Data augmentation is not generated İmages

Question

I am working on image classification (12 classes of image data) by applying CNN Model. As a result, İ have been facing overfitting therefore İ applied Data Augmentation. Although it works pretty well, however, İ have faced an error i.e.

Found 0 validated image filenames belonging to 0 classes.
Found 0 validated image filenames belonging to 0 classes.
Found 0 validated image filenames belonging to 0 classes.
/usr/local/lib/python3.7/dist-packages/keras_preprocessing/image/dataframe_iterator.py:282: UserWarning: Found 4985 invalid image filename(s) in x_col="Filepath". These filename(s) will be ignored.
  .format(n_invalid, x_col)
/usr/local/lib/python3.7/dist-packages/keras_preprocessing/image/dataframe_iterator.py:282: UserWarning: Found 4985 invalid image filename(s) in x_col="Filepath". These filename(s) will be ignored.
  .format(n_invalid, x_col)
/usr/local/lib/python3.7/dist-packages/keras_preprocessing/image/dataframe_iterator.py:282: UserWarning: Found 554 invalid image filename(s) in x_col="Filepath". These filename(s) will be ignored.
  .format(n_invalid, x_col)

As a result, it has been quite unable to generate new images.

My code:

import shutil

aug_path = r'/content/dataset' # path to augmentation directory
if os.path.isdir(aug_path):
    shutil.rmtree(aug_path) # remove anything in aug directory if it exists
os.mkdir(aug_path) # make the aug directory
for label in image_df['Label'].unique():
    subpath=os.path.join(aug_path, label) # path for the sub directory
    os.mkdir(subpath)

target= 110
image_shape=(256,256)
gen=ImageDataGenerator(horizontal_flip=True, vertical_flip=True, rotation_range=20, width_shift_range=.2,
                              height_shift_range=.2, zoom_range=.2)
groups=image_df.groupby('Label') # group by class
for label in image_df['Label'].unique():  # for every class               
    group=groups.get_group(label)  # a dataframe holding only rows with the specified label 
    sample_count=len(group)   # determine how many samples there are in this class  
    if sample_count< target: # if the class has less than target number of images
        aug_img_count=0
        delta=target-sample_count  # number of augmented images to create
        target_dir=os.path.join(aug_path, label)  # define where to write the images    
        aug_gen=gen.flow_from_dataframe( group,  x_col='Filepath', y_col=None, target_size=image_shape, class_mode=None, batch_size=1,
                                         shuffle=False, save_to_dir=target_dir, save_prefix='aug-',save_format='jpg')
        while aug_img_count<delta:
            images=next(aug_gen)            
            aug_img_count += len(images) 

def create_gen():
    # Load the Images with a generator and Data Augmentation
    train_generator = tf.keras.preprocessing.image.ImageDataGenerator(
        preprocessing_function=tf.keras.applications.mobilenet_v2.preprocess_input,
        validation_split=0.1
    )

    test_generator = tf.keras.preprocessing.image.ImageDataGenerator(
        preprocessing_function=tf.keras.applications.mobilenet_v2.preprocess_input
    )

    train_images = train_generator.flow_from_dataframe(
        dataframe=train_df,
        x_col='Filepath',
        y_col='Label',
        target_size=(128, 128),
        color_mode='rgb',
        class_mode='categorical',
        batch_size=64,
        shuffle=True,
        seed=0,
        subset='training',
        rotation_range=30, # Uncomment to use data augmentation
        zoom_range=0.15,
        width_shift_range=0.2,
        height_shift_range=0.2,
        shear_range=0.15,
        horizontal_flip=True,
        fill_mode="nearest"
    )

    val_images = train_generator.flow_from_dataframe(
        dataframe=train_df,
        x_col='Filepath',
        y_col='Label',
        target_size=(128, 128),
        color_mode='rgb',
        class_mode='categorical',
        batch_size=64,
        shuffle=True,
        seed=0,
        subset='validation',
        rotation_range=30, # Uncomment to use data augmentation
        zoom_range=0.15,
        width_shift_range=0.2,
        height_shift_range=0.2,
        shear_range=0.15,
        horizontal_flip=True,
        fill_mode="nearest"
    )

    test_images = test_generator.flow_from_dataframe(
        dataframe=test_df,
        x_col='Filepath',
        y_col='Label',
        target_size=(128, 128),
        color_mode='rgb',
        class_mode='categorical',
        batch_size=64,
        shuffle=False
    )
    
    return train_generator,test_generator,train_images,val_images,test_images

from sklearn.model_selection import train_test_split
# Separate in train and test data
train_df, test_df = train_test_split(image_df, train_size=0.9, shuffle=True, random_state=101)

# Create the generators
train_generator,test_generator,train_images,val_images,test_images = create_gen()

Output:

Found 0 validated image filenames belonging to 0 classes.
Found 0 validated image filenames belonging to 0 classes.
Found 0 validated image filenames belonging to 0 classes.
/usr/local/lib/python3.7/dist-packages/keras_preprocessing/image/dataframe_iterator.py:282: UserWarning: Found 4985 invalid image filename(s) in x_col="Filepath". These filename(s) will be ignored.
  .format(n_invalid, x_col)
/usr/local/lib/python3.7/dist-packages/keras_preprocessing/image/dataframe_iterator.py:282: UserWarning: Found 4985 invalid image filename(s) in x_col="Filepath". These filename(s) will be ignored.
  .format(n_invalid, x_col)
/usr/local/lib/python3.7/dist-packages/keras_preprocessing/image/dataframe_iterator.py:282: UserWarning: Found 554 invalid image filename(s) in x_col="Filepath". These filename(s) will be ignored.
  .format(n_invalid, x_col)

Answer 1

You have put parameters in flow_from_dataframe that actually belong in the call to ImageDataGenerator. For example in your code below I have marked what does not belong in flow_from_dataframe. See documentation here.

train_images = train_generator.flow_from_dataframe(
        dataframe=train_df,
        x_col='Filepath',
        y_col='Label',
        target_size=(128, 128),
        color_mode='rgb',
        class_mode='categorical',
        batch_size=64,
        shuffle=True,
        seed=0,
        subset='training',
        rotation_range=30,    remove
        zoom_range=0.15,       remove
        width_shift_range=0.2,  remove
        height_shift_range=0.2,  remove
        shear_range=0.15,       remove
        horizontal_flip=True,   remove
        fill_mode="nearest"     remove

P.S. looks like you used some of my code for augmentation from a Kagle notebook. Look at the notebook to see how to setup your generators