apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-25 01:20:43 +08:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity
Files
ae08bc8c893b3205a36780db254ce5327a9ffb5d
FastDeploy/streamer
History
Wang Xinyu 81eaeddbd0 [Streamer] Basic framework, YAML parser, ppyoloe demo and video decoder demo (#863) 
* support trt installed in sys dir

* streamer init

* link elements and run

* create source bin

* add config

* restruct dirs

* set property

* link elements

* integrate perf

* add bbox parser

* parse yaml to string, video decoder

* use try pull for decoder and nits

* streamer ppyoloe cpp

* update readme

* video decoder cpp dir

* add cn readme

* update readme

* cmake nits

* refactor perf measurement
2022-12-19 10:14:17 +08:00
..
examples
[Streamer] Basic framework, YAML parser, ppyoloe demo and video decoder demo (#863)
2022-12-19 10:14:17 +08:00
src
[Streamer] Basic framework, YAML parser, ppyoloe demo and video decoder demo (#863)
2022-12-19 10:14:17 +08:00
CMakeLists.txt
[Streamer] Basic framework, YAML parser, ppyoloe demo and video decoder demo (#863)
2022-12-19 10:14:17 +08:00
README_CN.md
[Streamer] Basic framework, YAML parser, ppyoloe demo and video decoder demo (#863)
2022-12-19 10:14:17 +08:00
README_EN.md
[Streamer] Basic framework, YAML parser, ppyoloe demo and video decoder demo (#863)
2022-12-19 10:14:17 +08:00
README.md
[Streamer] Basic framework, YAML parser, ppyoloe demo and video decoder demo (#863)
2022-12-19 10:14:17 +08:00

README_EN.md

English | 简体中文

FastDeploy Streamer

Introduction

FastDeploy Streamer (FDStreamer) is an AI multimedia stream processing framework that arranges functions such as AI inference, audio and video decoding, encoding, and streaming in the form of pipeline, to enable end-to-end optimization and deployment of AI applications.

Currently FDStreamer is only compatible with NVIDIA GPU/Jetson platform, please look forward to more hardware and platform support.

Environment

Jetson

  • DeepStream 6.1+

x86 GPU

Install DeepStream 6.1.1 and dependencies manually，or use below docker：

docker pull nvcr.io/nvidia/deepstream:6.1.1-devel

Build

  1. Build FastDeploy, or download FastDeploy prebuilt libraries

  2. Build Streamer

cd FastDeploy/streamer/
mkdir build && cd build/

# Download FastDeploy prebuilt libraries, please check `FastDeploy prebuilt libraries` above.
wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-x.x.x.tgz
tar xvf fastdeploy-linux-x64-x.x.x.tgz
cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-x.x.x
make -j
  1. Build and Run Example
Example Brief
PP-YOLOE Multiple input videos, PP-YOLOE object detection, NvTracker, Hardware codec, writing to mp4 file
Video Decoder Video decoding using hardward