我想为回归建立一个玩具LSTM模型。 This不错的教程对初学者来说已经太复杂了。TensorFlow dynamic_rnn regressor:ValueError尺寸不匹配
给定长度为time_steps
的序列,预测下一个值。考虑time_steps=3
和序列:
array([
[[ 1.],
[ 2.],
[ 3.]],
[[ 2.],
[ 3.],
[ 4.]],
...
目标值应该是:
array([ 4., 5., ...
我定义了以下模型:
# Network Parameters
time_steps = 3
num_neurons= 64 #(arbitrary)
n_features = 1
# tf Graph input
x = tf.placeholder("float", [None, time_steps, n_features])
y = tf.placeholder("float", [None, 1])
# Define weights
weights = {
'out': tf.Variable(tf.random_normal([n_hidden, 1]))
}
biases = {
'out': tf.Variable(tf.random_normal([1]))
}
#LSTM model
def lstm_model(X, weights, biases, learning_rate=0.01, optimizer='Adagrad'):
# Prepare data shape to match `rnn` function requirements
# Current data input shape: (batch_size, time_steps, n_features)
# Required shape: 'time_steps' tensors list of shape (batch_size, n_features)
# Permuting batch_size and time_steps
input dimension: Tensor("Placeholder_:0", shape=(?, 3, 1), dtype=float32)
X = tf.transpose(X, [1, 0, 2])
transposed dimension: Tensor("transpose_41:0", shape=(3, ?, 1), dtype=float32)
# Reshaping to (time_steps*batch_size, n_features)
X = tf.reshape(X, [-1, n_features])
reshaped dimension: Tensor("Reshape_:0", shape=(?, 1), dtype=float32)
# Split to get a list of 'time_steps' tensors of shape (batch_size, n_features)
X = tf.split(0, time_steps, X)
splitted dimension: [<tf.Tensor 'split_:0' shape=(?, 1) dtype=float32>, <tf.Tensor 'split_:1' shape=(?, 1) dtype=float32>, <tf.Tensor 'split_:2' shape=(?, 1) dtype=float32>]
# LSTM cell
cell = tf.nn.rnn_cell.LSTMCell(num_neurons) #Or GRUCell(num_neurons)
output, state = tf.nn.dynamic_rnn(cell=cell, inputs=X, dtype=tf.float32)
output = tf.transpose(output, [1, 0, 2])
last = tf.gather(output, int(output.get_shape()[0]) - 1)
return tf.matmul(last, weights['out']) + biases['out']
我们实例化LSTM模型pred = lstm_model(x, weights, biases)
我得到以下:
---> output, state = tf.nn.dynamic_rnn(cell=cell, inputs=X, dtype=tf.float32)
ValueError: Dimension must be 2 but is 3 for 'transpose_42' (op: 'Transpose') with input shapes: [?,1], [3]
1)你知道问题是什么吗?
2)将权重乘以LSTM输出产生回归?
你能分享错误的完整堆栈跟踪吗?从错误消息看来,有些'tf.transpose()'op被应用于2-D张量,但维度排列(第二个参数)有三个值。我猜想它来自[此行](https://github.com/tensorflow/tensorflow/blob/dc7293fe0f8084af1f608a5f0d4e93acd9f597f6/tensorflow/python/ops/rnn.py#L488),问题是'tf.nn .dynamic_rnn()'期望所有的时间步长被打包在一个张量中。尝试删除'tf.split()'并将原始的'X'值传递给'tf.nn.dynamic_rnn()'。 – mrry
@mrry我相信dynamic_rdd()的输入维度应该是(batch_size,time_steps,n_features)。因此,我不应该需要“预处理”步骤 – mastro
正确。我认为这是一个糟糕的错误消息。您正在传递'time_steps'二维张量列表,但正确的输入将是一个单一的3D张量(并且第一个维度应该是'batch_size'而不是'time_steps',所以不需要转置其一)。 – mrry