The goal is to achieve high performance in a given dataset using techniques learned in the lecture.
You can use any data augmentation techniques or DNN models or optimizer or tuning techniques 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 & Kaggle.
The Baseline on the Leaderboard is the ResNet34 results trained on Google Colab.
Please set your team name as Initial name, e.g., Team JH
Please merge team with your team member using Request Merge in Invite Others of Team tab.

CAUTION
You can't use imagenet pretrained model and extra datasets for training.
And also **you can't use test dataset for training.**

Train and Make the submission csv file

https://gitlab.com/mlvc_lab/practical-machine-learning-qna/-/issues?scope=all&utf8=%E2%9C%93&state=all
(log in with KHU account)

Copy this Google Colab ipynb file on your google drive and use that.