Question

我目前正在尝试制作用于回归目的的RNN网络，能够接收任意数量的样本并使用张量流输出14长度特征向量。

此时网络运行不正常，我正在尝试调试此问题。以下是代码：

def length(sequence): ##Zero padding to fit the max lenght... Question whether that is a good idea.
    used = tf.sign(tf.reduce_max(tf.abs(sequence), reduction_indices=2))
    length = tf.reduce_sum(used, reduction_indices=1)
    length = tf.cast(length, tf.int32)
    return length

def cost(output, target):
    # Compute cross entropy for each frame.
    print output
    cross_entropy = target * tf.log(output)
    print "Hello world"
    cross_entropy = -tf.reduce_sum(cross_entropy, reduction_indices=2)
    mask = tf.sign(tf.reduce_max(tf.abs(target), reduction_indices=2))
    cross_entropy *= mask
    # Average over actual sequence lengths.
    cross_entropy = tf.reduce_sum(cross_entropy, reduction_indices=1)
    cross_entropy /= tf.reduce_sum(mask, reduction_indices=1)
    return tf.reduce_mean(cross_entropy)

def last_relevant(output):
    max_length = int(output.get_shape()[1])
    relevant = tf.reduce_sum(tf.mul(output, tf.expand_dims(tf.one_hot(length(output), max_length), -1)), 1)
    return relevant

files_train_path = [dnn_train+f for f in listdir(dnn_train) if isfile(join(dnn_train, f))]
files_test_path = [dnn_test+f for f in listdir(dnn_test) if isfile(join(dnn_test, f))]

files_train_name = [f for f in listdir(dnn_train) if isfile(join(dnn_train, f))]
files_test_name = [f for f in listdir(dnn_test) if isfile(join(dnn_test, f))]

os.chdir(dnn_train)

train_name,train_data = generate_list_of_names_data(files_train_path)
train_data, train_names, train_output_data, train_class_output = load_sound_files(files_train_path,train_name,train_data)

max_length = 0 ## Used for variable sequence input

for element in train_data:
    if element.size > max_length:
        max_length = element.size

NUM_EXAMPLES = len(train_data)/2

test_data = train_data[NUM_EXAMPLES:]
test_output = train_output_data[NUM_EXAMPLES:]

train_data = train_data[:NUM_EXAMPLES]
train_output = train_output_data[:NUM_EXAMPLES]
print("--- %s seconds ---" % (time.time() - start_time))

#----------------------------------------------------------------------#
#----------------------------Main--------------------------------------#
### Tensorflow neural network setup

batch_size = None
sequence_length_max = max_length
input_dimension=1

data = tf.placeholder(tf.float32,[batch_size,sequence_length_max,input_dimension])
target = tf.placeholder(tf.float32,[None,14])

num_hidden = 24 ## Hidden layer
cell = tf.nn.rnn_cell.LSTMCell(num_hidden,state_is_tuple=True)  ## Long short term memory

output, state = tf.nn.dynamic_rnn(cell, data, dtype=tf.float32,sequence_length = length(data))  ## Creates the Rnn skeleton

last = last_relevant(output)#tf.gather(val, int(val.get_shape()[0]) - 1) ## Appedning as last

weight = tf.Variable(tf.truncated_normal([num_hidden, int(target.get_shape()[1])]))
bias = tf.Variable(tf.constant(0.1, shape=[target.get_shape()[1]]))

prediction = tf.nn.softmax(tf.matmul(last, weight) + bias)

cross_entropy = cost(output,target)# How far am I from correct value?

optimizer = tf.train.AdamOptimizer() ## TensorflowOptimizer
minimize = optimizer.minimize(cross_entropy)

mistakes = tf.not_equal(tf.argmax(target, 1), tf.argmax(prediction, 1))
error = tf.reduce_mean(tf.cast(mistakes, tf.float32))

## Training ##

init_op = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init_op)

batch_size = 1000
no_of_batches = int(len(train_data)/batch_size)
epoch = 5000
for i in range(epoch):
    ptr = 0
    for j in range(no_of_batches):
        inp, out = train_data[ptr:ptr+batch_size], train_output[ptr:ptr+batch_size]
        ptr+=batch_size
        sess.run(minimize,{data: inp, target: out})
    print "Epoch - ",str(i)
incorrect = sess.run(error,{data: test_data, target: test_output})
print('Epoch {:2d} error {:3.1f}%'.format(i + 1, 100 * incorrect))
sess.close()

由于cross_entropy函数中的错误，代码无法完全执行。

Tensor("RNN/transpose:0", shape=(?, 138915, 24), dtype=float32)
Traceback (most recent call last):
  File "tensorflow_test.py", line 186, in <module>
    cross_entropy = cost(output,target)# How far am I from correct value?
  File "tensorflow_test.py", line 122, in cost
    cross_entropy = target * tf.log(output)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/math_ops.py", line 754, in binary_op_wrapper
    return func(x, y, name=name)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/math_ops.py", line 903, in _mul_dispatch
    return gen_math_ops.mul(x, y, name=name)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_math_ops.py", line 1427, in mul
    result = _op_def_lib.apply_op("Mul", x=x, y=y, name=name)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py", line 703, in apply_op
    op_def=op_def)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2312, in create_op
    set_shapes_for_outputs(ret)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1704, in set_shapes_for_outputs
    shapes = shape_func(op)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/math_ops.py", line 1801, in _BroadcastShape
    % (shape_x, shape_y))
ValueError: Incompatible shapes for broadcasting: (?, 14) and (?, 138915, 24)

在我看来，我从RNN收到的输出具有相当高的维度。我只期望一个包含14个元素的向量，因此是一维向量。但不知怎的，我最终得到了相当大的维度？为什么？我想我的神经网络设置中的某些内容必定是不正确的。

Answer 1

dynamic_rnn的输出形状[batch_size, num_steps, dim_hidden]。在您的情况下，RNN中的时间步数显然是138915.

为什么我的输出量如此之高？

1 个答案: