I'm confused when I add data augmentation should I get more data or the same data I tested my x_train length to confirm but I got the same length before augmentation and after augmentation is that correct or should I get the double of my data?

print(len(x_train)) output : 5484

after augmentation :

datagen = ImageDataGenerator(
        featurewise_center=True,  # set input mean to 0 over the dataset
        samplewise_center=True,  # set each sample mean to 0
        featurewise_std_normalization=True,  # divide inputs by std of the dataset
        samplewise_std_normalization=True,  # divide each input by its std
        zca_whitening=False,  # apply ZCA whitening
        rotation_range=45,  # randomly rotate images in the range (degrees, 0 to 180)
        zoom_range = 0.2, # Randomly zoom image 
        width_shift_range=0.2,  # randomly shift images horizontally (fraction of total width)
        height_shift_range=0.2,  # randomly shift images vertically (fraction of total height)
        horizontal_flip=True,  # randomly flip images
        validation_split=0.2)  # randomly flip images
print(len(x_train)) output : 5484

is that good or what I should do please?


1 Answer 1


A little bit late reply, but it may help someone.

You should not worry about the data length after the augmentation, since keras does it when you send data to training. Therefore, the actual data length does not change.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.