[英]tf.matmul doesn't works as expected
我尝试在张量流中写入和(逻辑运算),有两个输入和两个权重乘以得到一个数字并将此数字加到偏差,我的问题在matmul中发送X(输入)和W(权重)到方法在形状。 [[1],[1]]用于X(垂直),[0.49900547,0.49900547]用于W(水平)得到一个数字作为结果,但是它给了我两个数字,我怎么做才能乘以? 这是我的代码>>
import tensorflow as tf
import numpy
rng = numpy.random
# Parameters
learning_rate = 0.01
training_epochs = 2000
display_step = 50
# Training Data
train_X = numpy.asarray([[[1.0],[1.0]],[[1.0],[0.0]],[[0.0],[1.0]],[[0.0],[0.0]]])
train_Y = numpy.asarray([1.0,0.0,0.0,0.0])
n_samples = train_X.shape[0]
# tf Graph Input
X = tf.placeholder("float",[2,1],name="inputarr")
Y = tf.placeholder("float",name = "outputarr")
# Create Model
# Set model weights
W = tf.Variable(tf.zeros([1,2]), name="weight")
b = tf.Variable(rng.randn(), name="bias")
# Construct a linear model
activation = tf.add(tf.matmul(X,W), b)
mulres = tf.matmul(X,W)
# Minimize the squared errors
cost = tf.reduce_sum(tf.pow(activation-Y, 2))/(2*n_samples) #L2 loss
optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost) #Gradient descent
# Initializing the variables
init = tf.initialize_all_variables()
# Launch the graph
with tf.Session() as sess:
sess.run(init)
# Fit all training data
for epoch in range(training_epochs):
for (x, y) in zip(train_X, train_Y):
sess.run(optimizer, feed_dict={X: x, Y: y})
#Display logs per epoch step
if epoch % display_step == 0:
print "Epoch:", '%04d' % (epoch+1), \
"W=", sess.run(W), "b=", sess.run(b) , "x= ",x," y =", y," result :",sess.run(mulres,feed_dict={X: x})
print "Optimization Finished!"
print "W=", sess.run(W), "b=", sess.run(b), '\n'
# Testing example, as requested (Issue #2)
test_X = numpy.asarray([[1.0,0.0]])
test_Y = numpy.asarray([0])
for x, y in zip(train_X, train_Y):
print "x: ",x,"y: ",y
print "Testing... (L2 loss Comparison)","result :",sess.run(mulres, feed_dict={X: x})
print sess.run(tf.matmul(X, W),feed_dict={X: x})
print "result :"
predict = sess.run(activation,feed_dict={X: x})
print predict
与标准矩阵乘法一样,如果A
具有形状[m, k]
,并且B
具有形状[k, n]
,则tf.matmul(A, B)
具有形状[m, n]
( m
行, n
列,订单TensorFlow使用)。
在你的程序中,你正在计算tf.matmul(X, W)
。 X
被定义为具有形状[2, 1]
的占位符; W
被定义为初始化为零的[1, 2]
矩阵的变量。 因此,当我在本地运行代码时, mulres = tf.matmul(X, W)
将具有形状[2, 2]
,这是打印的result: ...
( result: ...
)。
如果要使用单个输出定义隐藏层,则更改很简单:
W = tf.Variable(tf.zeros([1,2]), name="weight")
......应该替换为:
W = tf.Variable(tf.zeros([2, 1]), name="weight")
(实际上,将权重初始化为tf.zeros
会阻止它进行训练,因为所有输入元素在反向传播中都会得到相同的渐变。相反,您应该随机初始化它们,例如使用:
W = tf.Variable(tf.truncated_normal([2, 1], stddev=0.5), name="weight")
这将使网络能够为权重的每个组成部分学习不同的值。)
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.