import tensorflow as tf #引入模块
tf.compat.v1.disable_eager_execution()
x = tf.constant([[1.0, 2.0]]) #定义一个 2 阶张量等于[[1.0,2.0]]
w = tf.constant([[3.0], [4.0]]) #定义一个 2 阶张量等于[[3.0],[4.0]]
y = tf.matmul(x, w) #实现 xw 矩阵乘法
print (y) #打印出结果
# 初始化所有变量，也就是上面定义的a/b两个变量
#tf.compat.v1.Session() as session
with tf.compat.v1.Session() as sess:
print (sess.run(y))
结果输出：
Tensor(“MatMul_1:0”, shape=(1, 1), dtype=float32)
[[11.]]
效果如图：
另外的，
找不到原始地方是哪里了，无脑复制粘贴，跑了再说。
常用案例：
import tensorflow as tf
import numpy as np
import tensorflow.compat.v1 as tf
tf.disable_v2_behavior()
houses = 100
features = 2
x_data = np.zeros([houses, 2])
for house in range(houses):
x_data[house, 0] = np.round(np.random.uniform(50., 150.))
x_data[house, 1] = np.round(np.random.uniform(3., 7.))
weights = np.array([[2.], [3.]])
y_data = np.dot(x_data, weights) # 点积
x_data_ = tf.placeholder(tf.float32, [None, 2])
y_data_ = tf.placeholder(tf.float32, [None, 1])
weights_ = tf.Variable(np.ones([2, 1]), dtype=tf.float32)
y_model = tf.matmul(x_data_, weights_)
loss = tf.reduce_mean(tf.pow((y_model - y_data_), 2))
train_op = tf.train.AdamOptimizer(0.01).minimize(loss)
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
sess = tf.Session(config=config)
# sess = tf.Session()
init = tf.global_variables_initializer()
sess.run(init)
for _ in range(100):
for (x, y) in zip(x_data, y_data):
z1 = x.reshape(1, 2)
z2 = y.reshape(1, 1)
sess.run(train_op, feed_dict={
x_data_: z1, y_data_: z2})
print("--------------")
print(sess.run(weights_))
结果输出如下：
[[1.7226804]
[1.7358012]]
--------------
[[1.995762 ]
[2.0266747]]
--------------
[[2.0405617]
[2.0848765]]
--------------
[[2.0428774]
[2.101384 ]]
--------------
[[2.042211 ]
[2.1168568]]
--------------
[[2.0414085]
[2.1340635]]
--------------
[[2.0405357]
[2.1529143]]
--------------
[[2.0395954]
[2.1732705]]
--------------
[[2.0385902]
[2.1950126]]
--------------
[[2.0375223]
[2.2180226]]
--------------
[[2.0363958]
[2.2421906]]
--------------
[[2.0352123]
[2.267404 ]]
--------------
[[2.0339756]
[2.2935524]]
--------------
[[2.0326884]
[2.3205247]]
--------------
[[2.0313563]
[2.3482075]]
--------------
[[2.029984]
[2.376487]]
--------------
[[2.0285776]
[2.4052484]]
--------------
[[2.0271437]
[2.4343727]]
--------------
[[2.02569 ]
[2.4637434]]
--------------
[[2.0242243]
[2.4932399]]
--------------
[[2.0227544]
[2.5227406]]
--------------
[[2.021289 ]
[2.5521228]]
--------------
[[2.0198367]
[2.5812676]]
--------------
[[2.0184047]
[2.6100483]]
--------------
[[2.0170014]
[2.638347 ]]
--------------
[[2.0156336]
[2.6660457]]
--------------
[[2.0143073]
[2.693029 ]]
--------------
[[2.0130286]
[2.7191868]]
--------------
[[2.0118036]
[2.7444136]]
--------------
[[2.0106356]
[2.768612 ]]
--------------
[[2.009528]
[2.791693]]
--------------
[[2.0084841]
[2.813578 ]]
--------------
[[2.0075054]
[2.8342025]]
--------------
[[2.0065937]
[2.8535097]]
--------------
[[2.00575 ]
[2.8714588]]
--------------
[[2.0049756]
[2.8880222]]
--------------
[[2.00427 ]
[2.9031928]]
--------------
[[2.0036345]
[2.916972 ]]
--------------
[[2.003067 ]
[2.9293804]]
