Assignment 04 (Due date: Oct. 27, 2024)
Neural Networks
Assignment 04
Due date: Oct. 27, 2024
Convolutional Neural Network (CNN) with PyTorch
 
The purpose of the this assignment is to create a Convolutional Neural Networks (CNN) using PyTorch.
To begin this assignment download the Kamangar_04.zip and unzip it in your computer.
 
  • Your code should be using PyTorch
  • DO NOT alter/change the name of the function or the parameters of the function.
  • You may introduce additional functions (helper functions) as needed. All the helper functions should be put in the same file with train_nn_torch()  function.
  • The comments in the train_nn_torch()  function provide additional information that should help with your implementation.
 Notes:
  • The Assignment_04_tests.py file includes a very minimal set of unit tests for the CNN class module. Part of the assignment grade will be based on your code passing these tests (and some other unspecified tests)
  • You may modify the "Assignment_04_tests.py" to include more tests. You may also add additional tests to help you during development of your code.
  • DO NOT submit the "Assignment_04_tests.py" file when submitting your Assignment_04
  • You may run these tests using the command:      py.test --verbose Assignment_04_tests.py
 
 Grading Criteria
  • Your submitted function will be tested with multiple test units.
  • Passing the tests - 80 points
  • Qualitative Evaluation - 20 points (Grader may examine your code and subjectively award as many as 20 points.)
 
Submission Guidelines
  • The first four lines of any submitted file must follow the following format according to the assignment submission guidelines.
# Your name (last name, first name)
# Your student ID (100x_xxx_xxx)
# Date of submission (yyyy_mm_dd)
# Assignment_nn_kk
 
  • Change the name of the file according to the submission guidelines.
  • Create a directory and name it according to the submission guidelines and include your file in that directory.
  • Zip the directory and upload it  to Canvas according to the submission guidelines.
 
Top