AttributeError：模块'tensorflow.contrib.seq2seq'没有属性'prepare_attention'
我知道不推荐使用prepare_attention（）。有什么替代方案？另请注明语法。
我正在使用的功能是： def decoding_layer_train（encoder_state，dec_cell，dec_embed_input，sequence_length，decoding_scope， output_fn，keep_prob，batch_size）： '''解码训练数据'''
attention_states = tf.zeros([batch_size, 1, dec_cell.output_size])
att_keys, att_vals, att_score_fn, att_construct_fn = tf.contrib.seq2seq.prepare_attention(attention_states,
attention_option="bahdanau",
num_units=dec_cell.output_size)
train_decoder_fn = tf.contrib.seq2seq.attention_decoder_fn_train(encoder_state[0],
att_keys,
att_vals,
att_score_fn,
att_construct_fn,
name = "attn_dec_train")
train_pred, _, _ = tf.contrib.seq2seq.dynamic_rnn_decoder(dec_cell,
train_decoder_fn,
dec_embed_input,
sequence_length,
scope=decoding_scope)
train_pred_drop = tf.nn.dropout(train_pred, keep_prob)
return output_fn(train_pred_drop)