Welcome to our Support Center
Updated

SequenceErase

Description

Outputs a tensor sequence that removes the tensor at ‘position’ from ‘input_sequence’. Accepted range for ‘position’ is in [-n, n - 1], where n is the number of tensors in ‘input_sequence’. Negative value means counting positions from the back. ‘position’ is optional, by default it erases the last tensor from ‘input_sequence’.

 

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.

input_sequence (heterogeneous) – S : object, input sequence.
position (optional, heterogeneous) – I : object, position of the tensor in the sequence. Negative value means counting positions from the back. Accepted range in [-n, n - 1], where n is the number of tensors in ‘input_sequence’. It is an error if any of the index values are out of bounds. It must be a scalar(tensor of empty shape).

 Parameters : cluster,

 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_sequence (heterogeneous) – S : object, output sequence that has the tensor at the specified position removed.

Type Constraints

S in (seq(tensor(bool)), seq(tensor(complex128)), seq(tensor(complex64)), seq(tensor(double)), seq(tensor(float)),
seq(tensor(float16)), seq(tensor(int16)), seq(tensor(int32)), seq(tensor(int64)), seq(tensor(int8)), seq(tensor(string)), seq(tensor(uint16)), seq(tensor(uint32)), seq(tensor(uint64)), seq(tensor(uint8))) : Constrain to any tensor type.

I in (tensor(int32), tensor(int64)) : Constrain position to integral tensor. It must be a scalar(tensor of empty shape).

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