Model architectures 🏛
Metrics 📊
Solvers / Optimizers 🧮
Training parameters
Augmentations
Deployment
Smallest max size
Rescale such that the minimum side is equal to the given maximum size
Parameters
Minimum size of smallest side
The parameter that specifies the length of the maximum size that is to be used to resize minimum side of the image.
The aspect ratio of the original image is preserved.
Advanced option
Interpolation
The algorithm to be used for the resizing of the image. For more information regarding the interpolation, you can see it here .
1
import albumentations as albu
2
from PIL import Image
3
import numpy as np
4
5
6
transform =albu.SmallestMaxSize(max_size=1024, interpolation=1,p=1)
7
#default interpolation is INTER_LINEAR
8
9
10
image = np.array(Image.open('/some/image/file/path'))
11
image = transform(image=image)['image']
12
13
14
# Now the image is preprocessed and ready to be accepted by the model
15
Copied!
Further Resources
Last modified 9mo ago