--------------
[[2.0025673]
[2.9404554]]
--------------
[[2.0021315]
[2.9502413]]
--------------
[[2.0017574]
[2.9588048]]
--------------
[[2.001439 ]
[2.9662185]]
--------------
[[2.0011725]
[2.9725668]]
--------------
[[2.0009499]
[2.9779415]]
--------------
[[2.0007663]
[2.9824414]]
--------------
[[2.0006146]
[2.986167 ]]
--------------
[[2.0004895]
[2.9892175]]
--------------
[[2.000386 ]
[2.9916866]]
--------------
[[2.0003006]
[2.9936678]]
--------------
[[2.0002317]
[2.9952383]]
--------------
[[2.0001752]
[2.996469 ]]
--------------
[[2.0001302]
[2.9974225]]
--------------
[[2.0000956]
[2.998151 ]]
--------------
[[2.0000684]
[2.9986963]]
--------------
[[2.0000484]
[2.9991 ]]
--------------
[[2.0000334]
[2.99939 ]]
--------------
[[2.0000224]
[2.9995956]]
--------------
[[2.0000145]
[2.9997373]]
--------------
[[2.0000093]
[2.9998343]]
--------------
[[2.0000057]
[2.9998984]]
--------------
[[2.000003 ]
[2.9999387]]
--------------
[[2.0000017]
[2.999962 ]]
--------------
[[2.000001 ]
[2.9999797]]
--------------
[[2.0000005]
[2.9999895]]
--------------
[[2.0000002]
[2.9999952]]
--------------
[[2.0000002]
[2.9999952]]
--------------
[[2.0000002]
[2.9999952]]
--------------
[[2.0000002]
[2.9999952]]
--------------
[[2.0000002]
[2.9999952]]
--------------
[[2.0000002]
[2.9999952]]
--------------
[[2.0000002]
[2.9999955]]
--------------
[[2.0000002]
[2.9999955]]
--------------
[[2.0000002]
[2.9999955]]
--------------
[[2.0000002]
[2.9999955]]
--------------
[[2.0000002]
[2.9999955]]
--------------
[[2.0000002]
[2.9999955]]
--------------
[[2.0000002]
[2.9999955]]
--------------
[[2.0000002]
[2.9999955]]
--------------
[[2.0000002]
[2.9999955]]
--------------
[[2.0000002]
[2.9999955]]
--------------
[[2.0000002]
[2.999996 ]]
--------------
[[2.0000002]
[2.9999983]]
--------------
[[2. ]
[2.9999995]]
--------------
[[2. ]
[2.9999995]]
--------------
[[2. ]
[2.9999995]]
--------------
[[2. ]
[2.9999995]]
--------------
[[2. ]
[2.9999995]]
--------------
[[2. ]
[2.9999995]]
--------------
[[2. ]
[2.9999995]]
--------------
[[2. ]
[2.9999995]]
--------------
[[2. ]
[2.9999995]]
--------------
[[2. ]
[2.9999995]]
--------------
[[2. ]
[2.9999995]]
--------------
[[2. ]
[2.9999995]]
--------------
[[2. ]
[2.9999995]]
--------------
[[2. ]
[2.9999995]]
--------------
[[2. ]
[2.9999995]]
--------------
[[2. ]
[2.9999995]]
--------------
[[2. ]
[2.9999995]]
部分参考
出现问题：
AttributeError: module ‘tensorflow’ has no attribute ‘Session’
原因：
tensorflow2删除了 tf.Session()
解决方法：
tf.Session() 将改为tf.compat.v1.Session()
————————————————
版权声明：本文为CSDN博主「李亮_sdu」的原创文章，遵循CC 4.0 BY-SA版权协议，转载请附上原文出处链接及本声明。
原文链接：https://blog.csdn.net/qq_40575024/article/details/105862550
tensorFlow训练网络过程中出现NAN值：
在用多元线性回归解决房价预测问题时就遇到过权重出现NAN值问题。先采用的是tf.train.GradientDescentOptimize优化算法，结果训练过程中权重出现了NAN值，后来改用tf.train.AdamOptimize优化算法问题得到了解决。至于为什么还有待深究！
案例分析：如后面的图。
————————————————
版权声明：本文为CSDN博主「The_Thinker_QChen」的原创文章，遵循CC 4.0 BY-SA版权协议，转载请附上原文出处链接及本声明。
原文链接：https://blog.csdn.net/qq_33254870/article/details/81428441
转载：https://blog.csdn.net/dongbao520/article/details/117479851
查看评论