python學習day-14 改錯+dropout解決overfiting

 

 

1. tensorflow.initialize_all_variables已改成tensorflow.global_variables_initializer()

2. AttributeError: module ‘tensorflow.python.training.training’ has no attribute ‘SummaryWriter’

   tf.train.SummaryWriter已廢除 
   使用 tf.train.summary.FileWriter

3. AttributeError: module ‘tensorflow’ has no attribute ‘sub’

   減法 tf.sub() 已改成tf.subtract()

4. 參考：http://blog.csdn.NET/edwards_june/article/details/65652385

    

5. 前4個是 V0.11 的API 用在 V1.0 的錯誤

   5.1. AttributeError: 'module' object has no attribute 'merge_all_summaries'

   >> tf.merge_all_summaries() 改成：summary_op = tf.summary.merge_all()

   
   

    

   5.2. AttributeError: 'module' object has no attribute 'SummaryWriter'

   >> tf.train.SummaryWriter 改成：tf.summary.FileWriter

   
   

    

   5.3. AttributeError: 'module' object has no attribute 'scalar_summary'

   >> tf.scalar_summary 改成：tf.summary.scalar

    

   5.4. AttributeError: 'module' object has no attribute 'histogram_summary'

   >> histogram_summary 改成：tf.summary.histogram
    
   下邊這個是 V1.0 的API 用在 V0.11 的錯誤
   File "dis-alexnet_benchmark.py", line 110, in alexnet_v2
       biases_initializer=tf.zeros_initializer(),
   TypeError: zeros_initializer() takes at least 1 argument (0 given)
   >> 將 biases_initializer=tf.zeros_initializer() 改成：biases_initializer=tf.zeros_initialize 

6. 程序 
   
   """
   Please note, this code is only for python 3+. If you are using python 2+, please modify the code accordingly.
   """
   import tensorflow as tf
   from tensorflow.examples.tutorials.mnist import input_data
   # number 1 to 10 data
   mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
   
   
   # from tensorflow.examples.tutorials.mnist import input_data
   # mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
   def add_layer(inputs, in_size, out_size, activation_function=None,):
       # add one more layer and return the output of this layer
       Weights = tf.Variable(tf.random_normal([in_size, out_size]))
       biases = tf.Variable(tf.zeros([1, out_size]) + 0.1,)
       Wx_plus_b = tf.matmul(inputs, Weights) + biases
       if activation_function is None:
           outputs = Wx_plus_b
       else:
           outputs = activation_function(Wx_plus_b,)
       return outputs
   
   def compute_accuracy(v_xs, v_ys):
       global prediction
       y_pre = sess.run(prediction, feed_dict={xs: v_xs})
       correct_prediction = tf.equal(tf.argmax(y_pre,1), tf.argmax(v_ys,1))
       accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
       result = sess.run(accuracy, feed_dict={xs: v_xs, ys: v_ys})
       return result
   
   # define placeholder for inputs to network
   xs = tf.placeholder(tf.float32, [None, 784]) # 28x28
   ys = tf.placeholder(tf.float32, [None, 10])
   
   # add output layer
   prediction = add_layer(xs, 784, 10,  activation_function=tf.nn.softmax)
   
   # the error between prediction and real data
   cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction),
                                                 reduction_indices=[1]))       # loss
   train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
   
   sess = tf.Session()
   # important step
   tf.global_variables_initializer()
   
   for i in range(1000):
       batch_xs, batch_ys = mnist.train.next_batch(100)
       sess.run(train_step, feed_dict={xs: batch_xs, ys: batch_ys})
       if i % 50 == 0:
           print(compute_accuracy(
               mnist.test.images, mnist.test.labels))