Apples and Oranges — what’s the difference?

Using Convolutional Neural Networks to classify pictures of apples and oranges.

I have a lid but I’m not a can of paint
I have a lens but I’m not a camera
I’m in a socket but I’m not a plug
I have an iris but I’m not a bunch of flowers
I have lashes but I don’t have a whip.

What am I?

An eye! Our eyes (and the visual cortices in our brain) are extremely powerful. Just with a quick glance, we can immediately identify where objects are relative to us and do instant qualitative analysis. To our ancestors, this fast visual processing was probably very important. This also includes processing which foods are edible and which are as toxic as the manchineel.

These trees are one of the most toxic on Earth

How do we teach a computer to do the same thing? By using Neural Networks! This project uses CNNs to distinguish between apples and oranges.

Let’s get started.

Data: the good, the bad and the ugly

The first step to solving any ML problem is always to get an understanding of the data. For this project, I used this dataset from…