Question

我正在建立一个RNN模型来进行图像分类。我使用管道输入数据。但它返回

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

我想知道我能做些什么来解决这个问题，因为没有很多用输入管道实现RNN的例子。我知道如果我使用占位符它会起作用，但我的数据已经是张量形式。除非我可以使用张量来提供占位符，否则我更喜欢使用管道。

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

您需要正确使用reuse选项。以下更改将解决它。对于预测，您需要使用图中已存在的变量。

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))

tensorflow RNN实现

1 个答案: