How to balance data with keras.ImageDataGenerator()

Question

Having unbalanced data, how can I use ImageDataGenerator() to generate enough augmented data for shorter sample to balance all categories?

I don't think you can do that with ImageDataGenerator. There is simply no built-in option for that. However, you can use class_weights in ft method to somehow makeup for the contribution of low-count classes. — today
– today, Commented Apr 21, 2020 at 18:38
This may be your solution. stackoverflow.com/questions/42586475/… — CRich
– CRich, Commented Feb 12, 2021 at 5:33

Harshit Ruwali · Accepted Answer · 2020-04-21 19:32:17Z

You can use the following code,

datagen = ImageDataGenerator( featurewise_center=True, featurewise_std_normalization=True, rotation_range=20, width_shift_range=0.2, height_shift_range=0.2, horizontal_flip=True)

This will not affect your dataset at all. It formats the image while feeding into the model.
You may refer the documentation, Image Preprocessing
Hope this helps.

Taisa · Accepted Answer · 2021-05-24 20:27:40Z

You need to create a dictionary based on the weights of each class and then feed the model.fit_generator with it:

from sklearn.utils import class_weight import numpy as np class_weights = class_weight.compute_class_weight( 'balanced', np.unique(train_generator.classes), train_generator.classes) train_class_weights = dict(enumerate(class_weights)) model.fit_generator(..., class_weight=train_class_weights)

Collectives™ on Stack Overflow

How to balance data with keras.ImageDataGenerator()

2 Answers 2

Comments

Comments

Linked

Hot Network Questions

Collectives™ on Stack Overflow

2 Answers 2

Comments

Comments

Linked

Related