我正在尝试使用Tensorflow（r0.10，python 3.5）训练一个关于玩具分类问题的回归神经网络，但是我得到了令人困惑的结果。
我希望将一系列0和1的序列输入到RNN中，并使序列的给定元素的目标类为序列的当前值和先前值所表示的数字，将其视为二进制数。例如：
input sequence: [0, 0, 1, 0, 1, 1]
binary digits : [-, [0,0], [0,1], [1,0], [0,1], [1,1]]
target class : [-, 0, 1, 2, 1, 3]
似乎这是RNN应该能够很容易地学习的东西，但我的模型只能区分[0,2]和[1,3]。换句话说，它能够将当前数字为0的类与当前数字为1的类区分开来。这使我相信RNN模型没有正确地学习查看序列的先前值。
有几个教程和示例（[1]，[2]，[3]）演示了如何在tensorflow中构建和使用递归神经网络（RNN），但在研究它们之后，我仍然没有看到我的问题（所有示例都使用文本作为源数据并没有帮助。）
我将我的数据输入tf.nn.rnn()作为长度为T的列表，其元素为[batch_size x input_size]个序列。由于我的序列是一维的，input_size等于1，所以基本上我相信我输入了长度为batch_size的序列列表（documentation我不清楚哪个维度是被视为时间维度）。 这种理解是否正确？如果是这种情况，那么我不明白为什么RNN模型没有正确学习。
很难获得一小段可以通过我的完整RNN运行的代码，这是我能做的最好的（它主要是从the PTB model here和the char-rnn model here改编而来的）：
import tensorflow as tf
import numpy as np
input_size = 1
batch_size = 50
T = 2
lstm_size = 5
lstm_layers = 2
num_classes = 4
learning_rate = 0.1
lstm = tf.nn.rnn_cell.BasicLSTMCell(lstm_size, state_is_tuple=True)
lstm = tf.nn.rnn_cell.MultiRNNCell([lstm] * lstm_layers, state_is_tuple=True)
x = tf.placeholder(tf.float32, [T, batch_size, input_size])
y = tf.placeholder(tf.int32, [T * batch_size * input_size])
init_state = lstm.zero_state(batch_size, tf.float32)
inputs = [tf.squeeze(input_, [0]) for input_ in tf.split(0,T,x)]
outputs, final_state = tf.nn.rnn(lstm, inputs, initial_state=init_state)
w = tf.Variable(tf.truncated_normal([lstm_size, num_classes]), name='softmax_w')
b = tf.Variable(tf.truncated_normal([num_classes]), name='softmax_b')
output = tf.concat(0, outputs)
logits = tf.matmul(output, w) + b
probs = tf.nn.softmax(logits)
cost = tf.reduce_mean(tf.nn.seq2seq.sequence_loss_by_example(
[logits], [y], [tf.ones_like(y, dtype=tf.float32)]
))
optimizer = tf.train.GradientDescentOptimizer(learning_rate)
tvars = tf.trainable_variables()
grads, _ = tf.clip_by_global_norm(tf.gradients(cost, tvars),
10.0)
train_op = optimizer.apply_gradients(zip(grads, tvars))
init = tf.initialize_all_variables()
with tf.Session() as sess:
sess.run(init)
curr_state = sess.run(init_state)
for i in range(3000):
# Create toy data where the true class is the value represented
# by the current and previous value treated as binary, i.e.
train_x = np.random.randint(0,2,(T * batch_size * input_size))
train_y = train_x + np.concatenate(([0], (train_x[:-1] * 2)))
# Reshape into T x batch_size x input_size
train_x = np.reshape(train_x, (T, batch_size, input_size))
feed_dict = {
x: train_x, y: train_y
}
for j, (c, h) in enumerate(init_state):
feed_dict[c] = curr_state[j].c
feed_dict[h] = curr_state[j].h
fetch_dict = {
'cost': cost, 'final_state': final_state, 'train_op': train_op
}
# Evaluate the graph
fetches = sess.run(fetch_dict, feed_dict=feed_dict)
curr_state = fetches['final_state']
if i % 300 == 0:
print('step {}, train cost: {}'.format(i, fetches['cost']))
# Test
test_x = np.array([[0],[0],[1],[0],[1],[1]]*(T*batch_size*input_size))
test_x = test_x[:(T*batch_size*input_size),:]
probs_out = sess.run(probs, feed_dict={
x: np.reshape(test_x, [T, batch_size, input_size]),
init_state: curr_state
})
