NVIDIA NvNeural SDK
2022.2
GPU inference framework for NVIDIA Nsight Deep Learning Designer
|
Structure describing an activation function (IActivationFunction) for tool interfaces and network builders. More...
#include <nvneural/CoreTypes.h>
Public Attributes | |
ActivationFunctionId | activationFunction |
This is the activation function ID implemented by this activation function. | |
NetworkBackendId | backend |
This is the backend identifier supported by this instance of the activation function. More... | |
std::size_t | numParameters |
This is the number of parameters supported for this activation. More... | |
const char * | pDisplayName |
An optional human-readable layer name. More... | |
const char * | pDocumentation |
An optional human-readable descriptive text. More... | |
const char * | pObjectClass |
This is the programmatic class name used to instantiate the activation object through the IPlugin::createObject interface. More... | |
const ParamDesc * | pParameters |
This is the pointer to the contiguous memory of ParamDesc structs. More... | |
const char * | pSerializedName |
This is the name used to represent the activation function in serialized form. More... | |
std::size_t | structSize |
This is the sizeof() this struct. More... | |
TensorFormat | tensorFormat |
This is the tensor format supported by this activation function. More... | |
Structure describing an activation function (IActivationFunction) for tool interfaces and network builders.
All contained pointers must be valid for the lifetime of the relevant IPlugin object.
NetworkBackendId nvneural::ActivationDesc::backend |
This is the backend identifier supported by this instance of the activation function.
Activation functions supporting multiple backends should expose multiple ActivationDesc instances.
std::size_t nvneural::ActivationDesc::numParameters |
This is the number of parameters supported for this activation.
Those are described in the ParamDesc structure.
const char* nvneural::ActivationDesc::pDisplayName |
An optional human-readable layer name.
Generally used in host editor. If this is not defined (nullptr) then pSerializedName will be used. String should be treated as UTF-8.
Example: "Leaky ReLU"
const char* nvneural::ActivationDesc::pDocumentation |
An optional human-readable descriptive text.
Generally used in host editor. String should be treated as UTF-8.
const char* nvneural::ActivationDesc::pObjectClass |
This is the programmatic class name used to instantiate the activation object through the IPlugin::createObject interface.
Example: "com.nvidia.activations.relu"
const ParamDesc* nvneural::ActivationDesc::pParameters |
This is the pointer to the contiguous memory of ParamDesc structs.
The number of these structs in the memory block is defined in numParameters. Each struct describes a particular parameter.
const char* nvneural::ActivationDesc::pSerializedName |
This is the name used to represent the activation function in serialized form.
Examples: "relu", "leaky_tanh", "leaky_sigmoid"
std::size_t nvneural::ActivationDesc::structSize |
This is the sizeof() this struct.
It is used for versioning, for instance, one plugin could have an earlier version of this struct and the host a later version and thus, their structSize would be different.
TensorFormat nvneural::ActivationDesc::tensorFormat |
This is the tensor format supported by this activation function.
Activation functions supporting multiple tensor formats should expose multiple ActivationDesc instances.