mqchen1993's starred repositories
albumentations
Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125
Llama-Chinese
Llama中文社区,Llama3在线体验和微调模型已开放,实时汇总最新Llama3学习资料,已将所有代码更新适配Llama3,构建最好的中文Llama大模型,完全开源可商用
deepdoctection
A Repo For Document AI
SadTalker-Video-Lip-Sync
本项目基于SadTalkers实现视频唇形合成的Wav2lip。通过以视频文件方式进行语音驱动生成唇形,设置面部区域可配置的增强方式进行合成唇形(人脸)区域画面增强,提高生成唇形的清晰度。使用DAIN 插帧的DL算法对生成视频进行补帧,补充帧间合成唇形的动作过渡,使合成的唇形更为流畅、真实以及自然。
awesome-industrial-anomaly-detection
Paper list and datasets for industrial image anomaly/defect detection (updating). 工业异常/瑕疵检测论文及数据集检索库(持续更新)。
SystemAnimatorOnline
XR Animator, AI-based Full Body Motion Capture and Extended Reality (XR) solution, powered by System Animator Online
avatars4all
Live real-time avatars from your webcam in the browser. No dedicated hardware or software installation needed. A pure Google Colab wrapper for live First-order-motion-model, aka Avatarify in the browser. And other Colabs providing an accessible interface for using FOMM, Wav2Lip and Liquid-warping-GAN with your own media and a rich GUI.
Audio2Head
code for paper "Audio2Head: Audio-driven One-shot Talking-head Generation with Natural Head Motion" in the conference of IJCAI 2021
Data_Augmentation_Zoo_for_Object_Detection
Includes: Learning data augmentation strategies for object detection | GridMask data augmentation | Augmentation for small object detection in Numpy. Use RetinaNet with ResNet-18 to test these methods on VOC and KITTI.
Awesome-LLM-Tabular
Awesome-LLM-Tabular: a curated list of Large Language Model applied to Tabular Data
MetaDialog
Platform for few-shot natural language processing: Text Classification, Sequene Labeling.
DiffGesture
[CVPR 2023] Taming Diffusion Models for Audio-Driven Co-Speech Gesture Generation
Data-Augmentation-for-Object-Detection-YOLO-
This is a python based library to augment the training dataset for object detection using YOLO.
data_generator_object_detection_2d
A data generator for 2D object detection
llm-open-domain-table-reasoner
Official implementation of OpenTab (ICLR2024)