Homework 10: Convolutional Neural Networks with PyTorch



Wednesday 5/1/19, 11:59 PM CST


In this homework set, you will extend from neural network with simple fully connected layers (as in Homework 8) and learn to use convolution layers, batch normailzation, and advanced features to improve the accuracy.  

Code and External Libraries

The assignment must be done using PyTorch platform and GPU. Do all of your work in the provided iPython notebook.

The libraries you may need to have are in this requirements.txt file.


Total points: 100


Submission will be through gradescope


  1. Your python notebook renamed as netid_HW10.ipynb. Submit this in the HW10 Code section.
  2. Convert your python notebook with all outputs and questions answered into PDF format. Name it netid_HW10.pdf. Submit this in the HW10 Report section
Note: Make sure that your training plots are visible after converting to PDF. If this becomes difficult, save the plots as images and attach them to the end of your PDF submission.