In this project, I use an idea inspired by one of my academic research projects: I designed adaptable materials using oscillatory optimization goals. Here, I'm letting the learner, an algorithm that mimics the style of a painting, repeatedly change its mind about which style it prefers. The learner oscillates between learning how to paint like Van Gogh and learning how to paint like Picasso. After several cycles, the learner ends up painting in a style that has qualities of both!
We make use of a technique called Neural Style Transfer to mimic a single style. The code for this subproblem is heavy adapted from the following link: Neural Transfer using PyTorch.
pip install numpy
pip3 install torch torchvision
pip install matplotlib
Following along the jupyter notebook oscillating_using_pytorch-ongithub_final.ipynb
Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.
Please make sure to update tests as appropriate.