/neuralcomputationUoB

Assignment1

Primary LanguageJupyter NotebookGNU General Public License v2.0GPL-2.0

Project Requirements

  1. opencv
  2. numpy
  3. torch
  4. torchvision
  5. matplotlib

To Run

python main.py

Instructions

  1. Code by default trains for 50 epochs, and runs inference on the first image of train dataset
  2. To visualize training data, uncomment line 119. Press 'q' to exit.
  3. To test forward pass on dummy data, to check output dimensions, uncomment line 120.

To Do

  1. Add and test different loss functions (Focal Loss, Dice Loss etc)
  2. Test different model architectures