双向层：维度值必须为整数或无，或者具有__index__方法，获得'1932.0'类型为"<类'float'>的值

Question

这是我第一次使用双向层，但我没有找到任何使用Keras功能API的例子。mask_mastrix是一个具有形状(样本、时间步长(的张量，其二进制值为True/False。

with strategy.scope():
input_tensor = Input(shape=(timesteps, features))
enc = Bidirectional(LSTM(timesteps * 2, activation = 'tanh', return_sequences = True))(input_tensor, mask=mask_matrix)
enc = Bidirectional(LSTM(timesteps * 1.5, activation = 'tanh', return_sequences = False))(enc)

decode1 = RepeatVector(timesteps)(enc)
decode1 = Bidirectional(LSTM(200, activation = 'tanh', return_sequences = True))(decode1)
decode1 = Bidirectional(LSTM(timesteps, activation = 'tanh', return_sequences = True))(decode1)
decode1 = TimeDistributed(Dense(8, activation="softmax"), name="dec1")(decode1)
decode2 = RepeatVector(timesteps)(enc)
decode2 = Bidirectional(LSTM(timesteps, activation = 'tanh', return_sequences = True))(decode2)
decode2 = TimeDistributed(Dense(2, activation = "tanh"), name="dec2")(decode2)

new_model = Model(inputs=input_tensor, outputs = [decode1, decode2])
new_model.compile(loss={"dec1":"categorical_crossentropy", "dec2":'mse'}, optimizer='adam')
plot_model(new_model, to_file='model.png')

我得到以下错误：

Dimension value must be integer or None or have an __index__ method, got value '1932.0' with type '<class 'float'>'

我对此有两个问题：

1. 是什么导致了这个问题以及如何解决它
2. 使用双向层时，遮罩值是如何工作的？因为根据我的理解，这个层创建了两个LSTM：第一个是前向序列，第二个是后向序列(以获得整个上下文(。掩码的论点也会被推翻吗

提前感谢！

Answer 1

更改此行：

enc = Bidirectional(LSTM(timesteps * 2 // 3, activation = 'tanh', return_sequences = False))(enc)