tensorflow - tensorflow 的 DynamicAttentionWrapper 模块问题

Question

我指的是Kaggle 笔记本。看起来下面的代码应该适用于 Tensorflow 1.1。在使用任何最新版本的 Tensorflow 运行此程序时，我收到以下错误：

“AttributeError：模块‘tensorflow.contrib.seq2seq’没有属性‘DynamicAttentionWrapper’”

所以我将DynamicAttentionWrapper修改为AttentionWrapper。现在我收到另一个错误说明：“ new () 缺少 3 个必需的位置参数：'time'、'alignments' 和 'alignment_history'”

 dec_cell = tf.contrib.seq2seq.DynamicAttentionWrapper(dec_cell,
                                                          attn_mech,
                                                          rnn_size)

    initial_state = tf.contrib.seq2seq.DynamicAttentionWrapperState(enc_state[0],
                                                                    _zero_state_tensors(rnn_size, 
                                                                                        batch_size, 
                                                                                        tf.float32)) 

有人可以在这里帮助我。

所以我修改了

# Build the graph
train_graph = tf.Graph()
# Set the graph to default to ensure that it is ready for training
with train_graph.as_default():

    # Load the model inputs    
    input_data, targets, lr, keep_prob, summary_length, max_summary_length, text_length = model_inputs()

    # Create the training and inference logits
    training_logits, inference_logits = seq2seq_model(tf.reverse(input_data, [-1]),
                                                      targets, 
                                                      keep_prob,   
                                                      text_length,
                                                      summary_length,
                                                      max_summary_length,
                                                      len(vocab_to_int)+1,
                                                      rnn_size, 
                                                      num_layers, 
                                                      vocab_to_int,
                                                      batch_size)

    # Create tensors for the training logits and inference logits
    # Step 1
    training_logits = tf.identity(training_logits.rnn_output, 'logits')
    # Step 2
    inference_logits = tf.identity(inference_logits.sample_id, name='predictions')

    # Create the weights for sequence_loss
    masks = tf.sequence_mask(summary_length, max_summary_length, dtype=tf.float32, name='masks')

    with tf.name_scope("optimization"):
        # Loss function
        cost = tf.contrib.seq2seq.sequence_loss(
            training_logits,
            targets,
            masks)

        # Optimizer
        optimizer = tf.train.AdamOptimizer(learning_rate)

        # Gradient Clipping
        gradients = optimizer.compute_gradients(cost)
        capped_gradients = [(tf.clip_by_value(grad, -5., 5.), var) for grad, var in gradients if grad is not None]
        train_op = optimizer.apply_gradients(capped_gradients)
print("Graph is built.")

标签： tensorflow