Xunzhe Wen's repositories
multi-sensor_obstacle_fusion
Personal work on sensor fusion for self-driving cars. Including Lidar, Camera, Radar, and Fusion techniques.
probabilistic-machine-learning
Key words: Bayesian analysis, Probabilistic programming, Data analysis, Bayesian machine learning... Using Python with its library PyMC3, pandas...
optimization-in-deep-learning
Optimization algorithms commonly used in deep learning, mini-batch GD, SGD, and momentum methods AdapGrad, Adam... advanced methods Newton, quasi-Newton, L-BFGS...
Adaptive-Signal-Processing
Estimations and Wiener solutions; FIR filter banks based on STFT (short-time Fourier Transform ); Steepest descent and Newton method; Adaptive algorithms.
cv-facial-landmarks-applications
Facial landmarks detection along with their applications (virtual makeup).
Convolutional-neural-nets-implementation
Deep learning case studies with a popular deep learning framework Tensorflow, which included contents as Softmax , AutoEncoder, Multi-Layer Preceptrons, CNN, RNN, LSTM...
cv-facial-recognition
Recognizing human faces by OpenFace and Deep Learning methods.
cv-ocr-application
using OCR tech and case study for automatic number plate recognition.
supervised-homography-net
Supervised homography net (MobileNet v2) for perspective transform estimation and automated labeled data generation.
cv-mask-detection
Training custom object detector using yolo v3 and v4, along with inference and deployment. (using kaggle face mask data)
data-scientist-explore
CRISP-DM pipeline, data wrangling, data modeling, software development, web development/data visualization, data pipeline.
Labeling-image-recognition
Implement auto-labeling or ID image system, using vgg16 for recognition.
Semi-parametric-Learning
Clustering (unsupervised learning) algorithm implemented (K-means and DBSCAN). Objective-Oriented Programming demonstrated.
cv-semantic-segmnetation
Semantic segmentation notebooks
Data-Science--Cheat-Sheet
Cheat Sheets
deformable-registration-net
Non-rigid dewarp net. Used spatial transform net to local dewarp the features.
K-Means-Clustering-using-Cplusplus
Rewrite a function to implement the K-Means Clustering in c++.
self-driving-car
Udacity Self-Driving Car Engineer Nanodegree projects.
unsupervised-homography-net
Unsupervised perspective transform estimations (spatial transform network). Use the similarity between image patches as the loss.
vince-CV.github.io
vince's technical blogs: http://vince-CV.github.io
yolo-v3-object-detection
Yolo v3 for label detection and used Darknet-53 as the backbone.