Kaggle Comp: Plant Seedlings Classification

[SHAR1 (Sharwon Pius)]

Cross Validation with fast.ai

Hey All. no intro, just sharing how to do CV predictions with fastai for train and test sets. Why not with ImageClassifierData.from_csv ? - well, because it gonna precompute activations every time you change folds both for train and for test. Obviously it should be enough to precompute activations once and than just change train/validation sets based on CV indexes. So our steps: Precompute activations once: data = ImageClassifierData.from_csv(val_idxs =[0], test_name='test') learn = ConvL…

This is brilliant!