reshape

Description

Reshapes a Tensor.

Prototype

reshape(new_shape)

Parameters

**Table 1** Parameter description
Parameter	Input/Output	Description
new_shape	Input	New shape of the Tensor object. A list or tuple of immediates (of type int), Scalars (of type int or uint), or Exprs (of type int or uint).

Applicable Models

Atlas training products

Atlas inference product AI Core

Atlas inference product Vector Core

Atlas A2 training products/Atlas A2 inference products

Atlas 200I/500 A2 inference products

Restrictions

If the data of a Tensor is partially obtained from another Tensor, the Tensor cannot be reshaped by using this API.
The total size of the new shape must be the same as that of the old shape.
The new and old Tensors point to the same memory address. If the value of the new Tensor is changed, the value of the old Tensor changes accordingly.

Returns

The new Tensor.

Example

from tbe import tik
tik_instance = tik.Tik()
data_A = tik_instance.Tensor("float16", (128,), name="data_A", scope=tik.scope_gm)
data_a_reshape = data_A.reshape((64,2))

Parent topic: Tensor Management