DeploySharp.Engine 命名空间
Contains runtime execution engines for model deployment
包含模型部署的运行时执行引擎
Provides various execution environments and runtime implementations
for different deployment targets (CPU, GPU, edge devices etc.)
为不同部署目标(CPU、GPU、边缘设备等)提供多种执行环境和运行时实现
| DisplayNameAttribute |
Specifies a display name for enumeration fields
为枚举字段指定显示名称
|
| EnumExtensions |
Provides extension methods for working with enums
提供处理枚举的扩展方法
|
| InferEngineFactory |
Factory class for creating inference engine instances based on backend type.
根据后端类型创建推理引擎实例的工厂类
|
| OnnxRuntimeInferEngine |
ONNX Runtime inference engine implementation
ONNX Runtime推理引擎实现
|
| OpenVinoInferEngine |
OpenVINO inference engine implementation conforming to IModelInferEngine interface
OpenVINO推理引擎实现类，遵循IModelInferEngine接口
|
| IModelInferEngine |
Defines the core interface for model inference engines.
定义模型推理引擎的核心接口
|
| DeviceType |
Represents hardware device types available for inference operations.
表示可用于推理操作的硬件设备类型
|
| InferenceBackend |
Represents software inference backends supported by the system.
表示系统支持的软件推理后端
|
| OnnxRuntimeDeviceType |
Defines hardware acceleration device types supported by ONNX Runtime
定义ONNX Runtime支持的硬件加速设备类型
|