1
我在Tensorflow中制作LSTM神经网络。Tensorflow LSTM - 在LSTM单元上的矩阵乘法
输入张量大小是92
import tensorflow as tf
from tensorflow.contrib import rnn
import data
test_x, train_x, test_y, train_y = data.get()
# Parameters
learning_rate = 0.001
epochs = 100
batch_size = 64
display_step = 10
# Network Parameters
n_input = 28 # input size
n_hidden = 128 # number of hidden layers
n_classes = 20 # output size
# Placeholders
x = tf.placeholder(dtype=tf.float32, shape=[None, n_input])
y = tf.placeholder(dtype=tf.float32, shape=[None, n_classes])
# Network
def LSTM(x):
W = tf.Variable(tf.random_normal([n_hidden, n_classes]), dtype=tf.float32) # weights
b = tf.Variable(tf.random_normal([n_classes]), dtype=tf.float32) # biases
x_shape = 92
x = tf.transpose(x)
x = tf.reshape(x, [-1, n_input])
x = tf.split(x, x_shape)
lstm = rnn.BasicLSTMCell(
num_units=n_hidden,
forget_bias=1.0
)
outputs, states = rnn.static_rnn(
cell=lstm,
inputs=x,
dtype=tf.float32
)
output = tf.matmul(outputs[-1], W) + b
return output
# Train Network
def train(x):
prediction = LSTM(x)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
output = sess.run(prediction, feed_dict={"x": train_x})
print(output)
train(x)
我没有得到任何错误,但我喂养大小92的输入张量,并且在LSTM函数矩阵乘法返回包含一个列表一个结果向量,当期望的数量是92时,每个输入一个结果向量。
问题是矩阵只乘以输出数组中的最后一项?就像这样:
output = tf.matmul(outputs[-1], W) + b
代替:
output = tf.matmul(outputs, W) + b
这是我收到的时候我做了后者的错误:
ValueError: Shape must be rank 2 but is rank 3 for 'MatMul' (op: 'MatMul') with input shapes: [92,?,128], [128,20].