keras 注意：不兼容的形状：[32,2] 与 [1200,2]

Question

我正在尝试将注意力层添加到我的模型中以进行文本分类。但是在添加图层然后拟合模型后出现错误。这是我的代码：

model = Sequential()
for i in range(len(kernel_size)):
    model.add(Conv1D(filters=nb_filter, kernel_size=kernel_size[i], padding='valid', activation='relu',
                     input_shape=(data_batch_size, emb_dim)))
    model.add(MaxPooling1D(pool_size=pool_size))
model.add(Bidirectional(LSTM(units=lstm_out, return_sequences=True), merge_mode='concat',
                        input_shape=(X_train.shape[1], X_train.shape[2])))
model.add(Bidirectional(LSTM(units=lstm_out, go_backwards=True)))

# ------------------------------------------------------------------------------------------------------------
# ------------------------------------------------------------------------------------------------------------

model.add(Attention(return_sequences=True))

# ------------------------------------------------------------------------------------------------------------
# ------------------------------------------------------------------------------------------------------------

model.add(Dropout(DropoutP))
model.add(Dense(cat_output, activation='sigmoid'))

model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])

Y_tmp = np.zeros([Y_train.shape[0], 2])
Y_tmp[:, 0] = 2 - Y_train
Y_tmp[:, 1] = Y_train - 1
Y_train = Y_tmp

history = model.fit(X_train, Y_train, validation_split=test_size, epochs=nb_epoch, verbose=1,
                    callbacks=[EarlyStopping(monitor='val_accuracy', patience=0, restore_best_weights=True)])

这就是注意力class：

class Attention(Layer):

def __init__(self, return_sequences=True):
    self.return_sequences = return_sequences
    super(Attention, self).__init__()

def build(self, input_shape):
    self.W = self.add_weight(name="att_weight", shape=(input_shape[-1], 1), initializer="normal")
    self.b = self.add_weight(name="att_bias", shape=(input_shape[1], 1), initializer="zeros")

    super(Attention, self).build(input_shape)

def call(self, x):
    e = K.tanh(K.dot(x, self.W) + self.b)
    a = K.softmax(e, axis=1)
    output = x * a

    if self.return_sequences:
        return output

    return K.sum(output, axis=1)

这是错误：不兼容的形状：[32,2] 与 [1200,2]

我做错了什么？

Answer 1

有问题：

self.b = self.add_weight(name="att_bias", shape=(input_shape[1], 1), initializer="zeros")

应该是：

self.b = self.add_weight(name="att_bias", shape=(1,), initializer="zeros")

其实你是在重新定义Dense层。要亲自查看，您可以查看 layers and models via sub-classing.
中的自定义 Linear 层 custom attention layer 实际上是您想要使用 Dense 层并且更通用（Bahdanau 注意力层）。

keras 注意：不兼容的形状：[32,2] 与 [1200,2]

keras Attention: Incompatible shapes: [32,2] vs. [1200,2]

python

tensorflow

machine-learning

keras

attention-model