train model using tf.data.Dataset of tf.keras.preprocessing.image_dataset_from_directory is very slow keras

I am using tf.keras.preprocessing.image_dataset_from_directory to load my large dataset. the problem is the training phase is so slow when I exploit this method in fit_generator() although I use the google Colab GPU. The code is:

image_size = (224, 224)
batch_size = 32

data = tf.keras.preprocessing.image_dataset_from_directory(
     '/content/drive/My Drive/dataScience/september exam/data/trainImg',
    seed=1337,
    image_size=image_size,
    batch_size=batch_size,
)



for the training:

model.fit_generator(train_dataset,
             epochs=50,
             verbose=1)

Answer

You can try to reduce the image shape to 128×128, reduce the batch_size and use the GPU of the Collab, you should use model.fit() .Hope this helps you with time optimization.