基于attention的BiGRU的keras实现

from tensorflow.python.keras.layers import Input, GRU, Dense, Concatenate, TimeDistributed, Bidirectional
from tensorflow.python.keras.models import Model
from layers.attention import AttentionLayer


def define_nmt(hidden_size, batch_size, en_timesteps, en_vsize, fr_timesteps, fr_vsize):
    """ Defining a NMT model """

    # Define an input sequence and process it.
    if batch_size:
        encoder_inputs = Input(batch_shape=(batch_size, en_timesteps, en_vsize), name='encoder_inputs')
        decoder_inputs = Input(batch_shape=(batch_size, fr_timesteps - 1, fr_vsize), name='decoder_inputs')
    else:
        encoder_inputs = Input(shape=(en_timesteps, en_vsize), name='encoder_inputs')
        decoder_inputs = Input(shape=(fr_timesteps - 1, fr_vsize), name='decoder_inputs')

    # Encoder GRU