mathpopo

nanoDet-2

PSP

PSP

arrayfire

ArrayFire: a general purpose GPU library.

Audio-driven-TalkingFace-HeadPose

Code for "Audio-driven Talking Face Video Generation with Learning-based Personalized Head Pose"

bitsandbytes

Library for 8-bit optimizers and quantization routines.

buildx-pytorch-jetson

Building Pytorch wheel for arm64/aarch64 on amd64

compression

Data compression in TensorFlow

cvpods

All-in-one Toolbox for Computer Vision Research.

face-alignment

:fire: 2D and 3D Face alignment library build using pytorch

flashlight

A C++ standalone library for machine learning

Lip2Wav

This is the repository containing codes for our CVPR, 2020 paper titled "Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis"

LipGAN

This repository contains the codes for LipGAN. LipGAN was published as a part of the paper titled "Towards Automatic Face-to-Face Translation".

Machine_Learning_Code_Implementation

Mathematical derivation and pure Python code implementation of machine learning algorithms.

mdetr

MeshTransformer

Research code for CVPR 2021 paper "End-to-End Human Pose and Mesh Reconstruction with Transformers"

mmdetection-mini

mmdetection最小学习版

NAM

NeuralDubber

The project page repo for Neural Dubber.

onnx-tensorrt

ONNX-TensorRT: TensorRT backend for ONNX

onnxruntime-riscv

Fork of upstream onnxruntime focused on supporting risc-v accelerators

PaddleDetection

Object detection and instance segmentation toolkit based on PaddlePaddle.

PS-ViT

Official implementation of the paper Vision Transformer with Progressive Sampling, ICCV 2021.

riscv-aosp

Patches & Script for AOSP to run on Xuantie RISC-V CPU

Talking-Face_PC-AVS

Code for Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation (CVPR 2021)

TensorRT

TensorRT is a C++ library for high performance inference on NVIDIA GPUs and deep learning accelerators.

toit

Program your microcontrollers in a fast and robust high-level language.

tracking-pipeline

Voice2Mesh

Voice2Mesh: Cross-Modal 3D Face Model Generation from Voices

vortex

voxceleb_trainer

In defence of metric learning for speaker recognition