Resize

If you have ever worked on a Computer Vision project, you might know that using augmentations to diversify the dataset is the best practice. On this page, we will:

• Сover the Resize augmentation;

• Check out its parameters;

• See how Resize affects an image;

• And check out how to work with Resize using Python through the Albumentations library.

Let’s get into it!

Resize explained

As the name suggests, this data augmentation changes the size of your image according to the set height and width parameters.

Parameters

• Height after resize - sets the height of the resized image in pixels;

• Width after resize - sets the width of the resized image in pixels.

Advanced options

• Interpolation - used to specify the interpolation algorithm:
  • Nearest;
  • Linear;
  • Cubic;
  • Area;
  • LANCZOS4.

Resize visualized

Code Implementation

    import albumentations as albu
from PIL import Image

transform = albu.augmentations.geometric.resize.Resize(200,200)
augmented_image = transform(image=figure)['image']

# We have the resized image in augmented_image.
    Copy
  

Learn more about other augmentations…

• Horizontal Flip;
• Vertical Flip;
• Random Crop;
• Random Sized Crop;
• Rotate;
• Blur;
• Smallest max size;
• Center Crop;
• Color Jitter;
• Shift Scale Rotate;
• Longest Max Size;
• Equalize;
• To gray;
• Shear;
• Mosaic;
• Copy Paste.