Function: get_cur_output_dims

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	√

Runtime shape information supported by a model based on the model description.

C Prototype

aclError aclmdlGetCurOutputDims(const aclmdlDesc *modelDesc, size_t index, aclIODims *dims)

Python Function

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

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, index of the output whose dimensions to obtain, indexed 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, index of the output whose dimensions to obtain, indexed from 0.

Return Value	Description
dims	Dict, runtime 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, runtime 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.

Currently, this API can be used to obtain the shape of the model output tensors only in the following scenarios:

Set the batch size, resolution, or dimension value through model conversion to implement dynamic batch, dynamic image size, or dynamic dimension (ND format).
- If you have set batch by calling acl.mdl.set_dynamic_batch_size, set the width and height of the input image by calling acl.mdl.set_dynamic_hw_size, or set the value of a dynamic dimension by calling acl.mdl.set_input_dynamic_dims, you can call this API to obtain the actual dimension information of the output tensor of a specified model.
- If the acl.mdl.set_dynamic_batch_size, acl.mdl.set_dynamic_hw_size, or acl.mdl.set_input_dynamic_dims API is not called, this interface can be used to obtain the dimension information of the maximum dimensions.
Static-shape: This API is used to obtain the shape of the output tensors of a model.

Parent topic: aclmdlDesc