In this part of the homework, you will use Pytorch to design a deep network to classify images into 100 categories. You are provided with a BaseNet in your Github repository and you will work on improving the architecture and fine-tuning the hyper-parameters to improve the classification accuracy of the network.

**Goal:** Get hands-on experience designing and training deep convolutional neural networks using PyTorch.

Note that the number of submissions is limited to a few times per day, so try to tune your model before uploading CSV files. Also, you must make at least one submission for your final system. The best performance will be considered.