binary modulo operation. |
|
14 |
No |
Performs element-wise binary multiplication (with Numpy-style broadcasting su… |
|
22 |
No |
Generate a tensor of samples from a multinomial distribution according to the… |
|
13 |
No |
Neg takes one input data (Tensor ) and produces one output data |
|
22 |
No |
A NegativeLogLikelihoodLoss operator computes (weighted) negative log likelih… |
|
11 |
No |
Filter out boxes that have high intersection-over-union (IOU) overlap with pr… |
|
13 |
No |
Returns the indices of the elements that are non-zero |
|
1 |
No |
Returns the negation of the input tensor element-wise. |
|
11 |
No |
Produces a one-hot tensor based on inputs. |
|
15 |
No |
Constructs an optional-type value containing either an empty optional of a ce… |
|
18 |
No |
If the input is a tensor or sequence type, it returns the input. |
|
18 |
No |
Returns true if (1) the input is an optional-type and contains an element, |
|
7 |
No |
Returns the tensor resulted from performing the Or logical operation |
|
16 |
No |
PRelu takes input data (Tensor ) and slope tensor as input, and produces one |
|
25 |
No |
Given a tensor containing the data to be padded (data), a tensor containing t… |
|
7 |
No |
Performs element-wise exponentiation. |
|
10 |
No |
The convolution operator consumes a quantized input tensor, its scale and zer… |
|
21 |
No |
Matrix product that behaves like [numpy.matmul](https://numpy.org/doc/stable/… |
|
25 |
No |
The linear quantization operator consumes a high-precision tensor, a scale, a… |
|
23 |
No |
This is RMS normalization defined in ONNX as function as described in the pap… |
|
22 |
No |
Computes an one-layer simple RNN. This operator is usually supported |
|
22 |
No |
Generate a tensor with random values drawn from a normal distribution. The shape |
|
22 |
No |
Generate a tensor with random values drawn from a normal distribution. |
|
22 |
No |
Generate a tensor with random values drawn from a uniform distribution. The s… |
|
22 |
No |
Generate a tensor with random values drawn from a uniform distribution. |
|
27 |
No |
Generate a tensor containing a sequence of numbers that begin at start and ex… |
|
13 |
No |
Reciprocal takes one input data (Tensor ) and produces one output data |
|
18 |
No |
Computes the L1 norm of the input tensor’s elements along the provided axes. |
|
18 |
No |
Computes the L2 norm of the input tensor’s elements along the provided axes. |
|
18 |
No |
Computes the log sum of the input tensor’s elements along the provided axes. |
|
18 |
No |
Computes the log sum exponent of the input tensor’s elements along the provid… |
|
20 |
No |
Computes the max of the input tensor’s elements along the provided axes. |
|
18 |
No |
Computes the mean of the input tensor’s elements along the provided axes. |
|
20 |
No |
Computes the min of the input tensor’s elements along the provided axes. |
|
18 |
No |
Computes the product of the input tensor’s elements along the provided axes. |
|
13 |
No |
Computes the sum of the input tensor’s elements along the provided axes. |
|
18 |
No |
Computes the sum square of the input tensor’s elements along the provided axes. |
|
20 |
No |
RegexFullMatch performs a full regex match on each element of the input tenso… |
|
14 |
No |
Relu takes one input data (Tensor ) and produces one output data |
|
25 |
No |
Reshape the input tensor similar to numpy.reshape. |
|
19 |
No |
Resize the input tensor. In general, it calculates every value in the output … |
|
10 |
No |
Reverse batch of sequences having different lengths specified by sequence_lens. |
|
22 |
No |
Region of Interest (RoI) align operation described in the |
|
23 |
No |
RotaryEmbedding is the implementation of rotary positional embeddings (RoPE) … |
|
22 |
No |
Round takes one input Tensor and rounds the values, element-wise, meaning |
|
17 |
No |
Computes the Short-time Fourier Transform of the signal. |
|
11 |
No |
Scan can be used to iterate over one or more scan_input tensors, |
|
11 |
Yes |
