AttributeError: module 'keras.applications.mobilenet' has no attribute 'preprocess'

Question

I already imported preprocess module but it continuously showed the same error. How should I solve this error? Need help to solve this error !

The imported Libraries are given below,

import tensorflow as tf
import keras
from tensorflow.keras.preprocessing import image_dataset_from_directory
from keras.preprocessing.image import ImageDataGenerator
from keras.applications import MobileNet
from keras.applications.mobilenet import preprocess_input

Image Preparation,

train_path = 'eggplant/training'
test_path = 'eggplant/testing'
valid_path = 'eggplant/validation'

train_batches = ImageDataGenerator(preprocessing_function = keras.applications.mobilenet.preprocess.input).flow_from.directory(train_path, target_size=(224,224), batch_size=10)
train_batches = ImageDataGenerator(preprocessing_function = keras.applications.mobilenet.preprocess.input).flow_from.directory(valid_path, target_size=(224,224), batch_size=10)
train_batches = ImageDataGenerator(preprocessing_function = keras.applications.mobilenet.preprocess.input).flow_from.directory(test_path, target_size=(224,224), batch_size=10, shuffle=False)

Error is given below,

AttributeError                            Traceback (most recent call last)
<ipython-input-17-fc384b61e2b7> in <module>()
----> 1 train_batches = ImageDataGenerator(preprocessing_function = keras.applications.mobilenet.preprocess.input).flow_from.directory(train_path, target_size=(224,224), batch_size=10)
      2 train_batches = ImageDataGenerator(preprocessing_function = keras.applications.mobilenet.preprocess.input).flow_from.directory(valid_path, target_size=(224,224), batch_size=10)
      3 train_batches = ImageDataGenerator(preprocessing_function = keras.applications.mobilenet.preprocess.input).flow_from.directory(test_path, target_size=(224,224), batch_size=10, shuffle=False)

AttributeError: module 'keras.applications.mobilenet' has no attribute 'preprocess'

Answer 1

You should use preprocess_input instead of preprocess.input. As well as, you also need to change flow_from.directory to flow_from_directory.