In Part 1 of this tutorial, towards the end, we saw if we take an average of all the pixels in the apple and banana image dataset we get an image of banana and apple which is not much like them as given below. The images look more like a ghost :)
Whenever we think of creating an image classifier we straight away think of training a convolution neural net(CNN) containing different layers. We perform three famous steps of extract, fit and predict and we are done in most of the cases. But, in this case, we really don’t understand a few things which happen behind the scene:
1). How exactly are images interpreted by computers?
2). How do computers differentiate between the different classes of images?
We know that CNNs are really good at differentiating images but if we have to take a step back and think about how it can…
When you first start learning something new, it's always a wonderful feeling to be able to showcase a final product (doesn’t matter if it's a simple one), made using your new skill and something which can be used by others. The same is the case with deep learning. So, today in this tutorial we are going to learn to train a simple image classifier and then deploy it as a web app.
We will be going through an example of a simple fresh fruit classifier I built using fastai and PyTorch and deployed as a web app using Streamlit. This…