tf.data or tf.keras.utils.Sequence. Improving efficiency of tf.data?

I am trying to develop an image colorizer using autoencoders. There are 13000 training images. Each epoch takes about 45 minutes if I use tf.data and about 25 minutes if I use tf.utils.keras.Sequence. However with the use of Sequence there is a risk of deadlocks. How do I improve tf.data? I tried a couple of things but they don't seem to improve anything.

tf.data 1

image_path_list = glob.glob('datasets/imagenette/*')
data = tf.data.Dataset.list_files(image_path_list)

def tf_rgb2lab(image):
  im_shape = image.shape
  [image,] = tf.py_function(color.rgb2lab, [image], [tf.float32])
  image.set_shape(im_shape)
  return image

def preprocess(path):
  image = tf.io.read_file(path)
  image = tf.image.decode_jpeg(image, channels=3)
  image = tf.image.convert_image_dtype(image, tf.float32)
  image = tf.image.resize(image, [224, 224])
  image = tf_rgb2lab(image)
  L = image[:,:,0]/100.
  ab = image[:,:,1:]/128.
  input = tf.stack([L,L,L], axis=2)
  return input, ab

train_ds = data.repeat().map(preprocess, AUTOTUNE).batch(32).prefetch(AUTOTUNE)

tf.data 2

AUTOTUNE = tf.data.experimental.AUTOTUNE

def tf_rgb2lab(image):
  im_shape = image.shape
  [image,] = tf.py_function(color.rgb2lab, [image], [tf.float32])
  image.set_shape(im_shape)
  return image

def split_for_feed(image):  
  L = image[:,:,:,0]/100.
  ab = image[:,:,:,1:]/128.
  input = tf.stack([L,L,L], axis=-1)
  return input, ab

def read_images(path):
  image = tf.io.read_file(path)
  image = tf.image.decode_jpeg(image, channels=3)
  image = tf.image.convert_image_dtype(image, tf.float32)
  image = tf.image.resize(image, [224, 224])
  image = tf_rgb2lab(image)
  return image
  
data2 = data.repeat().map(read_images, AUTOTUNE).batch(32)
train_ds = data2.map(split_for_feed, AUTOTUNE).prefetch(AUTOTUNE)

Sequence

class ImageGenerator(tf.keras.utils.Sequence):
  def __init__(self, image_filenames, batch_size):
    self.image_filenames = image_filenames
    self.batch_size = batch_size

  def __len__(self):
    return math.ceil(len(self.image_filenames) / self.batch_size)

  def __getitem__(self, idx):
    batch = self.image_filenames[idx * self.batch_size : (idx + 1) * self.batch_size]
    X_batch = []
    y_batch = []
    for file_name in batch:
      file_name = 'datasets/imagenette/' + file_name
      try:
        color_image = transform.resize(io.imread(file_name),(224,224))
        lab_image = color.rgb2lab(color_image)
        L = lab_image[:,:,0]/100.
        ab = lab_image[:,:,1:]/128.
        X_batch.append(np.stack((L,L,L), axis=2))
        y_batch.append(ab)
      except:
        pass
    return np.array(X_batch), np.array(y_batch)