org.bytedeco.tensorrt.global

Class nvinfer_plugin

java.lang.Object

org.bytedeco.tensorrt.presets.nvinfer_plugin

org.bytedeco.tensorrt.global.nvinfer_plugin

All Implemented Interfaces:

InfoMapper

public class nvinfer_plugin
extends nvinfer_plugin

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	nvinfer_plugin.CodeTypeSSD \enum CodeTypeSSD \brief The type of encoding used for decoding the bounding boxes and loc_data.

Constructor Summary

Constructors

Constructor and Description
nvinfer_plugin()

Method Summary

Modifier and Type	Method and Description
static IPluginV2	createAnchorGeneratorPlugin(GridAnchorParameters param, int numLayers) \brief The Grid Anchor Generator plugin layer generates the prior boxes of designated sizes and aspect ratios across all dimensions (H x W) for all feature maps.
static IPluginV2	createBatchedNMSPlugin(NMSParameters param) \brief The BatchedNMS Plugin performs non_max_suppression on the input boxes, per batch, across all classes.
static IPluginV2	createInstanceNormalizationPlugin(float epsilon, Weights scale_weights, Weights bias_weights) \brief The Instance Normalization Plugin computes the instance normalization of an input tensor.
static IPluginV2	createNMSPlugin(DetectionOutputParameters param) \brief The DetectionOutput plugin layer generates the detection output based on location and confidence predictions by doing non maximum suppression.
static IPluginV2	createNormalizePlugin(Weights scales, boolean acrossSpatial, boolean channelShared, float eps) \brief The Normalize plugin layer normalizes the input to have L2 norm of 1 with scale learnable.
static IPluginV2	createPriorBoxPlugin(PriorBoxParameters param) \brief The PriorBox plugin layer generates the prior boxes of designated sizes and aspect ratios across all dimensions (H x W).
static IPluginV2	createRegionPlugin(RegionParameters params) \brief The Region plugin layer performs region proposal calculation: generate 5 bounding boxes per cell (for yolo9000, generate 3 bounding boxes per cell).
static IPluginV2	createReorgPlugin(int stride) \brief The Reorg plugin reshapes input of shape CxHxW into a (C*stride*stride)x(H/stride)x(W/stride) shape, used in YOLOv2.
static IPluginV2	createRPNROIPlugin(int featureStride, int preNmsTop, int nmsMaxOut, float iouThreshold, float minBoxSize, float spatialScale, DimsHW pooling, Weights anchorRatios, Weights anchorScales) \brief Create a plugin layer that fuses the RPN and ROI pooling using user-defined parameters.
static IPluginV2	createSplitPlugin(int axis, int[] output_lengths, int noutput)
static IPluginV2	createSplitPlugin(int axis, IntBuffer output_lengths, int noutput)
static IPluginV2	createSplitPlugin(int axis, IntPointer output_lengths, int noutput) \brief The Split Plugin performs a split operation on the input tensor.
static boolean	initLibNvInferPlugins(Pointer logger, BytePointer libNamespace)
static boolean	initLibNvInferPlugins(Pointer logger, String libNamespace) \brief Initialize and register all the existing TensorRT plugins to the Plugin Registry with an optional namespace.

Methods inherited from class org.bytedeco.tensorrt.presets.nvinfer_plugin

map

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

nvinfer_plugin

public nvinfer_plugin()

Method Detail

createRPNROIPlugin

public static IPluginV2 createRPNROIPlugin(int featureStride,
                                           int preNmsTop,
                                           int nmsMaxOut,
                                           float iouThreshold,
                                           float minBoxSize,
                                           float spatialScale,
                                           @ByVal
                                           DimsHW pooling,
                                           @ByVal
                                           Weights anchorRatios,
                                           @ByVal
                                           Weights anchorScales)

\brief Create a plugin layer that fuses the RPN and ROI pooling using user-defined parameters. Registered plugin type "RPROI_TRT". Registered plugin version "1".

Parameters:

featureStride - Feature stride.

preNmsTop - Number of proposals to keep before applying NMS.

nmsMaxOut - Number of remaining proposals after applying NMS.

iouThreshold - IoU threshold.

minBoxSize - Minimum allowed bounding box size before scaling.

spatialScale - Spatial scale between the input image and the last feature map.

pooling - Spatial dimensions of pooled ROIs.

anchorRatios - Aspect ratios for generating anchor windows.

anchorScales - Scales for generating anchor windows.

Returns:

Returns a FasterRCNN fused RPN+ROI pooling plugin. Returns nullptr on invalid inputs.

createNormalizePlugin

public static IPluginV2 createNormalizePlugin(@Const
                                              Weights scales,
                                              @Cast(value="bool")
                                              boolean acrossSpatial,
                                              @Cast(value="bool")
                                              boolean channelShared,
                                              float eps)

\brief The Normalize plugin layer normalizes the input to have L2 norm of 1 with scale learnable. Registered plugin type "Normalize_TRT". Registered plugin version "1".

