Configure the dataset for performance

AUTOTUNE = tf.data.AUTOTUNEtrain_dataset = train_dataset.prefetch(buffer_size=AUTOTUNE)validation_dataset = validation_dataset.prefetch(buffer_size=AUTOTUNE)test_dataset = test_dataset.prefetch(buffer_size=AUTOTUNE)

3. Use data augmentation

data_augmentation = tf.keras.Sequential([  tf.keras.layers.experimental.preprocessing.RandomFlip('horizontal'),  tf.keras.layers.experimental.preprocessing.RandomRotation(0.2),])

4. Rescale pixel values

preprocess_input = tf.keras.applications.mobilenet_v2.preprocess_input

rescale = tf.keras.layers.experimental.preprocessing.Rescaling(1./127.5, offset= -1)

You need to login in order to like this post: click here