張量流RNN實現

Question

我正在構建一個RNN模型來完成圖像分類。我用一條管道輸入數據。但是它返回

ValueError: Variable rnn/rnn/basic_rnn_cell/weights already exists, disallowed. Did you mean to set reuse=True in VarScope? Originally defined at: 

我不知道我能做些什麼來解決這個問題，因爲不存在具有輸入管道實現RNN的例子很多。我知道如果我使用佔位符，它會起作用，但我的數據已經是張量的形式。除非我可以用張量填充佔位符，否則我寧願只使用管道。

def RNN(inputs): 
with tf.variable_scope('cells', reuse=True): 
    basic_cell = tf.contrib.rnn.BasicRNNCell(num_units=batch_size) 

with tf.variable_scope('rnn'): 
    outputs, states = tf.nn.dynamic_rnn(basic_cell, inputs, dtype=tf.float32) 

fc_drop = tf.nn.dropout(states, keep_prob) 

logits = tf.contrib.layers.fully_connected(fc_drop, batch_size, activation_fn=None) 

return logits 

#Training 
with tf.name_scope("cost_function") as scope: 
    cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=train_label_batch, logits=RNN(train_batch))) 
    train_step = tf.train.MomentumOptimizer(learning_rate, 0.9).minimize(cost) 


#Accuracy 
with tf.name_scope("accuracy") as scope: 
    correct_prediction = tf.equal(tf.argmax(RNN(test_image), 1), tf.argmax(test_image_label, 0)) 
    accuracy = tf.cast(correct_prediction, tf.float32) 

Answer 1

您需要正確使用reuse選項。以下更改將解決它。爲了預測，你需要使用圖中已經存在的變量。

def RNN(inputs, reuse): 
    with tf.variable_scope('cells', reuse=reuse): 
     basic_cell = tf.contrib.rnn.BasicRNNCell(num_units=batch_size, reuse=reuse) 

    ... 

... 
#Training 
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=train_label_batch, logits=RNN(train_batch, reuse=None))) 

#Accuracy 
... 
    correct_prediction = tf.equal(tf.argmax(RNN(test_image, reuse=True), 1), tf.argmax(test_image_label, 0))