def create_embedding(word_index, num_words, word2vec_model):
 embedding_matrix = np.zeros((num_words, EMBEDDING_DIM))
 for word, i in word_index.items():
  try:
   embedding_vector = word2vec_model[word]
   embedding_matrix[i] = embedding_vector
  except:
   continue
 return embedding_matrix
 
#word_index:词典（统计词转换为索引）
#num_word:词典长度+1
#word2vec_model:词向量的model

def pre_load_embedding_model(model_file):
 # model = gensim.models.Word2Vec.load(model_file)
 # model = gensim.models.Word2Vec.load(model_file,binary=True)
 model = gensim.models.KeyedVectors.load_word2vec_format(model_file)
 return model

 embedding_matrix = create_embedding(word_index, num_words, word2vec_model)
 
 embedding_layer = Embedding(num_words,
        EMBEDDING_DIM,
        embeddings_initializer=Constant(embedding_matrix),
        input_length=MAX_SEQUENCE_LENGTH,
        trainable=False)
 sequence_input = Input(shape=(MAX_SEQUENCE_LENGTH,), dtype='int32')
 embedded_sequences = embedding_layer(sequence_input)

from keras.models import Sequential
from keras.layers import Embedding
import numpy as np
 
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)
print(output_array)
assert output_array.shape == (32, 10, 64)

import numpy as np
import keras
 
m = keras.models.Sequential()
"""
可以通过weights参数指定初始的weights参数
因为Embedding层是不可导的 
梯度东流至此回,所以把embedding放在中间层是没有意义的,emebedding只能作为第一层
注意weights到embeddings的绑定过程很复杂，weights是一个列表
"""
embedding = keras.layers.Embedding(input_dim=3, output_dim=2, input_length=1, weights=[np.arange(3 * 2).reshape((3, 2))], mask_zero=True)
m.add(embedding) # 一旦add，就会自动调用embedding的build函数,
print(keras.backend.get_value(embedding.embeddings))
m.compile(keras.optimizers.RMSprop(), keras.losses.mse)
print(m.predict([1, 2, 2, 1, 2, 0]))
print(m.get_layer(index=0).get_weights())
print(keras.backend.get_value(embedding.embeddings))

import numpy as np
import keras
 
m = keras.models.Sequential()
"""
可以通过weights参数指定初始的weights参数
因为Embedding层是不可导的 
梯度东流至此回,所以把embedding放在中间层是没有意义的,emebedding只能作为第一层
给embedding设置权值的第二种方式，使用constant_initializer 
"""
embedding = keras.layers.Embedding(input_dim=3, output_dim=2, input_length=1, embeddings_initializer=keras.initializers.constant(np.arange(3 * 2, dtype=np.float32).reshape((3, 2))))
m.add(embedding)
print(keras.backend.get_value(embedding.embeddings))
m.compile(keras.optimizers.RMSprop(), keras.losses.mse)
print(m.predict([1, 2, 2, 1, 2]))
print(m.get_layer(index=0).get_weights())
print(keras.backend.get_value(embedding.embeddings))

  if 'weights' in kwargs:
   self._initial_weights = kwargs['weights']
  else:
   self._initial_weights = None

 def __call__(self, inputs, **kwargs):
  """Wrapper around self.call(), for handling internal references.
  If a Keras tensor is passed:
   - We call self._add_inbound_node().
   - If necessary, we `build` the layer to match
    the _keras_shape of the input(s).
   - We update the _keras_shape of every input tensor with
    its new shape (obtained via self.compute_output_shape).
    This is done as part of _add_inbound_node().
   - We update the _keras_history of the output tensor(s)
    with the current layer.
    This is done as part of _add_inbound_node().
  # Arguments
   inputs: Can be a tensor or list/tuple of tensors.
   **kwargs: Additional keyword arguments to be passed to `call()`.
  # Returns
   Output of the layer's `call` method.
  # Raises
   ValueError: in case the layer is missing shape information
    for its `build` call.
  """
  if isinstance(inputs, list):
   inputs = inputs[:]
  with K.name_scope(self.name):
   # Handle laying building (weight creating, input spec locking).
   if not self.built:#如果未曾build，那就要先执行build再调用call函数
    # Raise exceptions in case the input is not compatible
    # with the input_spec specified in the layer constructor.
    self.assert_input_compatibility(inputs)
 
