Hi,
I’m trying to load train.csv and test.csv from Kaggle competition called “Digit recognizer”, the thing is that there aren’t any pictures, train and test have basically one column that represents label, and bunch of other columns that represent pixels.
Is there any way I can load this kind of information into ImageDataBunch?
So far I finished 2 weeks of deep learning course, so I’m sorry if this question is stupid. Btw, I know I can download MNIST dataset using untar_data(URLs.MNIST) - However I want to use this data.
Best,
Alex