def __init__(self, max_tokens, num_oov_indices, mask_token, oov_token, vocabulary=None, invert=False, output_mode=INT, sparse=False, pad_to_max_tokens=False, **kwargs): # If max_tokens is set, the value must be greater than 1 - otherwise we # are creating a 0-element vocab, which doesn't make sense. if max_tokens is not None and max_tokens <= 1: raise ValueError("If set, `max_tokens` must be greater than 1. " "You passed {}".format(max_tokens)) if num_oov_indices < 0: raise ValueError( "`num_oov_indices` must be greater than or equal to 0. " "You passed {}".format(num_oov_indices)) # 'output_mode' must be one of (INT, BINARY, COUNT, TFIDF) layer_utils.validate_string_arg(output_mode, allowable_strings=(INT, BINARY, COUNT, TFIDF), layer_name=self.__class__.__name__, arg_name="output_mode") if invert and output_mode != INT: raise ValueError( "`output_mode` must be {} when `invert` is true. You " "passed {}".format(INT, output_mode)) self.invert = invert self.max_tokens = max_tokens self.num_oov_indices = num_oov_indices self.oov_token = oov_token self.mask_token = mask_token self.output_mode = output_mode self.sparse = sparse self.pad_to_max_tokens = pad_to_max_tokens self._called = False self._vocab_size = 0 # We need to keep track our current vocab size outside of our layer weights # to support a static output shape when `output_mode != INT`. The bincount # ops do not set shape on their outputs, which means we have to set it # ourselves. We persist the current vocab size as a hidden part of the # config when serializing our model. if "vocabulary_size" in kwargs: self._vocab_size = kwargs["vocabulary_size"] del kwargs["vocabulary_size"] if max_tokens is not None: available_vocab_size = max_tokens - self._token_start_index() else: available_vocab_size = None super(IndexLookup, self).__init__(combiner=_IndexLookupCombiner( vocab_size=available_vocab_size, mask_value=mask_token, oov_value=oov_token, compute_idf=(output_mode == TFIDF)), **kwargs) # We need to save the key dtype so that we know if we're expecting int64 # keys. If we are, we will cast int32 inputs to int64 as well. if invert: self._key_dtype = dtypes.int64 self._value_dtype = self.dtype self._mask_key = 0 self._mask_value = mask_token key_index = lookup_ops.TextFileIndex.LINE_NUMBER value_index = lookup_ops.TextFileIndex.WHOLE_LINE default_value = self.oov_token oov_indices = None else: self._key_dtype = self.dtype self._value_dtype = dtypes.int64 self._mask_key = mask_token key_index = lookup_ops.TextFileIndex.WHOLE_LINE value_index = lookup_ops.TextFileIndex.LINE_NUMBER # Masks should map to 0 for int output and be dropped otherwise. Max ints # will be dropped from the bincount op. self._mask_value = 0 if self.output_mode == INT else dtypes.int64.max oov_start = self._oov_start_index() token_start = self._token_start_index() if self.num_oov_indices == 0: # If there are no OOV indices, we map OOV tokens to -1 for int output # and drop them from bagged output. Max ints will be dropped from the # bincount op. default_value = -1 if self.output_mode == INT else dtypes.int64.max oov_indices = None elif self.num_oov_indices == 1: # If there is only one OOV index, we can set that index as the default # value of the index_lookup table. default_value = oov_start oov_indices = None else: # If we hav multiple OOV values, we need to do a further hashing step; # to make this easier, we set the OOV value to -1. (This lets us do a # vectorized add and cast to boolean to determine locations where we # need to do extra hashing.) default_value = -1 oov_indices = list(range(oov_start, token_start)) if vocabulary is not None and isinstance(vocabulary, str): if not os.path.exists(vocabulary): raise ValueError("Vocabulary file %s does not exist." % vocabulary) total_offset = 0 if mask_token is None else 1 total_offset += num_oov_indices initializer = lookup_ops.TextFileInitializer( filename=vocabulary, key_dtype=self._key_dtype, key_index=key_index, value_dtype=self._value_dtype, value_index=value_index, value_index_offset=total_offset) self._table = self._static_table_class()( initializer, default_value=default_value) self._table_handler = table_utils.TableHandler( table=self._table, mask_token=self._mask_key, mask_value=self._mask_value, oov_tokens=oov_indices, use_v1_apis=self._use_v1_apis()) self.max_tokens = (self._table_handler.table_size() + self.num_oov_indices + (0 if mask_token is None else 1)) else: self._table = lookup_ops.MutableHashTable( key_dtype=self._key_dtype, value_dtype=self._value_dtype, default_value=default_value, name=(self._name + "_index_table")) self._table_handler = table_utils.TableHandler( table=self._table, oov_tokens=oov_indices, use_v1_apis=self._use_v1_apis()) if vocabulary is not None: self.set_vocabulary(vocabulary) if self.output_mode == TFIDF: # The TF-IDF weight may have a (None,) tensorshape. This creates # a 1D variable with arbitrary shape, which we can assign any weight to # so long as it has 1 dimension. In order to properly initialize this # weight in Keras, we need to provide a custom callable initializer which # does not depend on the shape of the weight (as all other initializers # do) since the weight is not known. Hence the lambda shape, dtype: [0]. if not self.pad_to_max_tokens or max_tokens is None: initializer = lambda shape, dtype: [0] else: initializer = init_ops.zeros_initializer # We are adding these here instead of in build() since they do not depend # on the input shape at all. idf_shape = (max_tokens, ) if self.pad_to_max_tokens else (None, ) self.tf_idf_weights = self._add_state_variable( name="idf", shape=tensor_shape.TensorShape(idf_shape), dtype=K.floatx(), initializer=initializer) tracked_table = self._add_trackable(self._table, trainable=False) # This is a workaround for summary() on this layer. Because the table is # not mutable during training, the effective number of parameters (and so # the weight shape) is 0; we add this as an attr so that the parameter # counting code in the Model object doesn't throw an attribute error. tracked_table.shape = tensor_shape.TensorShape((0, ))
def __init__(self, max_tokens, num_oov_indices, mask_token, oov_token, vocabulary=None, invert=False, output_mode=INT, sparse=False, pad_to_max_tokens=False, **kwargs): # If max_tokens is set, the value must be greater than 1 - otherwise we # are creating a 0-element vocab, which doesn't make sense. if max_tokens is not None and max_tokens <= 1: raise ValueError("If set, `max_tokens` must be greater than 1. " "You passed {}".format(max_tokens)) if num_oov_indices < 0: raise ValueError( "`num_oov_indices` must be greater than or equal to 0. " "You passed {}".format(num_oov_indices)) # 'output_mode' must be one of (INT, BINARY, COUNT, TFIDF) layer_utils.validate_string_arg(output_mode, allowable_strings=(INT, BINARY, COUNT, TFIDF), layer_name=self.__class__.__name__, arg_name="output_mode") self.invert = invert self.max_tokens = max_tokens self.num_oov_indices = num_oov_indices self.oov_token = oov_token self.mask_token = mask_token self.output_mode = output_mode self.sparse = sparse self.pad_to_max_tokens = pad_to_max_tokens self._called = False self._num_special_tokens = self.num_oov_indices if self.mask_token is not None: self._num_special_tokens += 1 # If there is only one OOV bucket, we can determine the OOV value (either 0 # or 1 depending on whether 0 is reserved) and set that as the default # value of the index_lookup table. If we hav multiple OOV values, we need to # do a further hashing step; to make this easier, we set the OOV value to # -1. (This lets us do a vectorized add and cast to boolean to determine # locations where we need to do extra hashing.) if self.num_oov_indices == 1: self._oov_value = 0 if mask_token is None else 1 else: self._oov_value = -1 if max_tokens is not None: available_vocab_size = max_tokens - self._num_special_tokens else: available_vocab_size = None super(IndexLookup, self).__init__(combiner=_IndexLookupCombiner( vocab_size=available_vocab_size, mask_value=mask_token, oov_value=oov_token, compute_idf=(output_mode == TFIDF)), **kwargs) # We need to save the key dtype so that we know if we're expecting int64 # keys. If we are, we will cast int32 inputs to int64 as well. if invert: self._key_dtype = dtypes.int64 self._value_dtype = self.dtype oov_value = self.oov_token oov_indices = None else: self._key_dtype = self.dtype self._value_dtype = dtypes.int64 oov_value = self._oov_value if self.num_oov_indices <= 1: oov_indices = None else: oov_start = 1 if mask_token is not None else 0 oov_end = oov_start + num_oov_indices oov_indices = list(range(oov_start, oov_end)) if vocabulary is not None and isinstance( vocabulary, lookup_ops.TextFileInitializer): self._table = self._static_table_class()(vocabulary, default_value=oov_value) self._table_handler = table_utils.TableHandler( table=self._table, mask_token=mask_token, oov_tokens=oov_indices, use_v1_apis=self._use_v1_apis()) self.max_tokens = (self._table_handler.table_size() + self.num_oov_indices + (0 if mask_token is None else 1)) else: self._table = lookup_ops.MutableHashTable( key_dtype=self._key_dtype, value_dtype=self._value_dtype, default_value=oov_value, name=(self._name + "_index_table")) self._table_handler = table_utils.TableHandler( table=self._table, oov_tokens=oov_indices, use_v1_apis=self._use_v1_apis()) if vocabulary is not None: self.set_vocabulary(vocabulary) if self.output_mode == TFIDF: # The TF-IDF weight may have a (None,) tensorshape. This creates # a 1D variable with arbitrary shape, which we can assign any weight to # so long as it has 1 dimension. In order to properly initialize this # weight in Keras, we need to provide a custom callable initializer which # does not depend on the shape of the weight (as all other initializers # do) since the weight is not known. Hence the lambda shape, dtype: [0]. if not self.pad_to_max_tokens or max_tokens is None: initializer = lambda shape, dtype: [0] else: initializer = init_ops.zeros_initializer # We are adding these here instead of in build() since they do not depend # on the input shape at all. idf_shape = (max_tokens, ) if self.pad_to_max_tokens else (None, ) self.tf_idf_weights = self._add_state_variable( name="idf", shape=tensor_shape.TensorShape(idf_shape), dtype=K.floatx(), initializer=initializer) tracked_table = self._add_trackable(self._table, trainable=False) # This is a workaround for summary() on this layer. Because the table is # not mutable during training, the effective number of parameters (and so # the weight shape) is 0; we add this as an attr so that the parameter # counting code in the Model object doesn't throw an attribute error. tracked_table.shape = tensor_shape.TensorShape((0, ))
def __init__(self, max_tokens, num_oov_indices, mask_token, oov_token, vocabulary=None, invert=False, output_mode=INT, sparse=False, **kwargs): # If max_tokens is set, the value must be greater than 1 - otherwise we # are creating a 0-element vocab, which doesn't make sense. if max_tokens is not None and max_tokens <= 1: raise ValueError("If set, max_tokens must be greater than 1. " "You passed %s" % (max_tokens,)) if num_oov_indices < 0: raise ValueError("`num_oov_indices` must be greater than 0. You passed " "%s" % (num_oov_indices,)) if invert and num_oov_indices != 1: raise ValueError("`num_oov_tokens` must be 1 when `invert` is True.") # 'output_mode' must be one of (INT, BINARY, COUNT) layer_utils.validate_string_arg( output_mode, allowable_strings=(INT, BINARY, COUNT), layer_name=self.__class__.__name__, arg_name="output_mode") self.invert = invert self.max_tokens = max_tokens self.num_oov_indices = num_oov_indices self.oov_token = oov_token self.mask_token = mask_token self.output_mode = output_mode self.sparse = sparse # If there is only one OOV bucket, we can determine the OOV value (either 0 # or 1 depending on whether 0 is reserved) and set that as the default # value of the index_lookup table. If we hav multiple OOV values, we need to # do a further hashing step; to make this easier, we set the OOV value to # -1. (This lets us do a vectorized add and cast to boolean to determine # locations where we need to do extra hashing.) if self.num_oov_indices == 1: self._oov_value = 0 if mask_token is None else 1 else: self._oov_value = -1 if max_tokens is not None: num_mask_tokens = (0 if mask_token is None else 1) vocab_size = max_tokens - (num_oov_indices + num_mask_tokens) else: vocab_size = None super(IndexLookup, self).