Sim is an open-source AI agent workflow builder. Sim's interface is a lightweight, intuitive way to rapidly build and deploy LLMs that connect with your favorite tools.

OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched

Model Zoo For OpenCV DNN and Benchmarks.

Object tracking implemented with YOLOv4, DeepSort, and TensorFlow.

The speechocean762 dataset for pronunciation scoring tasks.

Audio processing to compare two pronunciations.

Learn OpenCV : C++ and Python Examples

Expressive Body Capture: 3D Hands, Face, and Body from a Single Image

tracking person with yolo

中文语音识别; Mandarin Automatic Speech Recognition;

This is an update to faceit_live using first order model

Reconstructing real-time 3D faces from 2D images using deep learning.

An implementation of the classical 3DMM fitting algorithm

The PyTorch improved version of TPAMI 2017 paper: Face Alignment in Full Pose Range: A 3D Total Solution.

Face swap and 3D alignment from a single image based on PRNet

face swap presentation code from pydata 2018 warsaw https://www.youtube.com/watch?v=ExToU4KzDm8

Using encoder-decoder to restruct one face

Visualizer for deep learning and machine learning models

tensorboard for pytorch (and chainer, mxnet, numpy, ...)