我一直在尝试在本机器学习掌握教程中显示的 LSTM 模型的输出上实现注意力包装器：
from numpy import array
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import TimeDistributed
from keras.layers import LSTM
# prepare sequence
length = 5
seq = array([i/float(length) for i in range(length)])
X = seq.reshape(1, length, 1)
y = seq.reshape(1, length, 1)
# define LSTM configuration
n_neurons = length
n_batch = 1
n_epoch = 1000
# create LSTM
model = Sequential()
model.add(LSTM(n_neurons, input_shape=(length, 1), return_sequences=True))
model.add(TimeDistributed(Dense(1)))
model.compile(loss='mean_squared_error', optimizer='adam')
print(model.summary())
# train LSTM
model.fit(X, y, epochs=n_epoch, batch_size=n_batch, verbose=2)
# evaluate
result = model.predict(X, batch_size=n_batch, verbose=0)
for value in result[0,:,0]:
print('%.1f' % value)
(samples, steps, features)LSTM的输出return_sequences = true由注意力包装器（输出形状（样本、特征））接收。这是我修改后的代码：
model = Sequential()
model.add(LSTM(n_neurons, input_shape=(length, 1), return_sequences=True))
model.add(Attention())
model.add(TimeDistributed(Dense(1)))
我一直在使用此处描述的注意包装器：
def dot_product(x, kernel):
if K.backend() == 'tensorflow':
# todo: check that this is correct
return K.squeeze(K.dot(x, K.expand_dims(kernel)), axis=-1)
else:
return K.dot(x, kernel)
class Attention(Layer):
def __init__(self,
W_regularizer=None, b_regularizer=None,
W_constraint=None, b_constraint=None,
bias=True, **kwargs):
self.supports_masking = True
self.init = initializers.get('glorot_uniform')
self.W_regularizer = regularizers.get(W_regularizer)
self.b_regularizer = regularizers.get(b_regularizer)
self.W_constraint = constraints.get(W_constraint)
self.b_constraint = constraints.get(b_constraint)
self.bias = bias
super(Attention, self).__init__(**kwargs)
def build(self, input_shape):
assert len(input_shape) == 3
self.W = self.add_weight((input_shape[-1],),
initializer=self.init,
name='{}_W'.format(self.name),
regularizer=self.W_regularizer,
constraint=self.W_constraint)
if self.bias:
self.b = self.add_weight((input_shape[1],),
initializer='zero',
name='{}_b'.format(self.name),
regularizer=self.b_regularizer,
constraint=self.b_constraint)
else:
self.b = None
self.built = True
def compute_mask(self, input, input_mask=None):
# do not pass the mask to the next layers
return None
def call(self, x, mask=None):
eij = dot_product(x, self.W)
if self.bias:
eij += self.b
eij = K.tanh(eij)
a = K.exp(eij)
# apply mask after the exp. will be re-normalized next
if mask is not None:
# Cast the mask to floatX to avoid float64 upcasting in theano
a *= K.cast(mask, K.floatx())
# in some cases especially in the early stages of training the sum may be almost zero
# and this results in NaN's. A workaround is to add a very small positive number ε to the sum.
# a /= K.cast(K.sum(a, axis=1, keepdims=True), K.floatx())
a /= K.cast(K.sum(a, axis=1, keepdims=True) + K.epsilon(), K.floatx())
a = K.expand_dims(a)
weighted_input = x * a
return K.sum(weighted_input, axis=1)
def get_output_shape_for(self, input_shape):
return input_shape[0], input_shape[-1]
但是，我得到的错误是：
ValueError：输入 0 与层 time_distributed_1 不兼容：预期 ndim=3，发现 ndim=2
有没有办法重新调整注意力包装器输出的形状以使用 TimeDistributed 层？