The standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.

Use supervised learning to illuminate the latent space of GAN for controlled generation and edit

Label images and video for Computer Vision applications

PyTorch code for "PSGAN: Pose and Expression Robust Spatial-Aware GAN for Customizable Makeup Transfer" (CVPR 2020 Oral)

Code for the paper: Audio-Visual Scene Analysis with Self-Supervised Multisensory Features

A minimum example of aligning language models with RLHF similar to ChatGPT

Fast running Live Portrait with TensorRT and ONNX models

Real-time Python demos of google mediapipe

Zalo AI chalenge Voice Gender classification (https://challenge.zalo.ai/)

The Simple project to separate mixed voice. Using "Permutation Invariant Training Loss" and "PairWise Neg SisDr Loss"

This is the official implementation of the Video Dialog as Conversation about Objects Living in Space-Time paper

An Implementation of Heatmap Regression via Randomized Rounding

A small TensorFlow project created to test some machine learning problems

A system for Human-Object Interaction (HOI) in real scene.

An impementation of CNN Fixations for PyTorch.

Retinaface get 80.99% in widerface hard val using mobilenet0.25.