The Difference between Presizing and RandomResizedCrop + Data Augmentations

Part 1 (2020)
1

Hi! I’m a bit confused about the difference between simply just applying a RandomResizedCrop along with aug_transforms on a DataLoaders, and Presizing,
Also, I’m not certain when to use Presizing and when I should avoid them, is there any kind of general rule?

(I didn’t find any topic, or paper discussing this topic, that’s the reason why posted this topic.)
Cheers!

2

Hey There,

so the distinction is a bit hard to grasp, make sure you read the fastbook section on it for a in-depth explantation.

But basically the idea is to have to steps:

  1. We resize the image to a (larger, e.g full height) defined size
  2. Then do our data augmentations on it, without losing information (no black borders)

Or as it is described in the book:To implement this process in fastai you use Resize as an item transform with a large size, and RandomResizedCrop as a batch transform with a smaller size."

As to when to use it: I would say always, loosing information by Augmentation is never a good idea.
Cheers!

3

Thank you, it makes much more sense now! :slight_smile:

4

Another point is that if you want to do incremental size training it is a good idea to presize the data offline (e.g call resize_images on the full dataset) to increase training speed and maximize GPU utilization, resizing is expensive.
I generally build a set of folders: images_64, images_128, etc… to iterate fast and do the incremental training.

1 Like
5

Presizing saves a lot of time through removing I/O overhead and not having to resize everything every time, but in terms of model accuracy, online resizing (e.g. RandomResizedCrop) gives you a slight edge since it acts as a weak form of augmentation by exposing different parts of a picture to the model during each epoch. But again, presizing is usually much faster, so if I have a lot of data, I tend to go with it rather than online resizing.

Data augmentation should be applied after resizing (whether on the go or not) and typically gives better generalization.

1 Like