Hi! I’m a newbie here, if there’s anyone can help me, thank you so much.
The problem is: I was useing a dataset from kaggle, it’s called ‘Sign Language MNIST’, when I create a new kaggle kernel and I want to use fastai to deal with it, I found that I don’t know how to deal with this kind of dataset.
The dataset has no images, but its “.csv” sheet contains labels and each pixel’s value, I guess those pixels can be transformed into images, but I really don’t know how can I deal with it.
If anyone can help, that would be very kind of you, thank u so much.