Description

Objective
– Learn PyTorch and helper libraries
– Understand VOC Semantic Segmentation Dataset
– Create data transforms to augment the dataset
– Create the neural network
– Train and evaluate the neural network

Resources and Instructions Environment Setup:
We recommend using Google Colab to complete this assignment.
Upload the assignment ipynb file to google collab
• Runtime -> change runtime type
• Set hardware accelerator to GPU

Assignment:
Complete the two sections within the ipynb assignment file and run all cells. Reviewing the tutorial powerpoint and mnist ipynb file will be helpful.

Deliverable HTML output:
In the Jupyter notebook, go to File > Download as > HTML (.html) Submit a ZIP file containing the
HTML output. Please follow the naming convention of your zip file: a3_<user_id>.zip

Marking Scheme

This assignment is out of 10 marks.
• 2 marks for implementing the data augmentation section
• 8 marks for implementing a neural network o 8 marks will be given for an mIoU of at least 40% on the validation dataset.

Policies
Collaboration
You can discuss the problem with peers, but you must design and implement your own solution independently.

Use of online resources