我正在尝试 NLP。
下面是我的模型，
from keras import backend as K
K.clear_session()
latent_dim = 500
# Encoder
encoder_inputs = Input(shape=(max_len_text,))
enc_emb = Embedding(x_voc_size, latent_dim,trainable=True)(encoder_inputs)
#LSTM 1
encoder_lstm1 = LSTM(latent_dim,return_sequences=True,return_state=True)
encoder_output1, state_h1, state_c1 = encoder_lstm1(enc_emb)
#LSTM 2
encoder_lstm2 = LSTM(latent_dim,return_sequences=True,return_state=True)
encoder_output2, state_h2, state_c2 = encoder_lstm2(encoder_output1)
#LSTM 3
encoder_lstm3=LSTM(latent_dim, return_state=True, return_sequences=True)
encoder_outputs, state_h, state_c= encoder_lstm3(encoder_output2)
# Set up the decoder.
decoder_inputs = Input(shape=(None,))
dec_emb_layer = Embedding(y_voc_size, latent_dim,trainable=True)
dec_emb = dec_emb_layer(decoder_inputs)
#LSTM using encoder_states as initial state
decoder_lstm = LSTM(latent_dim, return_sequences=True, return_state=True)
decoder_outputs,decoder_fwd_state, decoder_back_state = decoder_lstm(dec_emb,initial_state=[state_h, state_c])
#Attention Layer
attn_layer = attention(name='AttentionLayer')
attn_out, attn_states = attention([encoder_outputs, decoder_outputs])
# Concat attention output and decoder LSTM output
decoder_concat_input = Concatenate(axis=-1, name='concat_layer')([decoder_outputs, attn_out])
#Dense layer
decoder_dense = TimeDistributed(Dense(y_voc_size, activation='softmax'))
decoder_outputs = decoder_dense(decoder_concat_input)
# Define the model
model = Model([encoder_inputs, decoder_inputs], decoder_outputs)
model.summary()
现在，这里的“注意力层”使用了一个名为 attention.py 的自定义模块中的类。
它在我的本地目录中，路径为 F:/attentionLayer/attention
我已经导入了这个和 from attentionLayer.attention import AttentionLayer，但是在运行模块时，我收到了这个错误：
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-93-9ff46e455cf1> in <module>
29
30 #Attention Layer
---> 31 attn_layer = attention(name='AttentionLayer')
32 attn_out, attn_states = attention([encoder_outputs, decoder_outputs])
33
TypeError: 'module' object is not callable
供您参考，attention.py 在下面，
import tensorflow as tf
import os
from tensorflow.python.keras.layers import Layer
from tensorflow.python.keras import backend as K
class AttentionLayer(Layer):
"""
This class implements Bahdanau attention (https://arxiv.org/pdf/1409.0473.pdf).
There are three sets of weights introduced W_a, U_a, and V_a
"""
def __init__(self, **kwargs):
super(AttentionLayer, self).__init__(**kwargs)
def build(self, input_shape):
assert isinstance(input_shape, list)
# Create a trainable weight variable for this layer.
self.W_a = self.add_weight(name='W_a',
shape=tf.TensorShape((input_shape[0][2], input_shape[0][2])),
initializer='uniform',
trainable=True)
self.U_a = self.add_weight(name='U_a',
shape=tf.TensorShape((input_shape[1][2], input_shape[0][2])),
initializer='uniform',
trainable=True)
self.V_a = self.add_weight(name='V_a',
shape=tf.TensorShape((input_shape[0][2], 1)),
initializer='uniform',
trainable=True)
super(AttentionLayer, self).build(input_shape) # Be sure to call this at the end
def call(self, inputs, verbose=False):
"""
inputs: [encoder_output_sequence, decoder_output_sequence]
"""
assert type(inputs) == list
encoder_out_seq, decoder_out_seq = inputs
if verbose:
print('encoder_out_seq>', encoder_out_seq.shape)
print('decoder_out_seq>', decoder_out_seq.shape)
def energy_step(inputs, states):
""" Step function for computing energy for a single decoder state
inputs: (batchsize * 1 * de_in_dim)
states: (batchsize * 1 * de_latent_dim)
"""
assert_msg = "States must be an iterable. Got {} of type {}".format(states, type(states))
assert isinstance(states, list) or isinstance(states, tuple), assert_msg
""" Some parameters required for shaping tensors"""
en_seq_len, en_hidden = encoder_out_seq.shape[1], encoder_out_seq.shape[2]
de_hidden = inputs.shape[-1]
""" Computing S.Wa where S=[s0, s1, ..., si]"""
# <= batch size * en_seq_len * latent_dim
W_a_dot_s = K.dot(encoder_out_seq, self.W_a)
""" Computing hj.Ua """
U_a_dot_h = K.expand_dims(K.dot(inputs, self.U_a), 1) # <= batch_size, 1, latent_dim
if verbose:
print('Ua.h>', U_a_dot_h.shape)
""" tanh(S.Wa + hj.Ua) """
# <= batch_size*en_seq_len, latent_dim
Ws_plus_Uh = K.tanh(W_a_dot_s + U_a_dot_h)
if verbose:
print('Ws+Uh>', Ws_plus_Uh.shape)
""" softmax(va.tanh(S.Wa + hj.Ua)) """
# <= batch_size, en_seq_len
e_i = K.squeeze(K.dot(Ws_plus_Uh, self.V_a), axis=-1)
# <= batch_size, en_seq_len
e_i = K.softmax(e_i)
if verbose:
print('ei>', e_i.shape)
return e_i, [e_i]
def context_step(inputs, states):
""" Step function for computing ci using ei """
assert_msg = "States must be an iterable. Got {} of type {}".format(states, type(states))
assert isinstance(states, list) or isinstance(states, tuple), assert_msg
# <= batch_size, hidden_size
c_i = K.sum(encoder_out_seq * K.expand_dims(inputs, -1), axis=1)
if verbose:
print('ci>', c_i.shape)
return c_i, [c_i]
fake_state_c = K.sum(encoder_out_seq, axis=1)
fake_state_e = K.sum(encoder_out_seq, axis=2) # <= (batch_size, enc_seq_len, latent_dim
""" Computing energy outputs """
# e_outputs => (batch_size, de_seq_len, en_seq_len)
last_out, e_outputs, _ = K.rnn(
energy_step, decoder_out_seq, [fake_state_e],
)
""" Computing context vectors """
last_out, c_outputs, _ = K.rnn(
context_step, e_outputs, [fake_state_c],
)
return c_outputs, e_outputs
def compute_output_shape(self, input_shape):
""" Outputs produced by the layer """
return [
tf.TensorShape((input_shape[1][0], input_shape[1][1], input_shape[1][2])),
tf.TensorShape((input_shape[1][0], input_shape[1][1], input_shape[0][1]))
]
TIA。 :)
答案 0 :(得分：1)
attention 是一个模块。你可能想写：
#Attention Layer
attn_layer = attention.AttentionLayer(name='AttentionLayer')
attn_out, attn_states = attn_layer.call([encoder_outputs, decoder_outputs])