CNN deep model using too much RAM - deep-learning

Question

I'm building a CNN for dectection of chest x-ray images with pneumonia, the problem I got is that when training the usage of ram just blows up, I'm using a Kaggle Notebook and the ram usage slowly grows till the 30gb limit and then shuts down, even before printing a single epoch.
I tried passing the data from float64 to float32 but no mayor results, just the rate in which reaches the 30gb limits slows down.
I don't really know where's the problem because I've seen similar codes also trained for the same dataset in Kaggle Notebooks, so I know that the data itself isn't the problem. My image dataset are 5216 images for train and just 16 for validation. Here's the code
image_size = (128,128)
data_train = tf.keras.utils.image_dataset_from_directory(train_path, color_mode ='grayscale', image_size = image_size)
data_train = data_train.map(lambda x, y: (tf.cast(x, tf.float32), y))
data_train_iterator = data_train.as_numpy_iterator()
batch_data_train = data_train_iterator.next()
data_val = tf.keras.utils.image_dataset_from_directory(val_path,color_mode ='grayscale', image_size = image_size)
data_val = data_val.map(lambda x, y: (tf.cast(x, tf.float32), y))
data_val_iterator = data_val.as_numpy_iterator()
batch_data_val = data_val_iterator.next()
data_augmentation = ImageDataGenerator(
rescale = 1./255,
rotation_range=20,
width_shift_range=0.2,
height_shift_range=0.2,
horizontal_flip=True,
vertical_flip=False,
zoom_range=0.2,
fill_mode='nearest'
)
data_aug_train = data_augmentation.flow_from_directory(train_path, target_size=image_size, batch_size=32, class_mode='categorical')
data_aug_val = data_augmentation.flow_from_directory(val_path, target_size=image_size, batch_size=32, class_mode='categorical')
def pneumonia_model():
model = Sequential()
model.add(Conv2D(16, (3, 3), activation='relu', padding="same", input_shape=(128,128,1)))
model.add(BatchNormalization())
model.add(Conv2D(16, (3, 3), padding="same", activation='relu'))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(32, (3, 3), activation='relu', padding="same", input_shape=(128,128,1)))
model.add(BatchNormalization())
model.add(Conv2D(32, (3, 3), padding="same", activation='relu'))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(64, (3, 3), activation='relu', padding="same"))
model.add(BatchNormalization())
model.add(Conv2D(64, (3, 3), padding="same", activation='relu'))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(96, (3, 3), dilation_rate=(2, 2), activation='relu', padding="same"))
model.add(BatchNormalization())
model.add(Conv2D(96, (3, 3), padding="valid", activation='relu'))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(128, (3, 3), dilation_rate=(2, 2), activation='relu', padding="same"))
model.add(BatchNormalization())
model.add(Conv2D(128, (3, 3), padding="valid", activation='relu'))
model.add(BatchNormalization())
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dense(64, activation='relu'))
model.add(Dropout(0.4))
model.add(Dense(2 , activation='softmax'))
print(model.summary())
return model
model = pneumonia_model()
model.compile('adam', loss=tf.losses.BinaryCrossentropy(), metrics=['accuracy'])
hist = model.fit(data_aug_train,epochs=20,validation_data = tuple(data_aug_val))`
`