Tham Ngap Wei

My job is build, optimize and deploy computer vision algorithms to production.

I generally treating computer vision algorithms as APIs or components, which I will be plugging into a full-stack app or hardware of some kind,

but I also know how to design the algorithms, train the deep learning models, study the paper by myself.

I have developed a full stack computer vision application which need to perform object detection, face recognition, age/gender recognition and others.

Not only that, I know how to deploy those models and create a complicated app based on them.

1 : Semantic segmentation by LinkNet : This is the first working example of LinkNet implemented by .

2 : Deep image homography : Surpass the accuracy of the paper 3.5 times with smaller, faster cnn model.

3 : Person detect with mxnet : Show you how to perform object detection with mxnet, opencv and c++

4 : Train a detector based on yolo v3 by custom data : Show you how to train a face, person detector by gluoncv

5 : Kaggle competition :

Top 6% in cat vs dog

Top 7% in the nature conservancy Fisheries Monitoring

7 : python_deep_learning : Deep learning exercise and project developed by python, it show you how to

A : Process imagenet data by python with SIMD and parallel

B : Neural style transfer

C : Super resolution

D : Semantic segmentation

8 : QRenamer : An easy to use rename tool developed by Qt5

9 : Similar vision : The app which can help you find and remove duplicate photos on your PC