https://github.com/nathom/numpy-fcn

FCN using only numpy
https://github.com/nathom/numpy-fcn

Last synced: about 1 month ago
JSON representation

FCN using only numpy

• Host: GitHub
• URL: https://github.com/nathom/numpy-fcn
• Owner: nathom
• Created: 2024-03-22T04:54:07.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2024-03-22T04:56:05.000Z (about 1 year ago)
• Last Synced: 2025-02-13T04:43:54.524Z (3 months ago)
• Language: TeX
• Size: 24.4 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
[![Review Assignment Due Date](https://classroom.github.com/assets/deadline-readme-button-24ddc0f5d75046c5622901739e7c5dd533143b0c8e959d652212380cedb1ea36.svg)](https://classroom.github.com/a/tCO2PRy9)

# PA1-Starter

1. main.py is the driver function that has to be run in order to run different set of experiments. You can run it by doing: `python main.py --experiment `.

2. the first time you run main.py, it will automatically download the data to the 'data' directory 

3. config files need to be in the 'config' directory

5. You are free to create new functions, change existing function signatures, add/remove member variables/functions in the provided classes but you need to maintain the overall given structure of the code. Specifically, you have to mandatorily use the classes provided in neuralnet.py to create your model (although, like already mentioned, you can add or remove variables/functions in these classes or change the function signatures)

6. We have marked sections to be implemented by you as TODO for your convenience