Tensorflow 多项式数组

Question

我正在尝试评估aX^2+bX+c，就像[a,b,c]\*[X*X X 1]在张量流中一样。我试过以下代码：import tensorflow as tfX = tf.placeholder(tf.float32, name="X")W = tf.Variable([1,2,1], dtype=tf.float32, name="weights")W=tf.reshape(W,[1,3])F = tf.Variable([X*X,X,1.0], dtype=tf.float32, name="Filter")F=tf.reshape(F,[3,1])print(W.shape)print(F.shape)Y=tf.matmul(W,F)with tf.Session() as sess:    sess.run(tf.global_variables_initializer())    for i in range(10):         sess.run(Y, feed_dict={X: i})    Y=sess.run(Y)print("Y:",Y)但是，初始化程序并不高兴：(1, 3)(3, 1)...tensorflow.python.framework.errors_impl.InvalidArgumentError: You must feed a value for placeholder tensor 'X' with dtype float     [[{{node X}}]]During handling of the above exception, another exception occurred:...Caused by op 'X', defined at:  File "sample.py", line 2, in <module>    X = tf.placeholder(tf.float32, name="X")  ...关于可能的替代方案有什么想法吗？

Answer 1

你只需要稍微修改一下代码。的值不tf.Variable应该是tf.placeholder，否则运行时会导致你的初始化错误sess.run(tf.global_variables_initializer())。你可以用tf.stack它来代替。另外，请记住在运行时馈送数据sess.run(Y)。

import tensorflow as tf

X = tf.placeholder(tf.float32, name="X")

W = tf.Variable([1,2,1], dtype=tf.float32, name="weights")

W = tf.reshape(W,[1,3])

F = tf.stack([X*X,X,1.0])

F = tf.reshape(F,[3,1])

Y = tf.matmul(W,F)

with tf.Session() as sess:

    sess.run(tf.global_variables_initializer())

    for i in range(10):

        Y_val = sess.run(Y, feed_dict={X: i})

        print("Y:",Y_val)

Y: [[1.]]

Y: [[4.]]

Y: [[9.]]

Y: [[16.]]

Y: [[25.]]

Y: [[36.]]

Y: [[49.]]

Y: [[64.]]

Y: [[81.]]

Y: [[100.]]

Answer 2

我认为即使您仍然可以初始化一个依赖于这样的占位符的变量，W除非您添加更多代码来仅初始化未初始化的变量，否则将重复初始化。那是更多的努力。

希望我没有错过这种方法的其他低效率。

import tensorflow as tf

sess = tf.InteractiveSession()

X = tf.placeholder(tf.float32, name="X")

W = tf.Variable([1, 2, 1], dtype=tf.float32, name="weights")

W = tf.reshape(W, [1, 3])

var = tf.reshape([X*X,X,1],[3,1])

F = tf.get_variable('F', dtype=tf.float32, initializer=var)

init = tf.global_variables_initializer()

Y=tf.matmul(W,F)

for i in range(10):

    sess.run([init], feed_dict={X: i})

    print(sess.run(Y))

[[1.]]

[[4.]]

[[9.]]

[[16.]]

[[25.]]

[[36.]]

[[49.]]

[[64.]]

[[81.]]

[[100.]]