keras/layers/recurrent.py [596:623]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            pass
        elif self.stateful:
            initial_state = self.states
        else:
            initial_state = self.get_initial_state(inputs)

        if isinstance(mask, list):
            mask = mask[0]

        if len(initial_state) != len(self.states):
            raise ValueError('Layer has ' + str(len(self.states)) +
                             ' states but was passed ' +
                             str(len(initial_state)) +
                             ' initial states.')
        input_shape = K.int_shape(inputs)
        timesteps = input_shape[1]
        if self.unroll and timesteps in [None, 1]:
            raise ValueError('Cannot unroll a RNN if the '
                             'time dimension is undefined or equal to 1. \n'
                             '- If using a Sequential model, '
                             'specify the time dimension by passing '
                             'an `input_shape` or `batch_input_shape` '
                             'argument to your first layer. If your '
                             'first layer is an Embedding, you can '
                             'also use the `input_length` argument.\n'
                             '- If using the functional API, specify '
                             'the time dimension by passing a `shape` '
                             'or `batch_shape` argument to your Input layer.')
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



keras/legacy/layers.py [553:580]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            pass
        elif self.stateful:
            initial_state = self.states
        else:
            initial_state = self.get_initial_state(inputs)

        if isinstance(mask, list):
            mask = mask[0]

        if len(initial_state) != len(self.states):
            raise ValueError('Layer has ' + str(len(self.states)) +
                             ' states but was passed ' +
                             str(len(initial_state)) +
                             ' initial states.')
        input_shape = K.int_shape(inputs)
        timesteps = input_shape[1]
        if self.unroll and timesteps in [None, 1]:
            raise ValueError('Cannot unroll a RNN if the '
                             'time dimension is undefined or equal to 1. \n'
                             '- If using a Sequential model, '
                             'specify the time dimension by passing '
                             'an `input_shape` or `batch_input_shape` '
                             'argument to your first layer. If your '
                             'first layer is an Embedding, you can '
                             'also use the `input_length` argument.\n'
                             '- If using the functional API, specify '
                             'the time dimension by passing a `shape` '
                             'or `batch_shape` argument to your Input layer.')
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -