Kyung Hee University Deep Learning Lecture Project Challenge
The goal of this challenge is to achieve high performance in a given dataset using techniques learned in the lecture.
You can use any neural networks and find your own model architecture to find out how to achieve optimal performance.
To prevent using a lot of GPU resources, you should use a network that can train by using the resources provided by Google Colab.
The baseline is the ResNet-18 result trained on Google Colab from TA and this code will be provided for all.