159 lines (139 sloc) 6.47 KB
"""Embedding layer.
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from .. import backend as K
from .. import initializers
from .. import regularizers
from .. import constraints
from ..engine.base_layer import Layer
from ..legacy import interfaces
from ..utils.generic_utils import to_list
class Embedding(Layer):
"""Turns positive integers (indexes) into dense vectors of fixed size.
eg. [[4], [20]] -> [[0.25, 0.1], [0.6, -0.2]]
This layer can only be used as the first layer in a model.
# Example
model = Sequential()
model.add(Embedding(1000, 64, input_length=10))
# the model will take as input an integer matrix of size (batch, input_length).
# the largest integer (i.e. word index) in the input should be
# no larger than 999 (vocabulary size).
# now model.output_shape == (None, 10, 64), where None is the batch dimension.
input_array = np.random.randint(1000, size=(32, 10))
model.compile('rmsprop', 'mse')
output_array = model.predict(input_array)
assert output_array.shape == (32, 10, 64)
# Arguments
input_dim: int > 0. Size of the vocabulary,
i.e. maximum integer index + 1.
output_dim: int >= 0. Dimension of the dense embedding.
embeddings_initializer: Initializer for the `embeddings` matrix
(see [initializers](../
embeddings_regularizer: Regularizer function applied to
the `embeddings` matrix
(see [regularizer](../
embeddings_constraint: Constraint function applied to
the `embeddings` matrix
(see [constraints](../
mask_zero: Whether or not the input value 0 is a special "padding"
value that should be masked out.
This is useful when using [recurrent layers](
which may take variable length input.
If this is `True` then all subsequent layers
in the model need to support masking or an exception will be raised.
If mask_zero is set to True, as a consequence, index 0 cannot be
used in the vocabulary (input_dim should equal size of
vocabulary + 1).
input_length: Length of input sequences, when it is constant.
This argument is required if you are going to connect
`Flatten` then `Dense` layers upstream
(without it, the shape of the dense outputs cannot be computed).
# Input shape
2D tensor with shape: `(batch_size, sequence_length)`.
# Output shape
3D tensor with shape: `(batch_size, sequence_length, output_dim)`.
# References
- [A Theoretically Grounded Application of Dropout in
Recurrent Neural Networks](
def __init__(self, input_dim, output_dim,
if 'input_shape' not in kwargs:
if input_length:
kwargs['input_shape'] = (input_length,)
kwargs['input_shape'] = (None,)
super(Embedding, self).__init__(**kwargs)
self.input_dim = input_dim
self.output_dim = output_dim
self.embeddings_initializer = initializers.get(embeddings_initializer)
self.embeddings_regularizer = regularizers.get(embeddings_regularizer)
self.activity_regularizer = regularizers.get(activity_regularizer)
self.embeddings_constraint = constraints.get(embeddings_constraint)
self.mask_zero = mask_zero
self.supports_masking = mask_zero
self.input_length = input_length
def build(self, input_shape):
self.embeddings = self.add_weight(
shape=(self.input_dim, self.output_dim),
self.built = True
def compute_mask(self, inputs, mask=None):
if not self.mask_zero:
return None
output_mask = K.not_equal(inputs, 0)
return output_mask
def compute_output_shape(self, input_shape):
if self.input_length is None:
return input_shape + (self.output_dim,)
# input_length can be tuple if input is 3D or higher
in_lens = to_list(self.input_length, allow_tuple=True)
if len(in_lens) != len(input_shape) - 1:
raise ValueError(
'"input_length" is %s, but received input has shape %s' %
(str(self.input_length), str(input_shape)))
for i, (s1, s2) in enumerate(zip(in_lens, input_shape[1:])):
if s1 is not None and s2 is not None and s1 != s2:
raise ValueError(
'"input_length" is %s, but received input has shape %s' %
(str(self.input_length), str(input_shape)))
elif s1 is None:
in_lens[i] = s2
return (input_shape[0],) + tuple(in_lens) + (self.output_dim,)
def call(self, inputs):
if K.dtype(inputs) != 'int32':
inputs = K.cast(inputs, 'int32')
out = K.gather(self.embeddings, inputs)
return out
def get_config(self):
config = {'input_dim': self.input_dim,
'output_dim': self.output_dim,
'mask_zero': self.mask_zero,
'input_length': self.input_length}
base_config = super(Embedding, self).get_config()
return dict(list(base_config.items()) + list(config.items()))