durgabhavaniv Goto Github PK

backscrub

Virtual Video Device for Background Replacement with Deep Semantic Segmentation

chips_challenge

color-tracking

This repo includes C++ Source for Color-based Ball Tracking Project

face_mask_detection_openvino

Detect faces and determine whether people are wearing mask.

face_mask_detection_system

face_reid_surveillance_system

Near Real-Time Face-reIdentification Surveillance System

ffmpeg-libav-tutorial

FFmpeg libav tutorial - learn how media works from basic to transmuxing, transcoding and more

ffmpeg-xma

fpga_as_a_service

generative-adversarial-networks

Introduction to generative adversarial networks, with code to accompany the O'Reilly tutorial on GANs

hello-world

inference

Reference implementations of inference benchmarks

media-recorder-api-demo

An implementation of the MediaStream Recording API

media_src

ml-suite

Getting Started with Xilinx ML Suite

models

Models and examples built with TensorFlow

mvmed-tracker

Multi-Object Tracker for the H.264 and MPEG-4 Compressed Domain.

open_model_zoo

Pre-trained Deep Learning models and samples (high quality and extremely fast)

opencv_gstreamer

Simple C++ example of using OpenCV with GStreamer

owt-client-javascript

Open WebRTC Toolkit JavaScript SDK

pptxtoimage

PPTXToImage using java and apache libs

quantum-mobile

Scripts to set up the Quantum Mobile Virtual Machine

resnet50-pynq

Quantized ResNet50 Dataflow Acceleration on Alveo, with PYNQ

spring-boot-file-upload-download-rest-api-example

Spring Boot File Upload / Download Rest API Example

tensorflow

An Open Source Machine Learning Framework for Everyone

u50-abr-video-transcode

Live video transcoding on Xilinx Alveo U50

video-compression-net

A new approach to video compression by refining the shortcomings of conventional approach and substituting each traditional component with their neural network counterpart. Our proposed work consists of motion estimation, compression and compensation and residue compression, learned end-to-end to minimize the rate-distortion trade off. The whole model is jointly optimized using a single loss function. Our work is based on a standard method to exploit the spatio-temporal redundancy in video frames to reduce the bit rate along with the minimization of distortions in decoded frames. We implement a neural network version of conventional video compression approach and encode the redundant frames with lower number of bit.

vitis-ai

Vitis AI is Xilinx’s development stack for AI inference on Xilinx hardware platforms, including both edge devices and Alveo cards.

xrt

Xilinx Run Time for FPGA