“Prétraitement de la création d'apprentissage du transfert V3” Réponses codées

Prétraitement de la création d'apprentissage du transfert V3

train_batches = ImageDataGenerator(preprocessing_function=tf.keras.applications.inception_v3.preprocess_input) \
    .flow_from_directory(directory=trin_path, target_size=(299,299), classes=['dogs', 'cats'], batch_size=10)
valid_batches = ImageDataGenerator(preprocessing_function=tf.keras.applications.inception_v3.preprocess_input) \
    .flow_from_directory(directory=valid_path, target_size=(299,299), classes=['dogs', 'cats'], batch_size=10)
test_batches = ImageDataGenerator(preprocessing_function=tf.keras.applications.inception_v3.preprocess_input) \
     .flow_from_directory(directory=test_path, target_size=(299,299), classes=['dogs', 'cats'], batch_size=10, shuffle=False)