TensorRT
|
The TensorRT API version 1 namespace. More...
Classes | |
class | Dims |
structure to define the dimensions of a tensor More... | |
class | DimsHW |
descriptor for two-dimensional spatial data More... | |
class | DimsCHW |
descriptor for data with one channel dimension and two spatial dimensions More... | |
class | DimsNCHW |
descriptor for data with one index dimension, one channel dimension and two spatial dimensions More... | |
class | Weights |
an array of weights used as a layer parameter More... | |
class | IHostMemory |
class to handle library allocated memory that is accessible to the user. More... | |
class | ITensor |
a tensor in a network definition More... | |
class | ILayer |
base class for all layer classes in a network definition More... | |
class | IConvolutionLayer |
a convolution layer in a network definition More... | |
class | IFullyConnectedLayer |
a fully connected layer in a network definition More... | |
class | IActivationLayer |
an Activation layer in a network definition More... | |
class | IPoolingLayer |
a Pooling layer in a network definition More... | |
class | ILRNLayer |
a LRN layer in a network definition More... | |
class | IScaleLayer |
a Scale layer in a network definition More... | |
class | ISoftMaxLayer |
a Softmax layer in a network definition More... | |
class | IConcatenationLayer |
a concatenation layer in a network definition More... | |
class | IDeconvolutionLayer |
a deconvolution layer in a network definition More... | |
class | IElementWiseLayer |
a elementwise layer in a network definition More... | |
class | IRNNLayer |
a RNN layer in a network definition More... | |
class | IOutputDimensionsFormula |
application-implemented inteface to compute layer output sizes More... | |
class | IPlugin |
plugin class for user-implemented layers More... | |
class | IPluginLayer |
layer type for plugins More... | |
class | IUnaryLayer |
layer that represents a unary operation More... | |
class | IPaddingLayer |
layer that represents a padding operation More... | |
struct | Permutation |
class | IShuffleLayer |
layer type for shuffling data More... | |
class | INetworkDefinition |
a network definition for input to the builder More... | |
class | IProfiler |
application-implemented interface for profiling More... | |
class | IExecutionContext |
context for executing inference using an engine More... | |
class | ICudaEngine |
an engine for executing inference on a built network More... | |
class | IInt8Calibrator |
application-implemented interface for calibration More... | |
class | IInt8EntropyCalibrator |
class | IInt8LegacyCalibrator |
class | IBuilder |
builds an engine from a network definition More... | |
class | IPluginFactory |
plugin factory for deserialization More... | |
class | IRuntime |
allows a serialized engine to be deserialized More... | |
class | ILogger |
application-implemented logging interface for the builder, engine and runtime. More... | |
Functions | |
template<typename T > | |
int | EnumMax () |
maximum number of elements in an enumeration type | |
template<> | |
int | EnumMax< DataType > () |
maximum number of elements in DataType enum. More... | |
template<> | |
int | EnumMax< DimensionType > () |
maximum number of elements in DimensionType enum. More... | |
template<> | |
int | EnumMax< LayerType > () |
maximum number of elements in LayerType enum. More... | |
template<> | |
int | EnumMax< ActivationType > () |
maximum number of elements in ActivationType enum. More... | |
template<> | |
int | EnumMax< PoolingType > () |
maximum number of elements in PoolingType enum. More... | |
template<> | |
int | EnumMax< ScaleMode > () |
maximum number of elements in ScaleMode enum. More... | |
template<> | |
int | EnumMax< ElementWiseOperation > () |
maximum number of elements in ElementWiseOperation enum. More... | |
template<> | |
int | EnumMax< RNNOperation > () |
maximum number of elements in RNNOperation enum. More... | |
template<> | |
int | EnumMax< RNNDirection > () |
maximum number of elements in RNNDirection enum. More... | |
template<> | |
int | EnumMax< RNNInputMode > () |
maximum number of elements in RNNInputMode enum. More... | |
template<> | |
int | EnumMax< UnaryOperation > () |
maximum number of elements in ElementWiseOperation enum. More... | |
template<> | |
int | EnumMax< CalibrationAlgoType > () |
maximum number of elements in CalibrationAlgoType enum. More... | |
template<> | |
int | EnumMax< ILogger::Severity > () |
maximum number of elements in DataType enum. More... | |
template<> | |
int | EnumMax< PluginType > () |
maximum number of elements in PluginType enum. More... | |
The TensorRT API version 1 namespace.
|
strong |
|
strong |
version of calibration algorithm to use
enum CalibrationAlgoType
|
strong |
|
strong |
|
strong |
enumerates the binary operations that may be performed by an ElementWise layer
|
strong |
the type values of layer classes
|
strong |
the type values for the various plugins
|
strong |
enumerates the RNN direction that may be performed by an RNN layer
Enumerator | |
---|---|
kUNIDIRECTION |
Network iterations from first input to last input. |
kBIDIRECTION |
Network iterates from first to last and vice versa and outputs concatenated. |
|
strong |
enumerates the RNN input modes that may occur with an RNN layer
Enumerator | |
---|---|
kLINEAR |
Perform the normal matrix multiplication in the first recurrent layer. |
kSKIP |
No operation is performed on the first recurrent layer. |
|
strong |
enumerates the RNN operations that may be performed by an RNN layer
Equation definitions: i - input gate o - output gate f - forget gate z - update gate r - reset gate c - cell gate h - hidden gate t - time step(t-1 means previous time step) Xi - input tensor W[izrfcoh] - W parameter weight matrices for the corresponding gates R[izrfcoh] - U parameter weight matrices for the corresponding gates Wb[izrfcoh] - W parameter bias vectors for the corresponding gates Rb[izrfcoh] - U parameter bias vectors for the corresponding gates ReLU(X) - max(X, 0) tanh - hyperbolic tangent of X sigmoid(X) - 1 / (1 + e^-X) [C|H] - Cell/Hidden state
|
strong |
controls how scale is applied in a Scale layer
Enumerator | |
---|---|
kUNIFORM |
identical coefficients across all elements of the tensor |
kCHANNEL |
per-channel coefficients |
kELEMENTWISE |
elementwise coefficients |
|
strong |
enumerates the binary operations that may be performed by an ElementWise layer
Enumerator | |
---|---|
kEXP |
exponentiation |
kLOG |
log (base e) |
kSQRT |
square root |
kRECIP |
reciprocal |
kABS |
absolute value |
kNEG |
negation |
|
inline |
maximum number of elements in ActivationType enum.
|
inline |
maximum number of elements in CalibrationAlgoType enum.
|
inline |
maximum number of elements in DataType enum.
|
inline |
maximum number of elements in DimensionType enum.
|
inline |
maximum number of elements in ElementWiseOperation enum.
|
inline |
maximum number of elements in DataType enum.
|
inline |
maximum number of elements in LayerType enum.
|
inline |
maximum number of elements in PluginType enum.
|
inline |
maximum number of elements in PoolingType enum.
|
inline |
maximum number of elements in RNNDirection enum.
|
inline |
maximum number of elements in RNNInputMode enum.
|
inline |
maximum number of elements in RNNOperation enum.
|
inline |
maximum number of elements in ScaleMode enum.
|
inline |
maximum number of elements in ElementWiseOperation enum.