2回答

• 

  Noah_________

  2018-06-29 16:09:52

  import os
  import model
  import tensorflow as tf
  import input_data
  
  data = input_data.read_data_sets('MNIST_data', one_hot=True)
  
  # model
  with tf.variable_scope("convolutional"):
      x = tf.placeholder(tf.float32, [None, 784], name='x')
      keep_prob = tf.placeholder(tf.float32)
      y, variables = model.convolutional(x, keep_prob)
  
  # train
  y_ = tf.placeholder(tf.float32, [None, 10], name='y')
  cross_entropy = -tf.reduce_sum(y_ * tf.log(y))
  train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
  correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
  accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
  
  saver = tf.train.Saver(variables)
  
  with tf.Session() as sess:
      merged_summary_op = tf.summary.merge_all()
      summary_writer = tf.summary.FileWriter('/tmp/mnist_log/1', sess.graph)
      summary_writer.add_graph(sess.graph)
      sess.run(tf.global_variables_initializer())
  
      for i in range(20000):
          batch = data.train.next_batch(50)
          if i % 100 == 0:
              train_accuracy = accuracy.eval(feed_dict={x: batch[0], y_: batch[1]})
              print("Step %d, training accuracy %g" % (i, train_accuracy))
          sess.run(train_step, feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
  
      print(sess.run(accuracy, feed_dict={x: data.test.images, y_: data.test.labels, keep_prob: 1.0}))
  
      path = saver.save(
          sess, os.path.join(os.path.dirname(__file__), 'data_convolutional', 'convolutional.ckpt'),
          write_meta_graph=False, write_state=False)
  
      print("Saved: ", path)

  
  

  0 0
• 

  minip

  2018-06-23 17:20:32

  show me the code

  2 0

  Noah__...

  找到问题根源了，少写了一个参数（o(╯□╰)o）

  2018-06-29 16:33:00

  共 2 条回复 >