Tensorflow：ValueError：尺寸必须相等

Question

我运行了该教程的代码，但出现以下错误

我读过一些类似的帖子，但并没有真正帮助我

ValueError：尺寸必须相等，但对于'RNN_forward / rnn / while / rnn / multi_rnn_cell / cell_0 / basic_lstm_cell / MatMul_1'（op：'MatMul'），输入形状分别为[250,128]，[364,256]，尺寸为128和364。

这是本教程结尾的代码：

n_words = len(word_index)
embed_size = 300
batch_size = 250
lstm_size = 128
num_layers = 2
dropout = 0.5
learning_rate = 0.001
epochs = 100
multiple_fc = False
fc_units = 256


# Train the model with the desired tuning parameters# Train  
for lstm_size in [64,128]:
    for multiple_fc in [True, False]:
        for fc_units in [128, 256]:
            log_string = 'ru={},fcl={},fcu={}'.format(lstm_size,
                                                      multiple_fc,
                                                      fc_units)
            model = build_rnn(n_words = n_words, 
                              embed_size = embed_size,
                              batch_size = batch_size,
                              lstm_size = lstm_size,
                              num_layers = num_layers,
                              dropout = dropout,
                              learning_rate = learning_rate,
                              multiple_fc = multiple_fc,
                              fc_units = fc_units)            
            train(model, epochs, log_string)

我更改了应用分析的数据集，并尝试对其进行调整。 您是否知道如何解决该错误？

我读了一些类似的文章，但并没有真正帮助我。

非常感谢你

Answer 1

浏览完本教程的链接后，我发现了同一问题的链接 。

建议将您的代码与此存储库合并。

试试看，让我知道它是否解决了问题:)

Answer 2

我通过该帖子解决了这个问题，我替换了以下代码：

  with tf.name_scope('RNN_layers'):
   lstm = tf.contrib.rnn.BasicLSTMCell(lstm_size)
   drop = tf.contrib.rnn.DropoutWrapper(lstm, output_keep_prob=keep_prob)
   cell = tf.contrib.rnn.MultiRNNCell([drop] * num_layers)

通过该代码：

with tf.name_scope('RNN_layers'):
 cell = tf.contrib.rnn.MultiRNNCell([lstm_cell(lstm_size, keep_prob) for _ in 
 range(num_layers)])

通过添加以下功能：

 def lstm_cell(lstm_size, keep_prob):
    lstm = tf.contrib.rnn.BasicLSTMCell(lstm_size)
    drop = tf.contrib.rnn.DropoutWrapper(lstm, output_keep_prob=keep_prob)
    return drop