【发布时间】：2016-10-26 21:41:55
【问题描述】：
我是 TensorFlow 新手，难以理解 RNN 模块。我正在尝试从 LSTM 中提取隐藏/单元状态。 对于我的代码，我使用来自https://github.com/aymericdamien/TensorFlow-Examples 的实现。
# tf Graph input
x = tf.placeholder("float", [None, n_steps, n_input])
y = tf.placeholder("float", [None, n_classes])
# Define weights
weights = {'out': tf.Variable(tf.random_normal([n_hidden, n_classes]))}
biases = {'out': tf.Variable(tf.random_normal([n_classes]))}
def RNN(x, weights, biases):
# Prepare data shape to match `rnn` function requirements
# Current data input shape: (batch_size, n_steps, n_input)
# Required shape: 'n_steps' tensors list of shape (batch_size, n_input)
# Permuting batch_size and n_steps
x = tf.transpose(x, [1, 0, 2])
# Reshaping to (n_steps*batch_size, n_input)
x = tf.reshape(x, [-1, n_input])
# Split to get a list of 'n_steps' tensors of shape (batch_size, n_input)
x = tf.split(0, n_steps, x)
# Define a lstm cell with tensorflow
#with tf.variable_scope('RNN'):
lstm_cell = rnn_cell.BasicLSTMCell(n_hidden, forget_bias=1.0, state_is_tuple=True)
# Get lstm cell output
outputs, states = rnn.rnn(lstm_cell, x, dtype=tf.float32)
# Linear activation, using rnn inner loop last output
return tf.matmul(outputs[-1], weights['out']) + biases['out'], states
pred, states = RNN(x, weights, biases)
# Define loss and optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
# Evaluate model
correct_pred = tf.equal(tf.argmax(pred,1), tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
# Initializing the variables
init = tf.initialize_all_variables()
现在我想为预测中的每个时间步提取单元格/隐藏状态。状态存储在 (c,h) 形式的 LSTMStateTuple 中，我可以通过评估 print states 找到它。但是，尝试调用 print states.c.eval()（根据文档应该给我张量 states.c 中的值）会产生一个错误，指出我的变量没有初始化，即使我在预测某些事情后立即调用它。代码在这里：
# Launch the graph
with tf.Session() as sess:
sess.run(init)
step = 1
# Keep training until reach max iterations
for v in tf.get_collection(tf.GraphKeys.VARIABLES, scope='RNN'):
print v.name
while step * batch_size < training_iters:
batch_x, batch_y = mnist.train.next_batch(batch_size)
# Reshape data to get 28 seq of 28 elements
batch_x = batch_x.reshape((batch_size, n_steps, n_input))
# Run optimization op (backprop)
sess.run(optimizer, feed_dict={x: batch_x, y: batch_y})
print states.c.eval()
# Calculate batch accuracy
acc = sess.run(accuracy, feed_dict={x: batch_x, y: batch_y})
step += 1
print "Optimization Finished!"
错误信息是
InvalidArgumentError: You must feed a value for placeholder tensor 'Placeholder' with dtype float
[[Node: Placeholder = Placeholder[dtype=DT_FLOAT, shape=[], _device="/job:localhost/replica:0/task:0/cpu:0"]()]]
在tf.all_variables() 中也看不到这些状态，只有经过训练的矩阵/偏置张量（如此处所述：Tensorflow: show or save forget gate values in LSTM）。我不想从头开始构建整个 LSTM，因为我在 states 变量中有状态，我只需要调用它。
【问题讨论】：
标签： python tensorflow lstm