Skip to content

ucsd-ml-arts/ml-art-final-will-stock-final

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Final Project

Will Stock, wstock@ucsd.edu

Abstract Proposal

For my final project, I continued my original proposal for my generated visual. I want to use images scraped from nike.com to generate images of Nike shoes, then create posters for a fictional Nike campaign in which new shoe designs are created by machine learning. I wanted these posters to emulate print Nike ads from the 1980s and 90s, which I find very visually appealing.

Project Report

report.pdf

Model/Data

nike 224_2.zip - Training dataset ImageGeneratorDCGAN-old - GAN for image generation

Code

  • Jupyter notebooks: generative_code.ipynb

Results

Documentation of your results in an appropriate format, both links to files and a brief description of their contents:

poster_1-01.png - output poster 1 poster_1-02.png - output poster 2 poster_1-03.png - output poster 3

Technical Notes

Any implementation details or notes we need to repeat your work.

  • Runs fine on datahub without any extra packages!

Reference

https://github.com/gsurma/image_generator

About

ml-art-final-will-stock-final created by GitHub Classroom

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published