Apollo 10.0
自动驾驶开放平台
|
#include <model_base.h>
Public 成员函数 | |
ModelBase () | |
~ModelBase () | |
virtual bool | Init ()=0 |
parse model description class and load the model | |
virtual bool | Inference (const std::vector< void * > &input_buffer, unsigned int input_size, std::vector< void * > *output_buffer, unsigned int output_size)=0 |
performing network inference | |
virtual bool | LoadModel ()=0 |
load the model from file | |
virtual void | Destory ()=0 |
free all memory requested, gpu or cpu | |
Public 属性 | |
std::string | model_path_ |
uint8_t | init_ = 0 |
在文件 model_base.h 第 25 行定义.
|
inline |
在文件 model_base.h 第 27 行定义.
|
inline |
在文件 model_base.h 第 28 行定义.
|
pure virtual |
free all memory requested, gpu or cpu
在 apollo::prediction::MultiAgentPedestrianCpuTorch, apollo::prediction::MultiAgentPedestrianGpuTorch, apollo::prediction::MultiAgentVehicleCpuTorch, apollo::prediction::MultiAgentVehicleGpuTorch, apollo::prediction::SemanticLstmPedestrianCpuTorch, apollo::prediction::SemanticLstmPedestrianGpuTorch, apollo::prediction::SemanticLstmVehicleCpuTorch , 以及 apollo::prediction::SemanticLstmVehicleGpuTorch 内被实现.
|
pure virtual |
performing network inference
input_buffer | vector of input tensor |
input_size | size of input_buffer |
output_buffer | vector of output tensor |
output_size | size of output_buffer |
在 apollo::prediction::MultiAgentPedestrianCpuTorch, apollo::prediction::MultiAgentPedestrianGpuTorch, apollo::prediction::MultiAgentVehicleCpuTorch, apollo::prediction::MultiAgentVehicleGpuTorch, apollo::prediction::SemanticLstmPedestrianCpuTorch, apollo::prediction::SemanticLstmPedestrianGpuTorch, apollo::prediction::SemanticLstmVehicleCpuTorch , 以及 apollo::prediction::SemanticLstmVehicleGpuTorch 内被实现.
|
pure virtual |
parse model description class and load the model
config_path | the model config |
在 apollo::prediction::MultiAgentPedestrianCpuTorch, apollo::prediction::MultiAgentPedestrianGpuTorch, apollo::prediction::MultiAgentVehicleCpuTorch, apollo::prediction::MultiAgentVehicleGpuTorch, apollo::prediction::SemanticLstmPedestrianCpuTorch, apollo::prediction::SemanticLstmPedestrianGpuTorch, apollo::prediction::SemanticLstmVehicleCpuTorch , 以及 apollo::prediction::SemanticLstmVehicleGpuTorch 内被实现.
|
pure virtual |
load the model from file
在 apollo::prediction::MultiAgentPedestrianCpuTorch, apollo::prediction::MultiAgentPedestrianGpuTorch, apollo::prediction::MultiAgentVehicleCpuTorch, apollo::prediction::MultiAgentVehicleGpuTorch, apollo::prediction::SemanticLstmPedestrianCpuTorch, apollo::prediction::SemanticLstmPedestrianGpuTorch, apollo::prediction::SemanticLstmVehicleCpuTorch , 以及 apollo::prediction::SemanticLstmVehicleGpuTorch 内被实现.
uint8_t apollo::prediction::ModelBase::init_ = 0 |
在文件 model_base.h 第 67 行定义.
std::string apollo::prediction::ModelBase::model_path_ |
在文件 model_base.h 第 66 行定义.