Concise Lecture Notes - Lesson 3 | Fastai v3 (2019)

These notes were typed out by me while watching the lecture, for a quick revision later on. To be able to fully understand them, they should be used alongside the jupyter notebooks that are available here:



Datablock api:

How do you train over misclassified images?

Does Datablock api blocks need to be in a certain order?

Yes they do! What kind of data -> how do you label it -> how do you split it -> what datasets you want? -> Optionally how to transform it? -> how to create a databunch from it.

How to increase score further?

Image Segmentation(CAMVID problem):

What is it and why do we do this?

Image Regression

Any time you want to predict some continuous value (In this case co-ordinates for center of face), you can do Image Regression in the same manner as well.


When using a dataset that is very different from imagenet (like sattelite or x-ray images), when transfer learning, should we normalize using the same stats we trained with?

How does tokenization work when words depend on each other like San Fransisco?

How to use pretrained models when your dataset has 2 channels or 4 channels instead of 3?

comments powered by Disqus