Forum
Login
Register

Welcome to our Support Center
Updated

Unsqueeze

Description

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 same data as data but with shape [1, 3, 4, 5, 1].

The input 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.

 

Input parameters

 

specified_outputs_name : array, this parameter lets you manually assign custom names to the output tensors of a node.

 Graphs in : cluster, ONNX model architecture.

data (heterogeneous) – T : object, original tensor.
axes (heterogeneous) – tensor(int64) : object, list 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).

 Parameters : cluster,

 training? : boolean, whether B should be transposed on the last two dimensions before doing multiplication.
Default value “True”.
 lda coeff : float, defines the coefficient by which the loss derivative will be multiplied before being sent to the previous layer (since during the backward run we go backwards).
Default value “1”.

 name (optional) : string, name of the node.

Output parameters

 

expanded (heterogeneous) – T : object, reshaped tensor with same data as input.

Type Constraints

T in (tensor(bfloat16), tensor(bool), tensor(complex128), tensor(complex64), tensor(double), tensor(float), tensor(float16), 
tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(string), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)) : Constrain input and output types to all tensor types.

Example

All these exemples are snippets PNG, you can drop these Snippet onto the block diagram and get the depicted code added to your VI (Do not forget to install Deep Learning library to run it).
Table of Contents