aclmdlSetDynamicBatchSize
Applicability
|
Product |
Supported |
|---|---|
|
Atlas 350 Accelerator Card |
√ |
|
|
√ |
|
|
√ |
|
|
√ |
|
|
√ |
|
|
√ |
Function Usage
Sets the number of images processed each time during model inference before model execution in dynamic batch scenarios.
Prototype
1
|
aclError aclmdlSetDynamicBatchSize(uint32_t modelId, aclmdlDataset *dataset, size_t index, uint64_t batchSize) |
Parameters
|
Parameter |
Input/Output |
Description |
|---|---|---|
|
modelId |
Input |
Model ID. A successful aclmdlLoadFromFile, aclmdlLoadFromMem, aclmdlLoadFromFileWithMem, or aclmdlLoadFromMemWithMem call returns a model ID. |
|
dataset |
Input and output |
Pointer to the input data for model inference. For details about the type definition, see aclmdlDataset. Data of type aclmdlDataset describes the input data for model inference, while data of type aclDataBuffer describes the input memory size and address. |
|
index |
Input |
Index of the dynamic batch size input. The input index is obtained by the aclmdlGetInputIndexByName call. The input name is fixed to ACL_DYNAMIC_TENSOR_NAME. |
|
batchSize |
Input |
Number of images processed each time during model inference. The configured batch size must be among the batch size profiles set during model building. If you do not know the batch profiles set during model building, you can call aclmdlGetDynamicBatch to obtain the batch profiles supported by the model and the batch size of each profile. |
Returns
0 on success; else, failure. For details, see aclError.