Unsqueeze#

  • Domain: ai.onnx

  • Since version: 25

Insert single-dimensional entries to the shape of an input tensor (data). Takes one required input axes - which contains a list of dimension indices and this operator will insert a dimension of value 1 into the corresponding index of the output tensor (expanded).

For example:

Given an input tensor (`data`) of shape [3, 4, 5], then
Unsqueeze(data, axes=[0, 4]) outputs a tensor (`expanded`) containing the same data as `data` but with shape [1, 3, 4, 5, 1].

The axes should not contain any duplicate entries. It is an error if it contains duplicates. The rank of the output tensor (output_rank) is the rank of the input tensor (data) plus the number of values in axes. Each value in axes should be within the (inclusive) range [-output_rank , output_rank - 1]. The order of values in axes does not matter and can come in any order.

Inputs

  • data (T): Original tensor

  • axes (tensor(int64)): 1D tensor of integers indicating the dimensions to be inserted. Negative value means counting dimensions from the back. Accepted range is [-r, r-1] where r = rank(expanded).

Outputs

  • expanded (T): Reshaped tensor with same data as input.

Type Constraints

  • T: Constrain input and output types to all tensor types up to IRv13. Allowed types: tensor(bfloat16), tensor(bool), tensor(complex128), tensor(complex64), tensor(double), tensor(float), tensor(float16), tensor(float4e2m1), tensor(float8e4m3fn), tensor(float8e4m3fnuz), tensor(float8e5m2), tensor(float8e5m2fnuz), tensor(float8e8m0), tensor(int16), tensor(int2), tensor(int32), tensor(int4), tensor(int64), tensor(int8), tensor(string), tensor(uint16), tensor(uint2), tensor(uint32), tensor(uint4), tensor(uint64), tensor(uint8).

Differences with previous version (24)#

SchemaDiff: Unsqueeze (domain 'ai.onnx')

  • old version: 24

  • new version: 25

  • breaking: no

Type constraints:

  • changed ‘T’: added types: [‘tensor(int2)’, ‘tensor(uint2)’]

Version History#