def get_config(self):
config = super().get_config()
config.update({
'axis': self.axis,
'mean': utils.listify_tensors(self.input_mean),
'variance': utils.listify_tensors(self.input_variance),
})
return config
def get_config(self):
config = super().get_config()
config.update({
"axis": self.axis,
"mean": utils.listify_tensors(self.input_mean),
"variance": utils.listify_tensors(self.input_variance),
})
return config
def get_config(self):
config = {
"invert": self.invert,
"max_tokens": self.max_tokens,
"num_oov_indices": self.num_oov_indices,
"oov_token": self.oov_token,
"mask_token": self.mask_token,
"output_mode": self.output_mode,
"pad_to_max_tokens": self.pad_to_max_tokens,
"vocabulary": utils.listify_tensors(self.input_vocabulary),
"idf_weights": utils.listify_tensors(self.input_idf_weights),
}
base_config = super().get_config()
return dict(list(base_config.items()) + list(config.items()))
def finalize_state(self):
if self.input_bin_boundaries is not None or not self.built:
return
# The bucketize op only support list boundaries.
self.bin_boundaries = utils.listify_tensors(
get_bin_boundaries(self.summary, self.num_bins))
def __init__(self,
bin_boundaries=None,
num_bins=None,
epsilon=0.01,
**kwargs):
# bins is a deprecated arg for setting bin_boundaries or num_bins that still
# has some usage.
if "bins" in kwargs:
logging.warning(
"bins is deprecated, please use bin_boundaries or num_bins instead."
)
if isinstance(kwargs["bins"], int) and num_bins is None:
num_bins = kwargs["bins"]
elif bin_boundaries is None:
bin_boundaries = kwargs["bins"]
del kwargs["bins"]
super().__init__(**kwargs)
base_preprocessing_layer.keras_kpl_gauge.get_cell(
"Discretization").set(True)
if num_bins is not None and num_bins < 0:
raise ValueError("`num_bins` must be greater than or equal to 0. "
"You passed `num_bins={}`".format(num_bins))
if num_bins is not None and bin_boundaries is not None:
raise ValueError(
"Both `num_bins` and `bin_boundaries` should not be "
"set. You passed `num_bins={}` and "
"`bin_boundaries={}`".format(num_bins, bin_boundaries))
bin_boundaries = utils.listify_tensors(bin_boundaries)
self.input_bin_boundaries = bin_boundaries
self.bin_boundaries = bin_boundaries if bin_boundaries is not None else []
self.num_bins = num_bins
self.epsilon = epsilon
def get_config(self):
vocab = self._lookup_layer.input_vocabulary
idf_weights = self._lookup_layer.input_idf_weights
config = {
"max_tokens": self._lookup_layer.max_tokens,
"standardize": self._standardize,
"split": self._split,
"ngrams": self._ngrams_arg,
"output_mode": self._output_mode,
"output_sequence_length": self._output_sequence_length,
"pad_to_max_tokens": self._lookup_layer.pad_to_max_tokens,
"sparse": self._lookup_layer.sparse,
"ragged": self._ragged,
"vocabulary": utils.listify_tensors(vocab),
"idf_weights": utils.listify_tensors(idf_weights),
}
base_config = super(TextVectorization, self).get_config()
return dict(list(base_config.items()) + list(config.items()))
def __init__(
self,
bin_boundaries=None,
num_bins=None,
epsilon=0.01,
output_mode="int",
sparse=False,
**kwargs,
):
# bins is a deprecated arg for setting bin_boundaries or num_bins that still
# has some usage.
if "bins" in kwargs:
logging.warning(
"bins is deprecated, please use bin_boundaries or num_bins instead."
)
if isinstance(kwargs["bins"], int) and num_bins is None:
num_bins = kwargs["bins"]
elif bin_boundaries is None:
bin_boundaries = kwargs["bins"]
del kwargs["bins"]
# By default, output int64 when output_mode='int' and floats otherwise.
if "dtype" not in kwargs or kwargs["dtype"] is None:
kwargs["dtype"] = (
tf.int64 if output_mode == INT else backend.floatx()
)
elif (
output_mode == "int" and not tf.as_dtype(kwargs["dtype"]).is_integer
):
# Compat for when dtype was always floating and ignored by the layer.
kwargs["dtype"] = tf.int64
super().__init__(**kwargs)
base_preprocessing_layer.keras_kpl_gauge.get_cell("Discretization").set(
True
)
# Check dtype only after base layer parses it; dtype parsing is complex.
if (
output_mode == INT
and not tf.as_dtype(self.compute_dtype).is_integer
):
input_dtype = kwargs["dtype"]
raise ValueError(
"When `output_mode='int'`, `dtype` should be an integer "
f"type. Received: dtype={input_dtype}"
)
# 'output_mode' must be one of (INT, ONE_HOT, MULTI_HOT, COUNT)
layer_utils.validate_string_arg(
output_mode,
allowable_strings=(INT, ONE_HOT, MULTI_HOT, COUNT),
layer_name=self.__class__.__name__,
arg_name="output_mode",
)
if sparse and output_mode == INT:
raise ValueError(
f"`sparse` may only be true if `output_mode` is "
f"`'one_hot'`, `'multi_hot'`, or `'count'`. "
f"Received: sparse={sparse} and "
f"output_mode={output_mode}"
)
if num_bins is not None and num_bins < 0:
raise ValueError(
"`num_bins` must be greater than or equal to 0. "
"You passed `num_bins={}`".format(num_bins)
)
if num_bins is not None and bin_boundaries is not None:
raise ValueError(
"Both `num_bins` and `bin_boundaries` should not be "
"set. You passed `num_bins={}` and "
"`bin_boundaries={}`".format(num_bins, bin_boundaries)
)
bin_boundaries = utils.listify_tensors(bin_boundaries)
self.input_bin_boundaries = bin_boundaries
self.bin_boundaries = (
bin_boundaries if bin_boundaries is not None else []
)
self.num_bins = num_bins
self.epsilon = epsilon
self.output_mode = output_mode
self.sparse = sparse
def test_numpy_input(self):
inputs = np.array([0, 1, 2, 3, 4])
outputs = preprocessing_utils.listify_tensors(inputs)
self.assertAllEqual([0, 1, 2, 3, 4], outputs)
self.assertIsInstance(outputs, list)
def test_tensor_input(self):
inputs = tf.constant([0, 1, 2, 3, 4])
outputs = preprocessing_utils.listify_tensors(inputs)
self.assertAllEqual([0, 1, 2, 3, 4], outputs)
self.assertIsInstance(outputs, list)
