Function: get_output_dims

Applicability

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	√

Function Usage

Obtains tensor dimension information of an output based on the model description.

Static-shape: This API is used to obtain the shape of the output tensors of a model.
In the dynamic-shape scenario, this API is used to obtain the shape of the maximum batch/image size profile.

Prototype

C Prototype

aclError aclmdlGetOutputDims(const aclmdlDesc *modelDesc, size_t index, aclmdlIODims *dims)

Python Function

dims, ret = acl.mdl.get_output_dims(model_desc, index)

Parameter Description

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 obtain, indexed starting at 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 obtain, indexed starting at 0

Return Value Description

Return Value	Description
dims	Dict, maximum supported combinations for dynamic-batch or dynamic-size scenarios based on the dictionary array. For details, see aclmdlIODims. dims = { "name": xxx, #tensor name "dimCount":xxx, # Number of dimensions in the shape "dims": [xx, xx, xx] # Shape } If the length of the tensor name is greater than 127, when dims["name"] is output, it converts the tensor name to the acl_modelId_${id}_input_${index}_${random character string} format and establishes a mapping between the converted name and the original name, you can call acl.mdl.get_tensor_real_name to transfer the converted name and obtain the original name. (If the original name is passed to the API, the original name is obtained.) NOTE: If the name of the converted tensor conflicts with the name of an existing tensor in the model, _${random string} is added to the end of the converted name. Otherwise, no random string is added. If the length of the tensor name is no longer than 127 characters, the tensor name is output when dims["name"] is output.
ret	Int, error code. 0 indicates success. Other values indicate failure.

Return Value

Description

dims

Dict, maximum supported combinations for dynamic-batch or dynamic-size scenarios based on the dictionary array. For details, see aclmdlIODims.

dims = {
        "name": xxx, #tensor name
        "dimCount":xxx, # Number of dimensions in the shape
        "dims": [xx, xx, xx]   # Shape
        }

If the length of the tensor name is greater than 127, when dims["name"] is output, it converts the tensor name to the acl_modelId_${id}_input_${index}_${random character string} format and establishes a mapping between the converted name and the original name, you can call acl.mdl.get_tensor_real_name to transfer the converted name and obtain the original name. (If the original name is passed to the API, the original name is obtained.)
NOTE:
If the name of the converted tensor conflicts with the name of an existing tensor in the model, _${random string} is added to the end of the converted name. Otherwise, no random string is added.
If the length of the tensor name is no longer than 127 characters, the tensor name is output when dims["name"] is output.

ret

Int, error code.

0 indicates success.
Other values indicate failure.

Parent topic: aclmdlDesc