我正在尝试在 tensorflow 中设计一个简单的 lstm。我想将一系列数据分为 1 到 10 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]]
为了使其适用于 lstm 输入，我首先将其转换为张量，然后对其进行整形(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单热编码标签。
#------------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 tensorflow 图创建了占位符，制作了 lstm 单元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，但在训练步骤出现了错误。这与输入形状有关吗？这是回溯---
追溯(最近的调用最后):
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
请您参考如下方法:
看看你的代码，你的 rnn 输出应该有一个维度 batch_size x 1 x num_hidden 而你的 w 有维度 batch_size x num_classes x 1 但是你想要乘法这两个是 batcH_size x num_classes。
你能试试 output = tf.reshape(output, [batch_size, num_hidden]) 和 weight = tf.Variable(tf.random_normal([num_hidden, num_classes])) 让我知道进展如何？
