ModelImpl class final
#include <model.hpp>
Implementation of the Model interface for QNN models.
Contents
Base classes
- class edge::Model
- A base class for machine learning models.
Constructors, destructors, conversion operators
Public functions
- auto operator=(const ModelImpl&) -> ModelImpl & deleted
- auto operator=(ModelImpl&&) -> ModelImpl & deleted
- auto loadModel(const std::filesystem::path& modelPath) -> STATUS final
- Loads the QNN model from the specified path.
- auto loadModel(const nonstd::span<uint8_t>& modelBuffer) -> STATUS final
- Loads the QNN model from the specified buffer.
- auto applyDelegate(const DELEGATE& delegate) -> STATUS final
- Applies a delegate to the QNN backend.
- auto execute() -> STATUS final
- Executes the QNN model.
Function documentation
auto edge::
Loads the QNN model from the specified path.
| Parameters | |
|---|---|
| modelPath | The path to the QNN model file. |
| Returns | STATUS Returns a status indicating whether the model was successfully loaded or not. |
This function loads a QNN model from the specified file path. The model file should be in the QNN context binary format.
auto edge::
Loads the QNN model from the specified buffer.
| Parameters | |
|---|---|
| modelBuffer | The buffer containing the QNN model. |
| Returns | STATUS Returns a status indicating whether the model was successfully loaded or not. |
This function loads a QNN model from the provided buffer. The buffer should contain the raw data of the QNN model.
auto edge::
Applies a delegate to the QNN backend.
| Parameters | |
|---|---|
| delegate | The delegate to apply. |
| Returns | The status of the operation. |
auto edge::
Executes the QNN model.
| Returns | The status of the operation. |
|---|