Function: get_input_dims_range

Product	Supported (√/x)
Atlas A3 training products/Atlas A3 inference products	√
Atlas A2 training products/Atlas A2 inference products	√
Atlas training products	√
Atlas inference products	√
Atlas 200I/500 A2 inference products	√

Obtains the dimension range of an input tensor based on the model description.

C Prototype

aclError aclmdlGetInputDimsRange(const aclmdlDesc *modelDesc, size_t index, aclmdlIODimsRange *dimsRange)

Python Function

dims_range, ret = acl.mdl.get_input_dims_range(model_desc, index)

Parameter	Description
model_desc	Int, pointer to data of the aclmdlDesc type. Call create_desc to create data of the aclmdlDesc type in advance.
index	Int, index of the input dimension information to be obtained, starting from 0.

Parameter

Description

model_desc

Int, pointer to data of the aclmdlDesc type.

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

index

Int, index of the input dimension information to be obtained, starting from 0.

Return Value	Description
dims_range	Dict, dictionary of input dimension information. For details, see aclmdlIODimsRange. Returns the shape range when the dynamic shape is used and the shape range is configured. The dynamic dimension upper and lower limits are different, but the static dimension upper and lower limits are the same. For example, if format of the input tensor is NCHW, dims is [1, 3, 10–224, 10–300], the N and C dimensions are fixed values, and the H and W dimensions are dynamic ranges, then aclmdlIODimsRange.rangeCount is 4, the aclmdlIODimsRange.range array contains four elements: {1,1}, {3, 3}, {10, 224} and {10, 300}. This API is not supported in the dynamic shape scenario when rank data is configured. The aclmdlIODimsRange.rangeCount returns 0. In the static-shape scenario, the shape range is returned, but the upper and lower limits of each dimension are the same.
ret	Int, 0 on success; else, failure.

Return Value

Description

dims_range

Dict, dictionary of input dimension information. For details, see aclmdlIODimsRange.

Returns the shape range when the dynamic shape is used and the shape range is configured. The dynamic dimension upper and lower limits are different, but the static dimension upper and lower limits are the same.
For example, if format of the input tensor is NCHW, dims is [1, 3, 10–224, 10–300], the N and C dimensions are fixed values, and the H and W dimensions are dynamic ranges, then aclmdlIODimsRange.rangeCount is 4, the aclmdlIODimsRange.range array contains four elements: {1,1}, {3, 3}, {10, 224} and {10, 300}.
This API is not supported in the dynamic shape scenario when rank data is configured. The aclmdlIODimsRange.rangeCount returns 0.
In the static-shape scenario, the shape range is returned, but the upper and lower limits of each dimension are the same.

ret

Int, 0 on success; else, failure.

Parent topic: aclmdlDesc