Melvyn Koh's Projects
Team Art Engineering | Razer Digital Fintech Hackathon 2020 (Team 50)
This application allows us to encode/decode text using an Atbash Cipher (a particular mono-alphabetic cipher formed by taking the alphabet and mapping it to its reverse).
Basic App for Bangkok Trip with Friends
Visit the end-product in the following URL
Source code for my free YouTube series on the Django web framework for Python.
A simple detector of prototypic emotions from facial images captured in video, written in Python.
Real-time face detection and emotion/gender classification using fer2013/imdb datasets with a keras CNN model and openCV.
The world's simplest facial recognition api for Python and the command line
A face recognition demo performed by feeding images of faces recorded by a webcam into a trained FaceNet network to determine the identity of the face
Facial Expression or Facial Emotion Detector can be used to know whether a person is sad, happy, angry and so on only through his/her face. This Repository can be used to carry out such a task.
π¦ Fast-Face : Android App for Real-time Face Landmark Detection. You can check your landmarks in 60ms
Just some of my own notes on finance and market basics
Includes Project 1 and Project 2. Using Tensorflow Python and Keras wrapper to create emotion detection with OpenCV3.
Trying out OpenCV with Python
Recommend the nearest hospitals based on my current location
PythonRiders' Repository for NTU IEEE Hackathon 2018
A project undertaken in Shanghai GES Information Technology while having a Professional Internship
Repo for Kaggle Days Beijing
Create a Spring Boot web backend in Kotlin with the following functionalities. 1. Upload data.csv file from https://www.kaggle.com/carrie1/ecommerce-data/download. 2. List the data from the uploaded data.csv file with pagination. 3. Search data from the uploaded data.csv file. The backend should be responsive and provide sufficient feedback for the frontend to know the progress of the file upload, listing of data and searching of data. Include unit tests.
My own implementations on the LeetCode questions
Welcome to the 30-Day LeetCoding Challenge! With many of us around the world being encouraged to stay indoors and work from home, this is the perfect opportunity for you to focus on studying up for future code interviews. In order to help you stay focused, LeetCode is running the 30-Day LeetCoding Challenge for the month of April. A problem will appear here at midnight PDT each day, and you'll have 24 hours to solve it and submit it here on the Explore Card.
competition: https://www.kaggle.com/c/jigsaw-toxic-comment-classification-challenge/overview evaluation: 6 class each binary, column-wise ROC AUC, https://www.kaggle.com/c/jigsaw-toxic-comment-classification-challenge#evaluation dataset: dir data/train.csv, data/test.csv technology: deep learning CNN http://cs231n.github.io/convolutional-networks/ lstm: http://colah.github.io/posts/2015-08-Understanding-LSTMs/, θͺε·±εηοΌζδΊε°±θ· οΌ https://zhuanlan.zhihu.com/p/35756075 bi-lstm: word embedding: https://towardsdatascience.com/introduction-to-word-embedding-and-word2vec-652d0c2060fa GloVe: embedding/glove.pdf keras: https://keras.io/zh/preprocessing/text/ network: tokenize -> word embedding -> (bi-lstm or lstm) -> CNN (3*3) (or deeper, see lstm_keras.py) -> pooling -> dense net -> 6 binary sigmoid for classify
Personal portfolio