Documentation

Pad

Availability

Atlas Training Series Product

Function Usage

Pads dimensions of the input tensor based on paddings. The padding value is 0.

Prototype

const aclTensor* Pad(const aclTensor* self, const aclTensor* paddings, aclOpExecutor* executor)

Parameters

Parameter

Input/Output

Description

self

Input

Input tensor to be padded. The data type can be FLOAT16, FLOAT, INT16, UINT16, INT32, or INT64. The data format can be ND.

paddings

Input

Padding sizes of dimensions of the input tensor. The shape is [self.dim, 2]. The data type can be INT32 or INT64, and the data format can be ND.

executor

Input

Operator executor, containing the operator computation process.

Returns

A tensor padded with 0s.

Constraints

None

Example

1
2
//Call l0op::Pad to perform dimension padding on self.
l0op::Pad(self, paddingsTensor, executor);