nvcaffeparser1 | |
IBlobNameToTensor | Object used to store and query Tensors after they have been extracted from a Caffe model using the ICaffeParser |
IBinaryProtoBlob | Object used to store and query data extracted from a binaryproto file using the ICaffeParser |
IPluginFactory | Plugin factory used to configure plugins |
IPluginFactoryExt | Plugin factory used to configure plugins with added support for TRT versioning |
ICaffeParser | Class used for parsing Caffe models |
nvinfer1 | The TensorRT API version 1 namespace |
plugin | |
INvPlugin | Common interface for the Nvidia created plugins |
Quadruple | The Permute plugin layer permutes the input tensor by changing the memory order of the data. Quadruple defines a structure that contains an array of 4 integers. They can represent the permute orders or the strides in each dimension |
PriorBoxParameters | The PriorBox plugin layer generates the prior boxes of designated sizes and aspect ratios across all dimensions . PriorBoxParameters defines a set of parameters for creating the PriorBox plugin layer. It contains: |
GridAnchorParameters | The Anchor Generator plugin layer generates the prior boxes of designated sizes and aspect ratios across all dimensions . GridAnchorParameters defines a set of parameters for creating the plugin layer for all feature maps. It contains: |
DetectionOutputParameters | The DetectionOutput plugin layer generates the detection output based on location and confidence predictions by doing non maximum suppression. DetectionOutputParameters defines a set of parameters for creating the DetectionOutput plugin layer. It contains: |
softmaxTree | The Region plugin layer performs region proposal calculation: generate 5 bounding boxes per cell (for yolo9000, generate 3 bounding boxes per cell). For each box, calculating its probablities of objects detections from 80 pre-defined classifications (yolo9000 has 9416 pre-defined classifications, and these 9416 items are organized as work-tree structure). RegionParameters defines a set of parameters for creating the Region plugin layer |
RegionParameters | |
Dims | Structure to define the dimensions of a tensor |
Dims2 | Descriptor for two-dimensional data |
DimsHW | Descriptor for two-dimensional spatial data |
Dims3 | Descriptor for three-dimensional data |
DimsCHW | Descriptor for data with one channel dimension and two spatial dimensions |
Dims4 | Descriptor for four-dimensional data |
DimsNCHW | Descriptor for data with one index dimension, one channel dimension and two spatial dimensions |
Weights | An array of weights used as a layer parameter |
IHostMemory | Class to handle library allocated memory that is accessible to the user |
ITensor | A tensor in a network definition |
ILayer | Base class for all layer classes in a network definition |
IConvolutionLayer | A convolution layer in a network definition |
IFullyConnectedLayer | A fully connected layer in a network definition. This layer expects an input tensor of three or more non-batch dimensions. The input is automatically reshaped into an MxV tensor X , where V is a product of the last three dimensions and M is a product of the remaining dimensions (where the product over 0 dimensions is defined as 1). For example: |
IActivationLayer | An Activation layer in a network definition |
IPoolingLayer | A Pooling layer in a network definition |
ILRNLayer | A LRN layer in a network definition |
IScaleLayer | A Scale layer in a network definition |
ISoftMaxLayer | A Softmax layer in a network definition |
IConcatenationLayer | A concatenation layer in a network definition |
IDeconvolutionLayer | A deconvolution layer in a network definition |
IElementWiseLayer | A elementwise layer in a network definition |
IGatherLayer | |
IRNNLayer | A RNN layer in a network definition |
IRNNv2Layer | An RNN layer in a network definition, version 2 |
IOutputDimensionsFormula | Application-implemented interface to compute layer output sizes |
IPlugin | Plugin class for user-implemented layers |
IPluginExt | Plugin class for user-implemented layers |
IPluginLayer | Layer type for plugins |
IUnaryLayer | Layer that represents an unary operation |
IReduceLayer | Layer that represents a reduction operator |
IPaddingLayer | Layer that represents a padding operation |
Permutation | |
IShuffleLayer | Layer type for shuffling data |
ITopKLayer | Layer that represents a TopK reduction |
IMatrixMultiplyLayer | Layer that represents a Matrix Multiplication |
IRaggedSoftMaxLayer | A RaggedSoftmax layer in a network definition |
IConstantLayer | Layer that represents a constant value |
INetworkDefinition | A network definition for input to the builder |
IProfiler | Application-implemented interface for profiling |
IExecutionContext | Context for executing inference using an engine |
ICudaEngine | An engine for executing inference on a built network |
IInt8Calibrator | Application-implemented interface for calibration |
IInt8EntropyCalibrator | |
IInt8LegacyCalibrator | |
IGpuAllocator | Application-implemented class for controlling allocation on the GPU |
IBuilder | Builds an engine from a network definition |
IPluginFactory | Plugin factory for deserialization |
IRuntime | Allows a serialized engine to be deserialized |
ILogger | Application-implemented logging interface for the builder, engine and runtime |
nvonnxparser | |
IOnnxConfig | Configuration Manager Class |
IONNXParser | ONNX Parser Class |
nvuffparser | |
FieldMap | An array of field params used as a layer parameter for plugin layers |
FieldCollection | |
IPluginFactory | Plugin factory used to configure plugins |
IPluginFactoryExt | Plugin factory used to configure plugins with added support for TRT versioning |
IUffParser | Class used for parsing models described using the UFF format |