A sample code sample to accompany the paper titled "Engineering flexible machine learning systems by traversing functionally-invariant paths"
- Create a conda environment using the environment_FIP.yml; conda env create -f environment_FIP.yml
- Run the jupyter notebook in the conda environment
- Run one cell after the other in the sequence it has been written!
- MNIST: https://www.kaggle.com/code/vincentlefoulon/pytorch-mnist (The MNIST dataset can be downloaded from torchvision.datasets.MNIST as mentioned under DataLoading)
- Fashion MNIST: https://github.com/zalandoresearch/fashion-mnist
- CIFAR-10: https://www.cs.toronto.edu/~kriz/cifar.html
- CIFAR-100: https://www.cs.toronto.edu/~kriz/cifar.html (scroll down to second half of the page)
- Yelp-reviews dataset for Transformer NLP task: https://huggingface.co/datasets/yelp_review_full
- IMDB-reviews dataset: https://huggingface.co/datasets/imdb
- WikiText dataset: https://huggingface.co/datasets/wikitext