Michael Kim's repositories
Ego-Lane-fitting-Pointclouds
This is the short, personal project. The goal of this project is to detect the ego lane markings and conduct polynomial fitting with small LiDAR point cloud. Due to lack of data, implementing Deep learning techniques is inappropriate; therefore, I wrote the source codes that cover from point cloud pre-processing to lane extraction algorithms using DBSCAN clustering & RANSAC algorithms.
ESPCN_Pytorch
Implemented ESPCN with Pytorch from scratch & trained with custom dataset / Test with low-resolution video
Helmholtz-coil-config_3pair
3rd year summer research intern at "Ion Trap Quantum Computing Group", Univ of Oxford (Jun 2019)
OW-champ-classification
Implement transfer learning of pre-trained Resnet50 architecture for the image classification of OW champions
ray
Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a toolkit of libraries (Ray AIR) for accelerating ML workloads.
Roll-a-Ball
Just for fun, trying to get used to C# & Unity3D
SRCNN_Pytorch
Implemented SRCNN with Pytorch from scratch & trained with custom dataset