import tensorflow as tfimport numpy as np x = tf.Variable(0)init = tf.initialize_all_variables()sess = tf.InteractiveSession()sess.run(init) print(x.eval()) x.assign(1)print(x.eval())
正确用法
1.
import tensorflow as tfx = tf.Variable(0)y = tf.assign(x, 1)with tf.Session() as sess: sess.run(tf.global_variables_initializer()) print sess.run(x) print sess.run(y) print sess.run(x)
2.
In [212]: w = tf.Variable(12)In [213]: w_new = w.assign(34) In [214]: with tf.Session() as sess: ...: sess.run(w_new) ...: print(w_new.eval()) # output34
3.
import tensorflow as tfx = tf.Variable(0)sess = tf.Session()sess.run(tf.global_variables_initializer())print(sess.run(x)) # Prints 0.x.load(1, sess)print(sess.run(x)) # Prints 1.
我的方法
import numpy as np #这是Python的一种开源的数值计算扩展，非常强大import tensorflow as tf #导入tensorflow ##构造数据##x_data=np.random.rand(100).astype(np.float32) #随机生成100个类型为float32的值y_data=x_data*0.1+0.3 #定义方程式y=x_data*A+B##-------####建立TensorFlow神经计算结构##weight=tf.Variable(tf.random_uniform([1],-1.0,1.0)) biases=tf.Variable(tf.zeros([1])) y=weight*x_data+biasesw1=weight*2loss=tf.reduce_mean(tf.square(y-y_data)) #判断与正确值的差距optimizer=tf.train.GradientDescentOptimizer(0.5) #根据差距进行反向传播修正参数train=optimizer.minimize(loss) #建立训练器init=tf.global_variables_initializer() #初始化TensorFlow训练结构#sess=tf.Session() #建立TensorFlow训练会话sess = tf.InteractiveSession() sess.run(init) #将训练结构装载到会话中print('weight',weight.eval())for step in range(400): #循环训练400次 sess.run(train) #使用训练器根据训练结构进行训练 if step%20==0: #每20次打印一次训练结果 print(step,sess.run(weight),sess.run(biases)) #训练次数，A值，B值 print(sess.run(loss)) print('weight new',weight.eval())#wop=weight.assign([3])#wop.eval()weight.load([1],sess)print('w1',w1.eval())
