20,290
edits
Xavier/JetPack 5.0.2/Getting Started/Components: Difference between revisions
Xavier/JetPack 5.0.2/Getting Started/Components (view source)
Revision as of 18:11, 1 December 2020
, 1 December 2020no edit summary
mNo edit summary |
mNo edit summary |
||
| Line 47: | Line 47: | ||
Features: | Features: | ||
* Kernel version 4.9 | * Kernel version 4.9 | ||
* Support for 64-bit | * Support for 64-bit userspace and runtime libraries | ||
* Vulkan Support | * Vulkan Support | ||
* V4L2 media-controller driver support for camera sensors (bypassing ISP) | * V4L2 media-controller driver support for camera sensors (bypassing ISP) | ||
| Line 61: | Line 61: | ||
== Multimedia API == | == Multimedia API == | ||
Multimedia API also known as MMAPI is a collection of lower-level APIs that support application development. MMAPI is for developers who use a custom framework or wish to avoid a framework like GStreamer. | Multimedia API also is known as MMAPI is a collection of lower-level APIs that support application development. MMAPI is for developers who use a custom framework or wish to avoid a framework like GStreamer. | ||
MMAPI should be downloaded separately from the NVIDIA Jetson Download Center [https://developer.nvidia.com/embedded/dlc/l4t-multimedia-api-31-0-1 L4T Multimedia API 31.0.1 ] | MMAPI should be downloaded separately from the NVIDIA Jetson Download Center [https://developer.nvidia.com/embedded/dlc/l4t-multimedia-api-31-0-1 L4T Multimedia API 31.0.1 ] | ||
| Line 68: | Line 68: | ||
* '''Libargus''' for imaging applications. | * '''Libargus''' for imaging applications. | ||
* '''Buffer utility''' for buffer allocation, management and sharing. | * '''Buffer utility''' for buffer allocation, management, and sharing. | ||
* '''NVOSD''' for On-Screen display. | * '''NVOSD''' for On-Screen display. | ||
* '''V4l2 API extensions''' for video converter, decoder and encoder support. | * '''V4l2 API extensions''' for video converter, decoder and encoder support. | ||
* '''Aplication framework''' | * '''Aplication framework''' | ||
* '''Samples''' that | * '''Samples''' that demonstrate image processing with CUDA, object detection, and classification with cuDNN, TensorRT, and OpenCV4Tegra usage. | ||
== TensorRT == | == TensorRT == | ||
TensorRT is a C++ library that facilitates high performance inference on NVIDIA platforms. It is designed to work with the most popular deep learning frameworks, such as TensorFlow, Caffe, PyTorch etc. It | TensorRT is a C++ library that facilitates high-performance inference on NVIDIA platforms. It is designed to work with the most popular deep learning frameworks, such as TensorFlow, Caffe, PyTorch, etc. It focuses specifically on running an already trained model, to train the model, other libraries like cuDNN are more suitable. Some frameworks like TensorFlow have integrated TensorRT so that it can be used to accelerate inference within the framework. For other frameworks like Caffe, a parser is provided to generate a model that can be imported on TensorRT. For more information on using this library read our wiki [[Xavier/Deep_Learning/TensorRT|here]] | ||
== CUDA == | == CUDA == | ||
| Line 114: | Line 114: | ||
| Motion Estimation || Implements the NVIDIA Iterative Motion Estimation algorithm to estimate motion in a frame. | | Motion Estimation || Implements the NVIDIA Iterative Motion Estimation algorithm to estimate motion in a frame. | ||
|- | |- | ||
| OpenCV and NPP Interop || Shows interoperability of VisionWorks with the NPP and OpenCV library. It takes two images, blurs them and performs alpha blending between them. | | OpenCV and NPP Interop || Shows interoperability of VisionWorks with the NPP and OpenCV library. It takes two images, blurs them, and performs alpha blending between them. | ||
|- | |- | ||
| OpenGL Interop || Shows interoperability of VisionWorks and OpenGL. | | OpenGL Interop || Shows interoperability of VisionWorks and OpenGL. | ||