This operator is deprecated. Please use ScatterElements, which provides the s… |
|
18 |
No |
ScatterElements takes three inputs data, updates, and indices of the same |
|
18 |
No |
ScatterND takes three inputs data tensor of rank r >= 1, indices tensor of ra… |
|
22 |
No |
Selu takes one input data (Tensor ) and produces one output data |
|
11 |
No |
Outputs a tensor copy from the tensor at ‘position’ in ‘input_sequence’. |
|
11 |
No |
Construct a tensor sequence containing ‘inputs’ tensors. |
|
11 |
No |
Construct an empty tensor sequence, with given data type. |
|
11 |
No |
Outputs a tensor sequence that removes the tensor at ‘position’ from ‘input_s… |
|
11 |
No |
Outputs a tensor sequence that inserts ‘tensor’ into ‘input_sequence’ at ‘pos… |
|
11 |
No |
Produces a scalar(tensor of empty shape) containing the number of tensors in … |
|
17 |
No |
Applies a sub-graph to each sample in the input sequence(s). |
|
25 |
No |
Takes a tensor as input and outputs an 1D int64 tensor containing the shape o… |
|
9 |
No |
Shrink takes one input data (Tensor ) and produces one Tensor output, |
|
13 |
No |
Sigmoid takes one input data (Tensor ) and produces one output data |
|
13 |
No |
Calculate the sign of the given input tensor element-wise. |
|
22 |
No |
Computes the Sin value of the input tensor element-wise. |
|
22 |
No |
Computes the Sinh value of the input tensor element-wise. |
|
25 |
No |
Takes a tensor as input and outputs a int64 scalar that equals to the total n… |
|
13 |
No |
Produces a slice of the input tensor along multiple axes. |
|
13 |
No |
The operator computes the normalized exponential values for the given input. |
|
13 |
No |
Loss function that measures the softmax cross entropy |
|
22 |
No |
Softplus takes one input data (Tensor ) and produces one output data |
|
22 |
No |
Calculates the softsign (x/(1+|x|)) of the given input tensor element-wise. |
|
13 |
No |
SpaceToDepth rearranges blocks of spatial data into depth. More specifically, |
|
18 |
No |
Split a tensor into a list of tensors, along the specified ‘axis’. |
|
11 |
No |
Split a tensor into a sequence of tensors, along the specified ‘axis’. |
|
13 |
No |
Square root takes one input data (Tensor ) and produces one output data |
|
25 |
No |
Remove single-dimensional entries from the shape of a tensor. |
|
20 |
No |
StringConcat concatenates string tensors elementwise (with NumPy-style broadc… |
|
10 |
No |
StringNormalization performs string operations for basic cleaning. |
|
20 |
No |
StringSplit splits a string tensor’s elements into substrings based on a deli… |
|
14 |
No |
Performs element-wise binary subtraction (with Numpy-style broadcasting suppo… |
|
13 |
No |
Element-wise sum of each of the input tensors (with Numpy-style broadcasting … |
|
24 |
No |
Swish function takes one input data (Tensor ) and produces one output data (T… |
|
22 |
No |
Computes the Tan value of the input tensor element-wise. |
|
13 |
No |
Calculates the hyperbolic tangent of the given input tensor element-wise. |
|
24 |
No |
TensorScatter is a generic tensor update operation, motivated by the requirem… |
|
9 |
No |
This transform extracts n-grams from the input sequence and save them as a ve… |
|
22 |
No |
ThresholdedRelu takes one input data (Tensor ) and produces one output data |
|
13 |
No |
Constructs a tensor by tiling a given tensor. |
|
11 |
No |
Retrieve the top-K largest or smallest elements along a specified axis. Given… |
|
25 |
No |
Returns a transpose of the input tensor. (Similar to numpy.transpose). |
|
14 |
No |
Given a 2-D matrix or batches of 2-D matrices, returns the upper or lower tri… |
|
11 |
No |
Find the unique elements of a tensor. When an optional attribute ‘axis’ is pr… |
|
25 |
No |
Insert single-dimensional entries to the shape of an input tensor (data). |
|
10 |
Yes |
Upsample the input tensor. |
|
16 |
No |
Return elements, either from X or Y, depending on condition. |
|
7 |
No |
Returns the tensor resulted from performing the Xor logical operation |