    # Collect input shapes to build layer.
    input_shapes = []
    for x_elem in to_list(inputs):
     if hasattr(x_elem, '_keras_shape'):
      input_shapes.append(x_elem._keras_shape)
     elif hasattr(K, 'int_shape'):
      input_shapes.append(K.int_shape(x_elem))
     else:
      raise ValueError('You tried to call layer "' +
           self.name +
           '". This layer has no information'
           ' about its expected input shape, '
           'and thus cannot be built. '
           'You can build it manually via: '
           '`layer.build(batch_input_shape)`')
    self.build(unpack_singleton(input_shapes))
    self.built = True#这句话其实有些多余，因为self.build函数已经把built置为True了
 
    # Load weights that were specified at layer instantiation.
    if self._initial_weights is not None:#如果传入了weights，把weights参数赋值到每个变量，此处会覆盖上面的self.build函数中的赋值。
     self.set_weights(self._initial_weights)
 
   # Raise exceptions in case the input is not compatible
   # with the input_spec set at build time.
   self.assert_input_compatibility(inputs)
 
   # Handle mask propagation.
   previous_mask = _collect_previous_mask(inputs)
   user_kwargs = copy.copy(kwargs)
   if not is_all_none(previous_mask):
    # The previous layer generated a mask.
    if has_arg(self.call, 'mask'):
     if 'mask' not in kwargs:
      # If mask is explicitly passed to __call__,
      # we should override the default mask.
      kwargs['mask'] = previous_mask
   # Handle automatic shape inference (only useful for Theano).
   input_shape = _collect_input_shape(inputs)
 
   # Actually call the layer,
   # collecting output(s), mask(s), and shape(s).
   output = self.call(inputs, **kwargs)
   output_mask = self.compute_mask(inputs, previous_mask)
 
   # If the layer returns tensors from its inputs, unmodified,
   # we copy them to avoid loss of tensor metadata.
   output_ls = to_list(output)
   inputs_ls = to_list(inputs)
   output_ls_copy = []
   for x in output_ls:
    if x in inputs_ls:
     x = K.identity(x)
    output_ls_copy.append(x)
   output = unpack_singleton(output_ls_copy)
 
   # Inferring the output shape is only relevant for Theano.
   if all([s is not None
     for s in to_list(input_shape)]):
    output_shape = self.compute_output_shape(input_shape)
   else:
    if isinstance(input_shape, list):
     output_shape = [None for _ in input_shape]
    else:
     output_shape = None
 
   if (not isinstance(output_mask, (list, tuple)) and
     len(output_ls) > 1):
    # Augment the mask to match the length of the output.
    output_mask = [output_mask] * len(output_ls)
 
   # Add an inbound node to the layer, so that it keeps track
   # of the call and of all new variables created during the call.
   # This also updates the layer history of the output tensor(s).
   # If the input tensor(s) had not previous Keras history,
   # this does nothing.
   self._add_inbound_node(input_tensors=inputs,
         output_tensors=output,
         input_masks=previous_mask,
         output_masks=output_mask,
         input_shapes=input_shape,
         output_shapes=output_shape,
         arguments=user_kwargs)
 
   # Apply activity regularizer if any:
   if (hasattr(self, 'activity_regularizer') and
     self.activity_regularizer is not None):
    with K.name_scope('activity_regularizer'):
     regularization_losses = [
      self.activity_regularizer(x)
      for x in to_list(output)]
    self.add_loss(regularization_losses,
        inputs=to_list(inputs))
  return output

 def build(self, input_shape):
  self.embeddings = self.add_weight(
   shape=(self.input_dim, self.output_dim),
   initializer=self.embeddings_initializer,
   name='embeddings',
   regularizer=self.embeddings_regularizer,
   constraint=self.embeddings_constraint,
   dtype=self.dtype)
  self.built = True