Charles Yuan's Projects
My first project, created when I was first learning Python. A virtual assistant that has a bunch of random functions built in.
My notes and code that I wrote while taking Andrew Ng's Machine Learning course on Coursera.
Notes and code from Coursera's Reinforcement Learning Specialization, offered by the University of Alberta.
Work done with Detectron2 for research. Details may be disclosed later.
We learned Verilog in ECE253 through a series of labs. Included here are the lab guides and our submissions for each. Shoutout to Parth Dua for being my partner.
A C++ OpenCV art generator, inspired by the designs of Otaku Lamps.
A music player that recommends songs based on your detected mood. Created for TOHacks 2021.
A facial expression classifier created using OpenCV and large CNN, with numerous techniques used to increase the accuracy of the model.
A Discord bot I created in Python. Her name is Eve.
A GUI made using Tkinter for my DJI Tello EDU, named Flydo.
A Generative Adversarial Network trained on a dataset of over 60,000 anime girl images to generate new ones.
A gesture classifier created using OpenCV and a basic CNN.
Vector search-based chatbot to help retail investors analyze company 10K and 10Q filings.
A Discord bot I made in Go. Her name is Mary.
A CNN classifier trained on medical images from the Kvasir Dataset, along with a ResNet50 model trained using transfer learning for comparison.
The labs I've done while following the 2020 MIT Introduction to Deep Learning course.
Utilizing Spacy and Tensorflow to train custom Named Entity Recognizers.
Machine learning algorithms implemented using Python modules such as numpy, math, sklearn, etc.
OpenCV projects using python
My professional portfolio website
An app to share your investment portfolio with your friends!
A reinforcement learning stock trader for the S&P 500.
Projects listed on my resume.
A Seq2Seq model created for translating basic English phrases to Japanese.
A hand tracker created using OpenCV and a re-trained SSD MobileNet v2 via transfer learning on the EgoHands Dataset.
A REST API to generate stock trade recommendations daily.
Basic stock prediction model.
UNet model with VGG11 encoder pre-trained on Kaggle Carvana dataset