# Get the softmax outputs for the points in the sequence
# that have [0, 0], [0, 1], [1, 0], [1, 1] as their
# last two values.
for i in [1, 2, 3, 5]:
print('{}: [{:.4f} {:.4f} {:.4f} {:.4f}]'.format(
[1, 2, 3, 5].index(i), *list(probs_out[i,:]))
)
这里的最终输出是
0: [0.4899 0.0007 0.5080 0.0014]
1: [0.0003 0.5155 0.0009 0.4833]
2: [0.5078 0.0011 0.4889 0.0021]
3: [0.0003 0.5052 0.0009 0.4936]
表示它只是学习区分[0,2]和[1,3]。 为什么这个模型不能学习使用序列中的先前值？
答案 0 :(得分：3)
在this blog post的帮助下计算出来（它有很好的输入张量图）。事实证明，我没有正确理解tf.nn.rnn()输入的形状：
让我们说你有batch_size个序列。每个序列都有input_size个维度，长度为T（选择这些名称以匹配tf.nn.rnn() here的文档。然后，您需要将输入拆分为T - 长度列表，其中每个元素的形状为batch_size x input_size。 这意味着您的连续序列将分布在列表 的元素中。我认为连续序列将保持在一起，以便列表inputs中的每个元素都是一个序列的示例。
回想起来这是有道理的，因为我们希望并行化序列中的每一步，所以我们想要运行每个序列的第一步（列表中的第一个元素），然后是每个序列的第二步（列表中的第二个元素） ）等等。
代码的工作版本：
import tensorflow as tf
import numpy as np
sequence_size = 50
batch_size = 7
num_features = 1
lstm_size = 5
lstm_layers = 2
num_classes = 4
learning_rate = 0.1
lstm = tf.nn.rnn_cell.BasicLSTMCell(lstm_size, state_is_tuple=True)
lstm = tf.nn.rnn_cell.MultiRNNCell([lstm] * lstm_layers, state_is_tuple=True)
x = tf.placeholder(tf.float32, [batch_size, sequence_size, num_features])
y = tf.placeholder(tf.int32, [batch_size * sequence_size * num_features])
init_state = lstm.zero_state(batch_size, tf.float32)
inputs = [tf.squeeze(input_, [1]) for input_ in tf.split(1,sequence_size,x)]
outputs, final_state = tf.nn.rnn(lstm, inputs, initial_state=init_state)
w = tf.Variable(tf.truncated_normal([lstm_size, num_classes]), name='softmax_w')
b = tf.Variable(tf.truncated_normal([num_classes]), name='softmax_b')
output = tf.reshape(tf.concat(1, outputs), [-1, lstm_size])
logits = tf.matmul(output, w) + b
probs = tf.nn.softmax(logits)
cost = tf.reduce_mean(tf.nn.seq2seq.sequence_loss_by_example(
[logits], [y], [tf.ones_like(y, dtype=tf.float32)]
))
# Now optimize on that cost
optimizer = tf.train.GradientDescentOptimizer(learning_rate)
tvars = tf.trainable_variables()
grads, _ = tf.clip_by_global_norm(tf.gradients(cost, tvars),
10.0)
train_op = optimizer.apply_gradients(zip(grads, tvars))
init = tf.initialize_all_variables()
with tf.Session() as sess:
sess.run(init)
curr_state = sess.run(init_state)
for i in range(3000):
# Create toy data where the true class is the value represented
# by the current and previous value treated as binary, i.e.
train_x = np.random.randint(0,2,(batch_size * sequence_size * num_features))
train_y = train_x + np.concatenate(([0], (train_x[:-1] * 2)))
# Reshape into T x batch_size x sequence_size
train_x = np.reshape(train_x, [batch_size, sequence_size, num_features])
feed_dict = {
x: train_x, y: train_y
}
for j, (c, h) in enumerate(init_state):
feed_dict[c] = curr_state[j].c
feed_dict[h] = curr_state[j].h
fetch_dict = {
'cost': cost, 'final_state': final_state, 'train_op': train_op
}
# Evaluate the graph
fetches = sess.run(fetch_dict, feed_dict=feed_dict)
curr_state = fetches['final_state']
if i % 300 == 0:
print('step {}, train cost: {}'.format(i, fetches['cost']))
# Test
test_x = np.array([[0],[0],[1],[0],[1],[1]]*(batch_size * sequence_size * num_features))
test_x = test_x[:(batch_size * sequence_size * num_features),:]
probs_out = sess.run(probs, feed_dict={
x: np.reshape(test_x, [batch_size, sequence_size, num_features]),
init_state: curr_state
})
# Get the softmax outputs for the points in the sequence
# that have [0, 0], [0, 1], [1, 0], [1, 1] as their
# last two values.
for i in [1, 2, 3, 5]:
print('{}: [{:.4f} {:.4f} {:.4f} {:.4f}]'.format(
[1, 2, 3, 5].index(i), *list(probs_out[i,:]))
)