__init__( combiner=_IndexLookupCombiner(vocab_size, self.mask_token), **kwargs) self._output_dtype = dtypes.int64 # We need to save the key dtype so that we know if we're expecting int64 # keys. If we are, we will cast int32 inputs to int64 as well. if invert: self._key_dtype = self._output_dtype value_dtype = self.dtype oov_value = self.oov_token else: self._key_dtype = self.dtype value_dtype = self._output_dtype oov_value = self._oov_value self._table = lookup_ops.MutableHashTable( key_dtype=self._key_dtype, value_dtype=value_dtype, default_value=oov_value, name=(self._name + "_index_table")) tracked_table = self._add_trackable(self._table, trainable=False) # This is a workaround for summary() on this layer. Because the table is # not mutable during training, the effective number of parameters (and so # the weight shape) is 0; we add this as an attr so that the parameter # counting code in the Model object doesn't throw an attribute error. tracked_table.shape = tensor_shape.TensorShape((0,)) if self.num_oov_indices <= 1: oov_indices = None else: oov_start = 1 if mask_token is not None else 0 oov_end = oov_start + num_oov_indices oov_indices = list(range(oov_start, oov_end)) self._table_handler = table_utils.TableHandler( table=self._table, oov_tokens=oov_indices, use_v1_apis=self._use_v1_apis()) if vocabulary is not None: self.set_vocabulary(vocabulary)
def __init__(self, max_tokens, num_oov_indices, mask_token, oov_token, vocabulary=None, invert=False, output_mode=INT, sparse=False, pad_to_max_tokens=False, **kwargs): # If max_tokens is set, the value must be greater than 1 - otherwise we # are creating a 0-element vocab, which doesn't make sense. if max_tokens is not None and max_tokens <= 1: raise ValueError("If set, `max_tokens` must be greater than 1. " "You passed {}".format(max_tokens)) if num_oov_indices < 0: raise ValueError( "`num_oov_indices` must be greater than or equal to 0. " "You passed {}".format(num_oov_indices)) # Support deprecated names for output_modes. if output_mode == "binary": output_mode = MULTI_HOT if output_mode == "tf-idf": output_mode = TF_IDF # 'output_mode' must be one of (INT, MULTI_HOT, COUNT, TF_IDF) layer_utils.validate_string_arg(output_mode, allowable_strings=(INT, MULTI_HOT, COUNT, TF_IDF), layer_name=self.__class__.__name__, arg_name="output_mode") if invert and output_mode != INT: raise ValueError( "`output_mode` must be {} when `invert` is true. You " "passed {}".format(INT, output_mode)) self.invert = invert self.max_tokens = max_tokens self.num_oov_indices = num_oov_indices self.output_mode = output_mode self.sparse = sparse self.pad_to_max_tokens = pad_to_max_tokens self._called = False # A note on vocab_size: we need to always keep a non-Tensor representation # of vocab_size around to use in graph building. Because we might be # in a tf.function, we can't rely on evaluating the actual tables to # find the value either. self._vocab_size = None # We need to keep track our current vocab size outside of our layer weights # to support a static output shape when `output_mode != INT`. The bincount # ops do not set shape on their outputs, which means we have to set it # ourselves. We persist the current vocab size as a hidden part of the # config when serializing our model. if "vocabulary_size" in kwargs: self._vocab_size = kwargs["vocabulary_size"] del kwargs["vocabulary_size"] restore_from_static_table = kwargs.pop("has_static_table", False) # Make sure the mask token and oov token are truly of the dtype we want. We # can ignore strings here, because they have only one dtype. dtype = kwargs["dtype"] if dtype == dtypes.int32: mask_token = None if mask_token is None else np.int32(mask_token) oov_token = None if oov_token is None else np.int32(oov_token) elif dtype == dtypes.int64: mask_token = None if mask_token is None else np.int64(mask_token) oov_token = None if oov_token is None else np.int64(oov_token) self.mask_token = mask_token self.oov_token = oov_token if max_tokens is not None: available_vocab_size = max_tokens - self._token_start_index() else: available_vocab_size = None super(IndexLookup, self).