Tensorflow-Fehler: Keine Variablen zur Optimierung

Question

Ich versuche, ein neuronales Netzwerk in Tensorflow zu implementieren. Ich verwende tf.train.GradientDescentOptimizer, um die Entropie zu minimieren. Doch es zeigt mir den Fehler ValueError: No variables to optimize

Unten ist der Code

import tensorflow as tf 
from tensorflow.examples.tutorials.mnist import input_data 
mnist = input_data.read_data_sets("MNIST_data/", one_hot = True) 

x = tf.placeholder(tf.float32,[None,748]) 
w = tf.zeros([748,10]) 
b = tf.zeros([10]) 
y = tf.matmul(x,w) + b 
y_ = tf.placeholder(tf.float32,[None,10]) 
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels = y_, logits = y)) 
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy) 

sess = tf.InteractiveSessoin() 
tf.global_variables_initializer().run() 

for i in range(1000): 
    batch_xs, batch_ys = mnist.train.next_batch(100) 
    sess.run(train_step, feed_dict = {x:batch_xs, y_:batch_ys}) 

Ich erhalte den Fehler so etwas wie dieses

Traceback (most recent call last): 
    File "NeuralNetwork.py", line 15, in <module> 
    train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy) 
    File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/training/optimizer.py", line 193, in minimize 
    grad_loss=grad_loss) 
    File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/training/optimizer.py", line 244, in compute_gradients 
    raise ValueError("No variables to optimize") 
ValueError: No variables to optimize 

Answer 1

Sie nicht‘haben alle Variablen in der grafischen Darstellung optimiert werden.

w = tf.zeros([748,10]) 
b = tf.zeros([10]) 

sollte

w = tf.Variable(tf.zeros([748,10])) 
b = tf.Variable(tf.zeros([10]))