placeholder 和 计算

import tensorflow as tf
import numpy as np

# 设计一个3维数组
x = tf.placeholder('float', [None,2,2])

# 加法器
y = tf.add(x,x)



#随机产生一个2*2 数组
rand_array2=np.random.rand(2,2)

# 编程3维

rarray = [rand_array1]

with tf.Session() as sess:
	sess.run(y,feed_dict={x:rarray})

For example:

  
  

   
   

   
   

  
  
x = tf.placeholder(tf.float32, shape=(1024, 1024))
y = tf.matmul(x, x)

with tf.Session() as sess:
  print(sess.run(y))  # ERROR: will fail because x was not fed.

  rand_array = np.random.rand(1024, 1024)
  print(sess.run(y, feed_dict={x: rand_array}))  # Will succeed.

x = [[1,2,3], [4,5,6]]
t1= tf.transpose(x)
t2 = tf.transpose(x, perm=[1, 0]) 

x = [[[1 , 2,  3],
	  [4 , 5, 6]],
	  [[7,8,9],
	  [10,11,12]]]

t3= tf.transpose(x, perm=[0, 2, 1])
sess.run(t1)
sess.run(t2)
sess.run(t3)

>>> sess.run(t1)
array([[1, 4],
       [2, 5],
       [3, 6]], dtype=int32)
>>> sess.run(t2)
array([[1, 4],
       [2, 5],
       [3, 6]], dtype=int32)
>>> sess.run(t3)
array([[[ 1,  4],
        [ 2,  5],
        [ 3,  6]],


       [[ 7, 10],
        [ 8, 11],

        [ 9, 12]]], dtype=int32)

import tensorflow as tf
import numpy as np

x = tf.placeholder('float', [None,2,2])

y = tf.add(x,x)




rand_array2=np.random.rand(2,2)
rarray = [rand_array1]
with tf.Session() as sess:
	sess.run(y,feed_dict={x:rarray})


x = [[1,2,3], [4,5,6]]
t1= tf.transpose(x)
t2 = tf.transpose(x, perm=[1, 0]) 

x = [[[1 , 2,  3],
	  [4 , 5, 6]],
	  [[7,8,9],
	  [10,11,12]]]

t3= tf.transpose(x, perm=[0, 2, 1])
sess.run(t1)
sess.run(t2)
sess.run(t3)



a = tf.placeholder(tf.float32)
b = tf.placeholder(tf.float32)
adder_node = a + b
y = tf.placeholder(tf.float32)
squared_deltas = tf.square(linear_model - y)
loss = tf.reduce_sum(squared_deltas)
print(sess.run(loss, {x:[1,2,3,4], y:[0,-1,-2,-3]}))

print(sess.run(adder_node,{a:3,b:4.5}))7.5print(sess.run(adder_node,{a:[1,3],b:[2,4]}))[ 3. 7.]W = tf.Variable([.3], tf.float32)b = tf.Variable([-.3], tf.float32)x = tf.placeholder(tf.float32)linear_model = W * x + binit = tf.global_variables_initializer()sess.run(init)print(sess.run(linear_model,
 {x:[1,2,3,4]}))