Function: set_input_dynamic_dims

Function Usage

Sets the runtime dimensions for model inference before model execution, assuming that the input shape is dynamic and the input data format is ND (supporting any format).

Prototype

C Prototype

        
             aclError aclmdlSetInputDynamicDims(uint32_t modelId, aclmdlDataset *dataset, size_t index, const aclmdlIODims *dims)

Python Function

        
             ret = acl.mdl.set_input_dynamic_dims(model_id, dataset_in, index, dims)

Parameters

Parameter	Description
modelId	Int, model ID. You can obtain the model ID after the model is successfully loaded by calling the following APIs: acl.mdl.load_from_file acl.mdl.load_from_mem acl.mdl.load_from_file_with_mem acl.mdl.load_from_mem_with_mem
dataset	Int, model input data. Data of type aclmdlDataset describes the input data for model inference, while data of type aclDataBuffer describes the input buffer size and address. For details, see aclmdlDataset.
index	Int, index of the dynamic dimension size input. The input index is obtained by the acl.mdl.get_input_index_by_name API. The input name is fixed to ascend_mbatch_shape_data.
dims	Dict, dimension size for model inference. For details, see aclmdlIODims. You can call the acl.mdl.get_input_dynamic_dims API to obtain the number of dimension size profiles as well as the size of each profile supported by the model. Example: Use the following parameters to convert a model with ATC: input_shape="data:1,1,40,-1;label:1,-1;mask:-1,-1", dynamic_dims="20,20,1,1; 40,40,2,2; 80,60,4,4" If the actual dimension of the input data is (1,1,40,20,1,20,1,1), input dims as follows (name is not required): dims = {'dimCount': 8, 'name': '', 'dims': [1,1,40,20,1,20,1,1]}

Returns

Return Value	Description
ret	Int, error code. 0 indicates success, and other values indicate failure.

Reference

For details about the API call sequence and example, see Dynamic Batch/Dynamic Image Size/Dynamic Dimension (Setting Multi-Dimension Profiles).

Parent topic: Model Execution