Tensorflow：ValueError：尺寸必須相等

Question

我運行了該教程的代碼，但出現以下錯誤

我讀過一些類似的帖子，但並沒有真正幫助我

ValueError：尺寸必須相等，但對於'RNN_forward / rnn / while / rnn / multi_rnn_cell / cell_0 / basic_lstm_cell / MatMul_1'（op：'MatMul'），輸入形狀分別為[250,128]，[364,256]，尺寸為128和364。

這是本教程結尾的代碼：

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)

我更改了應用分析的數據集，並嘗試對其進行調整。 您是否知道如何解決該錯誤？

我讀了一些類似的文章，但並沒有真正幫助我。

非常感謝你

Answer 1

瀏覽完本教程的鏈接后，我發現了同一問題的鏈接 。

建議將您的代碼與此存儲庫合並。

試試看，讓我知道它是否解決了問題:)

Answer 2

我通過該帖子解決了這個問題，我替換了以下代碼：

  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)

通過該代碼：

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

通過添加以下功能：

 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