tensorflow keras running error about initializers

(Tensorflow version is 1.8)

Error Message contains : "lstm/lstm_cell/recurrent_kernel/Initializer/random_normal"

It means that it needs initailizers

Initializations define the way to set the initial random weights of Keras layers

The keyword arguments used for passing initializers to layers will depend on the layer. Usually it is simply kernel_initializer and bias_initializer:

model.add(Dense(64,
                kernel_initializer='random_uniform',
                bias_initializer='zeros'))

- from: https://keras.io/initializers

In tensorflow

model.add(Dense(32, activation='relu', kernel_initializer='random_uniform')) <- it works

Add kernel initializer to solve the error

(but when there is no bias_initializer, it works well, I think it is defined as default.)