__init__(combiner=_IndexLookupCombiner( vocab_size=available_vocab_size, mask_value=mask_token, oov_value=oov_token, compute_idf=(output_mode == TF_IDF)), **kwargs) # We need to save the key dtype so that we know if we're expecting int64 # keys. If we are, we will cast int32 inputs to int64 as well. if invert: self._key_dtype = dtypes.int64 self._value_dtype = self.dtype self._mask_key = 0 self._mask_value = mask_token key_index = lookup_ops.TextFileIndex.LINE_NUMBER value_index = lookup_ops.TextFileIndex.WHOLE_LINE default_value = self.oov_token oov_indices = None else: self._key_dtype = self.dtype self._value_dtype = dtypes.int64 self._mask_key = mask_token key_index = lookup_ops.TextFileIndex.WHOLE_LINE value_index = lookup_ops.TextFileIndex.LINE_NUMBER # Masks should map to 0 for int output and be dropped otherwise. Max ints # will be dropped from the bincount op. self._mask_value = 0 if self.output_mode == INT else dtypes.int64.max oov_start = self._oov_start_index() token_start = self._token_start_index() if self.num_oov_indices == 0: # If there are no OOV indices, we map OOV tokens to -1 and error out # during call if we find a negative index. default_value = -1 oov_indices = None elif self.num_oov_indices == 1: # If there is only one OOV index, we can set that index as the default # value of the index_lookup table. default_value = oov_start oov_indices = None else: # If we hav multiple OOV values, we need to do a further hashing step; # to make this easier, we set the OOV value to -1. (This lets us do a # vectorized add and cast to boolean to determine locations where we # need to do extra hashing.) default_value = -1 oov_indices = list(range(oov_start, token_start)) self._static_vocabulary_path = None has_vocab_path = (vocabulary is not None and isinstance(vocabulary, str)) if has_vocab_path or restore_from_static_table: self._has_static_table = True if vocabulary is None: # If we're restoring a layer that was saved with a static table # initializer, we create a fake initializer object to let the code # progress. The savedmodel restoration code will handle restoring # the actual data. initializer = _NullInitializer(self._key_dtype, self._value_dtype) else: if not gfile.Exists(vocabulary): raise ValueError("Vocabulary file %s does not exist." % (vocabulary, )) self._static_vocabulary_path = vocabulary num_tokens = table_utils.num_tokens_in_file(vocabulary) self._vocab_size = self._token_start_index() + num_tokens initializer = lookup_ops.TextFileInitializer( filename=vocabulary, key_dtype=self._key_dtype, key_index=key_index, value_dtype=self._value_dtype, value_index=value_index, value_index_offset=self._token_start_index()) self._table = lookup_ops.StaticHashTable( initializer, default_value=default_value) self._table_handler = table_utils.TableHandler( table=self._table, mask_token=self._mask_key if self.mask_token is not None else None, mask_value=self._mask_value, oov_tokens=oov_indices) tracked_table = self._add_trackable(self._table, trainable=False) else: self._has_static_table = False self._table = lookup_ops.MutableHashTable( key_dtype=self._key_dtype, value_dtype=self._value_dtype, default_value=default_value, name=(self._name + "_index_table")) self._table_handler = table_utils.TableHandler( table=self._table, oov_tokens=oov_indices) if vocabulary is not None: self.set_vocabulary(vocabulary) tracked_table = self._add_trackable(self._table, trainable=False) if self.output_mode == TF_IDF: # The TF-IDF weight may have a (None,) tensorshape. This creates # a 1D variable with arbitrary shape, which we can assign any weight to # so long as it has 1 dimension. In order to properly initialize this # weight in Keras, we need to provide a custom callable initializer which # does not depend on the shape of the weight (as all other initializers # do) since the weight is not known. Hence the lambda shape, dtype: [0]. if not self.pad_to_max_tokens or max_tokens is None: initializer = lambda shape, dtype: [0] else: initializer = init_ops.zeros_initializer # We are adding these here instead of in build() since they do not depend # on the input shape at all. idf_shape = (max_tokens, ) if self.pad_to_max_tokens else (None, ) self.tf_idf_weights = self._add_state_variable( name="idf", shape=tensor_shape.TensorShape(idf_shape), dtype=backend.floatx(), initializer=initializer) # This is a workaround for summary() on this layer. Because the table is # not mutable during training, the effective number of parameters (and so # the weight shape) is 0; we add this as an attr so that the parameter # counting code in the Model object doesn't throw an attribute error. tracked_table.shape = tensor_shape.TensorShape((0, ))
def get_table(dtype=dtypes.string, oov_tokens=None): table = lookup_ops.MutableHashTable(key_dtype=dtype, value_dtype=dtypes.int64, default_value=-7, name="index_table") return table_utils.TableHandler(table, oov_tokens)