My experiments and progress within various fastai applications

Here is where I will be posting any experiments regarding the fastai library before I publish them anywhere

• Explores over/under/moderate sampling

• Slight experimental encoder-inspired layer setup

• Permutation importance in the fastai library

• An attempt to find some mathematical way to calculate the size for hidden layers on tabular models

• An example of how to deal with key points when they go off-image after transforms

• A walkthrough on how to generate labeled test-sets in the fastai library and integrate them into a Learner

• An attempt at using MixUp for tabular problems. Did not improve accuracy

• Working to try a 4-part ensemble for the IMDB dataset utilizing Spacy and SentencePiece tokenization on forwards and backwards models