Function: get_input_size_by_index

Applicability

Product	Supported
Atlas 350 Accelerator Card	√
Atlas A3 training product/Atlas A3 inference product	√
Atlas A2 training product/Atlas A2 inference product	√
Atlas training product	√
Atlas inference product	√
Atlas 200I/500 A2 inference product	√

Function Usage

Obtains the input size in bytes based on data of the aclmdlDesc type.

Prototype

C Prototype

size_t aclmdlGetInputSizeByIndex(aclmdlDesc *modelDesc, size_t index)

Python Function

size = acl.mdl.get_input_size_by_index(model_desc, index)

Parameters

Parameter	Description
model_desc	Int, pointer address of the data of the aclmdlDesc type. Call acl.mdl.create_desc to create data of the aclmdlDesc type in advance.
index	Int, sequence number of the input to be obtained, starting from 0.

Parameter

Description

model_desc

Int, pointer address of the data of the aclmdlDesc type.

Call acl.mdl.create_desc to create data of the aclmdlDesc type in advance.

index

Int, sequence number of the input to be obtained, starting from 0.

Returns

Return Value	Description
size	Int, size of the input, in bytes If dynamic batch/image size (width and height) is enabled, the input size of the maximum profile is returned. In other (static) cases, the size of the specified input is returned. The unit is byte.

Restrictions

If the shape input by the model is dynamic and the value of the dimension is –1 (indicating that any value greater than or equal to 1 can be used for the dimension), the size obtained from this call is 0. You need to allocate the memory based on the size of the memory occupied.

Parent topic: aclmdlDesc