TensorFlow修改變量值后，需要重新賦值，assign用起來(lái)有點(diǎn)小技巧，就是需要需要弄個(gè)操作子，運(yùn)行一下。

下面這么用是不行的

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())

正確用法

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 #這是Python的一種開(kāi)源的數(shù)值計(jì)算擴(kuò)展，非常強(qiáng)大import tensorflow as tf #導(dǎo)入tensorflow ##構(gòu)造數(shù)據(jù)##x_data=np.random.rand(100).astype(np.float32) #隨機(jī)生成100個(gè)類型為float32的值y_data=x_data*0.1+0.3 #定義方程式y(tǒng)=x_data*A+B##-------####建立TensorFlow神經(jīng)計(jì)算結(jié)構(gòu)##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)) #判斷與正確值的差距optimizer=tf.train.GradientDescentOptimizer(0.5) #根據(jù)差距進(jìn)行反向傳播修正參數(shù)train=optimizer.minimize(loss) #建立訓(xùn)練器init=tf.global_variables_initializer() #初始化TensorFlow訓(xùn)練結(jié)構(gòu)#sess=tf.Session() #建立TensorFlow訓(xùn)練會(huì)話sess = tf.InteractiveSession() sess.run(init)  #將訓(xùn)練結(jié)構(gòu)裝載到會(huì)話中print('weight',weight.eval())for step in range(400): #循環(huán)訓(xùn)練400次  sess.run(train) #使用訓(xùn)練器根據(jù)訓(xùn)練結(jié)構(gòu)進(jìn)行訓(xùn)練  if step%20==0: #每20次打印一次訓(xùn)練結(jié)果  print(step,sess.run(weight),sess.run(biases)) #訓(xùn)練次數(shù)，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())

以上這篇對(duì)TensorFlow的assign賦值用法詳解就是小編分享給大家的全部?jī)?nèi)容了，希望能給大家一個(gè)參考，也希望大家多多支持武林站長(zhǎng)站。