Parameters:

scales - Scale weights that are applied to the output tensor.

acrossSpatial - Whether to compute the norm over adjacent channels (acrossSpatial is true) or nearby spatial locations (within channel in which case acrossSpatial is false).

channelShared - Whether the scale weight(s) is shared across channels.

eps - Epsilon for not dividing by zero.

createPriorBoxPlugin

public static IPluginV2 createPriorBoxPlugin(@ByVal
                                             PriorBoxParameters param)

\brief The PriorBox plugin layer generates the prior boxes of designated sizes and aspect ratios across all dimensions (H x W). PriorBoxParameters defines a set of parameters for creating the PriorBox plugin layer. Registered plugin type "PriorBox_TRT". Registered plugin version "1".

createAnchorGeneratorPlugin

public static IPluginV2 createAnchorGeneratorPlugin(GridAnchorParameters param,
                                                    int numLayers)

\brief The Grid Anchor Generator plugin layer generates the prior boxes of designated sizes and aspect ratios across all dimensions (H x W) for all feature maps. GridAnchorParameters defines a set of parameters for creating the GridAnchorGenerator plugin layer. Registered plugin type "GridAnchor_TRT". Registered plugin version "1".

createNMSPlugin

public static IPluginV2 createNMSPlugin(@ByVal
                                        DetectionOutputParameters param)

\brief 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. Registered plugin type "NMS_TRT". Registered plugin version "1".

createReorgPlugin

public static IPluginV2 createReorgPlugin(int stride)

\brief The Reorg plugin reshapes input of shape CxHxW into a (C*stride*stride)x(H/stride)x(W/stride) shape, used in YOLOv2. It does that by taking 1 x stride x stride slices from tensor and flattening them into (stride x stride) x 1 x 1 shape. Registered plugin type "Reorg_TRT". Registered plugin version "1".

Parameters:

stride - Strides in H and W, it should divide both H and W. Also stride * stride should be less than or equal to C.

createRegionPlugin

public static IPluginV2 createRegionPlugin(@ByVal
                                           RegionParameters params)

\brief 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. Registered plugin type "Region_TRT". Registered plugin version "1".

createBatchedNMSPlugin

public static IPluginV2 createBatchedNMSPlugin(@ByVal
                                               NMSParameters param)

\brief The BatchedNMS Plugin performs non_max_suppression on the input boxes, per batch, across all classes. It greedily selects a subset of bounding boxes in descending order of score. Prunes away boxes that have a high intersection-over-union (IOU) overlap with previously selected boxes. Bounding boxes are supplied as [y1, x1, y2, x2], where (y1, x1) and (y2, x2) are the coordinates of any diagonal pair of box corners and the coordinates can be provided as normalized (i.e., lying in the interval [0, 1]) or absolute. The plugin expects two inputs. Input0 is expected to be 4-D float boxes tensor of shape [batch_size, num_boxes, q, 4], where q can be either 1 (if shareLocation is true) or num_classes. Input1 is expected to be a 3-D float scores tensor of shape [batch_size, num_boxes, num_classes] representing a single score corresponding to each box. The plugin returns four outputs. num_detections : A [batch_size] int32 tensor indicating the number of valid detections per batch item. Can be less than keepTopK. Only the top num_detections[i] entries in nmsed_boxes[i], nmsed_scores[i] and nmsed_classes[i] are valid. nmsed_boxes : A [batch_size, max_detections, 4] float32 tensor containing the co-ordinates of non-max suppressed boxes. nmsed_scores : A [batch_size, max_detections] float32 tensor containing the scores for the boxes. nmsed_classes : A [batch_size, max_detections] float32 tensor containing the classes for the boxes. Registered plugin type "BatchedNMS_TRT". Registered plugin version "1". The batched NMS plugin can require a lot of workspace due to intermediate buffer usage. To get the estimated workspace size for the plugin for a batch size, use the API plugin->getWorkspaceSize(batchSize).

createSplitPlugin

public static IPluginV2 createSplitPlugin(int axis,
                                          IntPointer output_lengths,
                                          int noutput)

\brief The Split Plugin performs a split operation on the input tensor. It splits the input tensor into several output tensors, each of a length corresponding to output_lengths. The split occurs along the axis specified by axis.

Parameters:

axis - The axis to split on.

output_lengths - The lengths of the output tensors.

noutput - The number of output tensors.

createSplitPlugin

public static IPluginV2 createSplitPlugin(int axis,
                                          IntBuffer output_lengths,
                                          int noutput)

createSplitPlugin

public static IPluginV2 createSplitPlugin(int axis,
                                          int[] output_lengths,
                                          int noutput)

createInstanceNormalizationPlugin

public static IPluginV2 createInstanceNormalizationPlugin(float epsilon,
                                                          @ByVal
                                                          Weights scale_weights,
                                                          @ByVal
                                                          Weights bias_weights)

\brief The Instance Normalization Plugin computes the instance normalization of an input tensor. The instance normalization is calculated as found in the paper https://arxiv.org/abs/1607.08022. The calculation is y = scale * (x - mean) / sqrt(variance + epsilon) + bias where mean and variance are computed per instance per channel.

Parameters:

epsilon - The epsilon value to use to avoid division by zero.

scale_weights - The input 1-dimensional scale weights of size C to scale.

bias_weights - The input 1-dimensional bias weights of size C to offset.

initLibNvInferPlugins

@Cast(value="bool")
public static boolean initLibNvInferPlugins(Pointer logger,
                                                                 String libNamespace)

\brief Initialize and register all the existing TensorRT plugins to the Plugin Registry with an optional namespace. The plugin library author should ensure that this function name is unique to the library. This function should be called once before accessing the Plugin Registry.

Parameters:

logger - Logger object to print plugin registration information

libNamespace - Namespace used to register all the plugins in this library

initLibNvInferPlugins

@Cast(value="bool")
public static boolean initLibNvInferPlugins(Pointer logger,
                                                                 @Cast(value="const char*")
                                                                 BytePointer libNamespace)