ImageDataGenerator, Apply augmentation on images that have more than 4 channels about keras-preprocessing HOT 3 OPEN

I think this limitation comes from Pillow and not from keras-preprocessing. TF has a similar limitation in tf.io.decode_image

from keras-preprocessing.

I think this limitation comes from Pillow and not from keras-preprocessing. TF has a similar limitation in tf.io.decode_image

then what if I want to do so

from keras-preprocessing.

You can implement your own tf Dataset: https://www.tensorflow.org/guide/data

Or your own keras.Sequence, they are deprecated, but still works.

Then for your data augmentation, you can do something similar to this post and use apply_transform.

I think the new keras preprocessing layers could be useful on your case. More info : https://keras.io/guides/preprocessing_layers/

from keras-preprocessing.