Member-only story
Starting Deep Learning Research (PART 1): A start using FastAI
∘ Entry Requirements ∘ What we want to do
∘ Libraries we will use
∘ Grab the Data and Set Everything Up
∘ Code Imports
∘ Load Data
∘ Teaching our AI: Part 1
∘ Teaching our AI : Part 2
∘ How Well Did We Do?
∘ Using The Model
∘ Fin
So, you took your first steps into Deep Learning. Maybe you read a few articles, did a course or two, and watched a bunch of videos. Or maybe you just heard so much about it that you wanted to learn more. Welcome. This is a beautiful world. It is also very overwhelming. There is so much to learn and understand. But we need to start somewhere. This is your ticket. Enjoy the ride.
Note: This will be very long-winded as it is meant for complete beginners. It might seem very scary at first. But don’t panic. The hardest part is getting started. Hold on. Come back to it. It will take time. Slow down. Read through it. It will save you a lot of pain later on.
Entry Requirements
- Go to this link for the code and follow along kaggle_notebook. Once that opens up, click the button next to “Accelerator” and choose GPU. Accept the terms.
- You have learned some Python. If not, go to YouTube and learn as much as you can first. Do as many examples and problems as you deem enough to understand. Come back.
- You know what a GPU is and if you have one.
- You have a computer and an internet connection.
- If you have a powerful computer, you can set this up locally. fastai
- You will need an editor. I would recommend VSCode.
- If you do not, that’s alright. You can still follow along.
- Watch a small tutorial on how to use a Jupyter Notebook here.
What we want to do
Today we will be teaching our little “AI” how to categorize different fruits. To do that, we need to give examples — aka the “dataset”. You can grab it from Kaggle. We will show our little “AI” quite a lot of images and tell it “hey, this is an Apple, this is not one” and so on, in the hope…
