在张量流中使用 LSTM RNN 进行分类，ValueError: Shape (1, 10, 5) must have rank 2

Question

我正在尝试在 tensorflow 中设计一个简单的 lstm。我想将一个数据序列分类为从 1 到 10 的类。

我有 10 个时间戳和数据 X。我现在只采用一个序列，所以我的批量大小 = 1。 在每个时期，都会生成一个新序列。例如 X 是一个像这样的 numpy 数组-

X [[ 2.52413028  2.49449348  2.46520466  2.43625973  2.40765466  2.37938545
     2.35144815  2.32383888  2.29655379  2.26958905]]

为了使其适合 lstm 输入，我首先将其转换为张量，然后对其进行重构（batch_size、sequence_lenght、输入维度）-

X= np.array([amplitude * np.exp(-t / tau)])
print 'X', X

#Sorting out the input
train_input = X
train_input = tf.convert_to_tensor(train_input)
train_input = tf.reshape(train_input,[1,10,1])
print 'ti', train_input

对于输出，我在 1 到 10 的类别范围内生成一个热编码标签。

#------------sorting out the output
train_output= [int(math.ceil(tau/resolution))]
train_output= one_hot(train_output, num_labels=10)
print 'label', train_output

train_output = tf.convert_to_tensor(train_output)

>>label [[ 0.  1.  0.  0.  0.  0.  0.  0.  0.  0.]]

然后我为张量流图创建了占位符，制作了 lstm 单元格并给出了权重和偏差-

data = tf.placeholder(tf.float32, shape= [batch_size,len(t),1])
target = tf.placeholder(tf.float32, shape = [batch_size, num_classes])

cell = tf.nn.rnn_cell.LSTMCell(num_hidden)
output, state = rnn.dynamic_rnn(cell, data, dtype=tf.float32)

weight = tf.Variable(tf.random_normal([batch_size, num_classes, 1])),
bias = tf.Variable(tf.random_normal([num_classes]))

#training
prediction = tf.nn.softmax(tf.matmul(output,weight) + bias)
cross_entropy = -tf.reduce_sum(target * tf.log(prediction))
optimizer = tf.train.AdamOptimizer()
minimize = optimizer.minimize(cross_entropy)

到目前为止，我已经编写了代码，但在训练步骤中出现了错误。它与输入形状有关吗？这是回溯---

Traceback（最近一次调用最后一次）：

  File "/home/raisa/PycharmProjects/RNN_test1/test3.py", line 66, in <module>
prediction = tf.nn.softmax(tf.matmul(output,weight) + bias)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/math_ops.py", line 1036, in matmul
name=name)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_math_ops.py", line 911, in _mat_mul
transpose_b=transpose_b, name=name)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/op_def_library.py", line 655, in apply_op
op_def=op_def)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2156, in create_op
set_shapes_for_outputs(ret)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1612, in set_shapes_for_outputs
shapes = shape_func(op)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/common_shapes.py", line 81, in matmul_shape
a_shape = op.inputs[0].get_shape().with_rank(2)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/tensor_shape.py", line 625, in with_rank
raise ValueError("Shape %s must have rank %d" % (self, rank))
ValueError: Shape (1, 10, 5) must have rank 2

Answer 1

查看您的代码，您的 rnn 输出的维度应为 batch_size x 1 x num_hidden，而您的 w 的维度应为 batch_size x num_classes x 1，但是您希望将这两者相乘为 batcH_size x num_classes。

您可以试试output = tf.reshape(output, [batch_size, num_hidden]) 和weight = tf.Variable(tf.random_normal([num_hidden, num_classes])) 并告诉我这是怎么回事吗？

Answer 2

如果您使用的是 TF >= 1.0，则可以利用 tf.contrib.rnn 库和 OutputProjectionWrapper 将全连接层添加到 RNN 的输出中。比如：

# Network definition.
cell = tf.contrib.rnn.LSTMCell(num_hidden)
cell = tf.contrib.rnn.OutputProjectionWrapper(cell, num_classes)  # adds an output FC layer for you
output, state = tf.nn.dynamic_rnn(cell, data, dtype=tf.float32)

# Training.
cross_entropy = tf.nn.softmax_cross_entropy_with_logits(logits=output, labels=targets)
cross_entropy = tf.reduce_sum(cross_entropy)
optimizer = tf.train.AdamOptimizer()
minimize = optimizer.minimize(cross_entropy)

请注意，我使用的是 softmax_cross_entropy_with_logits，而不是使用您的 prediction 操作并手动计算交叉熵。它应该更高效、更健壮。

OutputProjectionWrapper 基本上做同样的事情，但它可能有助于缓解一些头痛。