Jetson Inference
DNN Vision Library
|
▼DNN Vision Library (jetson-inference) | C++ runtime library for supporting deep vision neural network models and inferencing with TensorRT. Available network primitives currently include: |
tensorNet | DNN abstract base class that provides TensorRT functionality underneath. These functions aren't typically accessed by end users unless they are implementing their own DNN class like imageNet or detectNet |
imageNet | Image recognition DNN (GoogleNet, AlexNet, ResNet) |
detectNet | Object detection DNN (SSD, DetectNet) |
segNet | Semantic segmentation DNN (FCN or Fully-Convolutional Networks) |
poseNet | Pose estimation DNN |
actionNet | Action/activity recognition DNN |
depthNet | Mono depth estimation from monocular images |
backgroundNet | Foreground/background segmentation and removal DNN |
Object Tracking | Object tracking used by detectNet |
Model Downloader | Utilities for automatically downloading pre-trained models |
▼Utilities Library (jetson-utils) | Tools and utilities for video streaming, codecs, display, and CUDA processing |
Camera Capture | Camera capture and streaming for MIPI CSI and V4L2 devices (deprecated) |
Codec | Hardware-accelerated video encoder and decoder (H.264/H.265) using GStreamer |
Command-Line Parsing | Parsing of command line arguments, flags, and variables |
CSV Parsing | Text file parsing for Comma-Separated Value (CSV) formats, with user-defined delimiters beyond just commas, including spaces, tabs, or other symbols |
▼CUDA | CUDA utilities and image processing kernels |
Color Mapping | Defines various colormaps and color mapping functions |
Color Conversion | Colorspace conversion functions for various YUV formats, RGB, BGR, Bayer, and grayscale |
Cropping | Crop an image to the specified region of interest (ROI) |
Drawing | Drawing basic 2D shapes using CUDA |
Error Checking | Error checking and logging macros |
Fonts | TTF font rasterization and image overlay rendering using CUDA |
Memory Management | Allocation of CUDA mapped zero-copy memory |
Normalization | Normalize the pixel intensities of an image between two ranges |
Overlay | Overlay images and vector shapes onto other images |
Pixel Filtering | CUDA device functions for sampling pixels with bilinear filtering |
Point Cloud | 3D point cloud processing and visualization |
Resize | Rescale an image to a different resolution |
Warping | Various image warps and matrix transforms |
Filesystem | Functions for listing files in directories and manipulating file paths |
Image Formats | Enumerations and helper functions for different types of image formats |
Image I/O | Loading and saving image files from disk |
Input | HID input devices including gamepad controllers, joysticks, and keyboard |
Logging | Message logging with a variable level of output and destinations |
Matrix | 3x3 matrix operations from mat33.h |
Multithreading | Mutex, events, threads, and process objects based on pthreads |
Networking | TCP/UDP sockets and IP address manipulation |
OpenGL | OpenGL textures and display window (X11/GLX) |
Time | Timestamping operations for measuring the timing of CPU code |
Video Streaming | VideoSource and videoOutput APIs for input and output video streams |