Welcome to our Support Center
Updated

UnfoldTensor

Description

Returns a tensor which contains all slices of size size from input tensor in the dimension dim. Step between two slices is given by step. If sizedim is the size of dimension dim for input tensor, the size of dimension dim in the returned tensor will be (sizedim - size) / step + 1. An additional dimension of size size is appended in the returned tensor.

 

Input parameters

 

specified_outputs_name : array, this parameter lets you manually assign custom names to the output tensors of a node.
input (heterogeneous) – T : object, input tensor.

 Parameters : cluster,

dim : integer, specify the dimension to unfold.
Default value “0”.
size : integer, specify the size.
Default value “0”.
step : integer, specify the step.
Default value “0”.
 training? : boolean, whether the layer is in training mode (can store data for backward).
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

 

output (heterogeneous) – T : object, output tensor.

Type Constraints

T in (tensor(uint8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(int8), tensor(int16), tensor(int32), tensor(int64), tensor(bfloat16), tensor(float16), tensor(float), tensor(double), tensor(string), tensor(bool), tensor(complex64), tensor(complex128)) : Allow inputs and outputs to be any kind of tensor.

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