vince-cv Goto Github PK
Name: Xunzhe Wen
Type: User
Bio: Computer Vision / Sensor Fusion / Perceptual Algorithm RD.
Location: Beijing, China
Name: Xunzhe Wen
Type: User
Bio: Computer Vision / Sensor Fusion / Perceptual Algorithm RD.
Location: Beijing, China
Estimations and Wiener solutions; FIR filter banks based on STFT (short-time Fourier Transform ); Steepest descent and Newton method; Adaptive algorithms.
Deep learning case studies with a popular deep learning framework Tensorflow, which included contents as Softmax , AutoEncoder, Multi-Layer Preceptrons, CNN, RNN, LSTM...
Facial landmarks detection along with their applications (virtual makeup).
Recognizing human faces by OpenFace and Deep Learning methods.
Training custom object detector using yolo v3 and v4, along with inference and deployment. (using kaggle face mask data)
using OCR tech and case study for automatic number plate recognition.
Semantic segmentation notebooks
Cheat Sheets
CRISP-DM pipeline, data wrangling, data modeling, software development, web development/data visualization, data pipeline.
Non-rigid dewarp net. Used spatial transform net to local dewarp the features.
Rewrite a function to implement the K-Means Clustering in c++.
Implement auto-labeling or ID image system, using vgg16 for recognition.
Personal work on sensor fusion for self-driving cars. Including Lidar, Camera, Radar, and Fusion techniques.
Optimization algorithms commonly used in deep learning, mini-batch GD, SGD, and momentum methods AdapGrad, Adam... advanced methods Newton, quasi-Newton, L-BFGS...
Key words: Bayesian analysis, Probabilistic programming, Data analysis, Bayesian machine learning... Using Python with its library PyMC3, pandas...
Udacity Self-Driving Car Engineer Nanodegree projects.
Clustering (unsupervised learning) algorithm implemented (K-means and DBSCAN). Objective-Oriented Programming demonstrated.
Supervised homography net (MobileNet v2) for perspective transform estimation and automated labeled data generation.
Unsupervised perspective transform estimations (spatial transform network). Use the similarity between image patches as the loss.
vince's technical blogs: http://vince-CV.github.io
Yolo v3 for label detection and used Darknet-53 as the backbone.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.