Python mnist.evaluation方法代碼示例

本文整理匯總了Python中tensorflow.examples.tutorials.mnist.mnist.evaluation方法的典型用法代碼示例。如果您正苦於以下問題：Python mnist.evaluation方法的具體用法？Python mnist.evaluation怎麽用？Python mnist.evaluation使用的例子？那麽, 這裏精選的方法代碼示例或許可以為您提供幫助。您也可以進一步了解該方法所在類tensorflow.examples.tutorials.mnist.mnist的用法示例。

在下文中一共展示了mnist.evaluation方法的7個代碼示例，這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚，您的評價將有助於係統推薦出更棒的Python代碼示例。

示例1: do_eval

# 需要導入模塊: from tensorflow.examples.tutorials.mnist import mnist [as 別名]
# 或者: from tensorflow.examples.tutorials.mnist.mnist import evaluation [as 別名]
def do_eval(sess,
            eval_correct,
            images_placeholder,
            labels_placeholder,
            data_set):
  """Runs one evaluation against the full epoch of data.

  Args:
    sess: The session in which the model has been trained.
    eval_correct: The Tensor that returns the number of correct predictions.
    images_placeholder: The images placeholder.
    labels_placeholder: The labels placeholder.
    data_set: The set of images and labels to evaluate, from
      input_data.read_data_sets().
  """
  # And run one epoch of eval.
  true_count = 0  # Counts the number of correct predictions.
  steps_per_epoch = data_set.num_examples // FLAGS.batch_size
  num_examples = steps_per_epoch * FLAGS.batch_size
  for step in xrange(steps_per_epoch):
    feed_dict = fill_feed_dict(data_set, images_placeholder, labels_placeholder)
    true_count += sess.run(eval_correct, feed_dict=feed_dict)
  precision = true_count / num_examples
  print('  Num examples: %d  Num correct: %d  Precision @ 1: %0.04f' %
        (num_examples, true_count, precision))

開發者ID:GoogleCloudPlatform，項目名稱:cloudml-samples，代碼行數:27，代碼來源:task.py

示例2: do_eval

# 需要導入模塊: from tensorflow.examples.tutorials.mnist import mnist [as 別名]
# 或者: from tensorflow.examples.tutorials.mnist.mnist import evaluation [as 別名]
def do_eval(sess,
            eval_correct,
            images_placeholder,
            labels_placeholder,
            data_set):
  """Runs one evaluation against the full epoch of data.

  Args:
    sess: The session in which the model has been trained.
    eval_correct: The Tensor that returns the number of correct predictions.
    images_placeholder: The images placeholder.
    labels_placeholder: The labels placeholder.
    data_set: The set of images and labels to evaluate, from
      input_data.read_data_sets().
  """
  # And run one epoch of eval.
  true_count = 0  # Counts the number of correct predictions.
  steps_per_epoch = data_set.num_examples // FLAGS.batch_size
  num_examples = steps_per_epoch * FLAGS.batch_size
  for step in xrange(steps_per_epoch):
    feed_dict = fill_feed_dict(data_set,
                               images_placeholder,
                               labels_placeholder)
    true_count += sess.run(eval_correct, feed_dict=feed_dict)
  precision = true_count / num_examples
  print('  Num examples: %d  Num correct: %d  Precision @ 1: %0.04f' %
        (num_examples, true_count, precision))

開發者ID:GoogleCloudPlatform，項目名稱:cloudml-samples，代碼行數:29，代碼來源:task.py

示例3: do_eval

# 需要導入模塊: from tensorflow.examples.tutorials.mnist import mnist [as 別名]
# 或者: from tensorflow.examples.tutorials.mnist.mnist import evaluation [as 別名]
def do_eval(sess,
            eval_correct,
            images_placeholder,
            labels_placeholder,
            data_set):
  """Runs one evaluation against the full epoch of data.

  Args:
    sess: The session in which the model has been trained.
    eval_correct: The Tensor that returns the number of correct predictions.
    images_placeholder: The images placeholder.
    labels_placeholder: The labels placeholder.
    data_set: The set of images and labels to evaluate, from
      input_data.read_data_sets().
  """
  # And run one epoch of eval.
  true_count = 0  # Counts the number of correct predictions.
  steps_per_epoch = data_set.num_examples // FLAGS.batch_size
  num_examples = steps_per_epoch * FLAGS.batch_size
  for step in xrange(steps_per_epoch):
    feed_dict = fill_feed_dict(data_set,
                               images_placeholder,
                               labels_placeholder)
    true_count += sess.run(eval_correct, feed_dict=feed_dict)
  precision = float(true_count) / num_examples
  sess.run(precision)
  print('  Num examples: %d  Num correct: %d  Precision @ 1: %0.04f' %
        (num_examples, true_count, precision))

開發者ID:jowettcz，項目名稱:deep_learning_study，代碼行數:30，代碼來源:fully_connected_feed.py

示例4: do_eval

# 需要導入模塊: from tensorflow.examples.tutorials.mnist import mnist [as 別名]
# 或者: from tensorflow.examples.tutorials.mnist.mnist import evaluation [as 別名]
def do_eval(sess,
            eval_correct,
            images_placeholder,
            labels_placeholder,
            data_set):
    """Runs one evaluation against the full epoch of data.
    Args:
        sess: The session in which the model has been trained.
        eval_correct: The Tensor that returns the number of correct predictions.
        images_placeholder: The images placeholder.
        labels_placeholder: The labels placeholder.
        data_set: The set of images and labels to evaluate, from
            input_data.read_data_sets().
    """
    # And run one epoch of eval.
    true_count = 0  # Counts the number of correct predictions.
    steps_per_epoch = data_set.num_examples // FLAGS.batch_size
    num_examples = steps_per_epoch * FLAGS.batch_size
    for step in xrange(steps_per_epoch):
        feed_dict = fill_feed_dict(data_set,
                                   images_placeholder,
                                   labels_placeholder)
        true_count += sess.run(eval_correct, feed_dict=feed_dict)
    precision = true_count / num_examples
    print('  Num examples: %d  Num correct: %d  Precision @ 1: %0.04f' %
            (num_examples, true_count, precision))

開發者ID:gradientzoo，項目名稱:python-gradientzoo，代碼行數:28，代碼來源:tensorflow_mnist.py

示例5: do_eval

# 需要導入模塊: from tensorflow.examples.tutorials.mnist import mnist [as 別名]
# 或者: from tensorflow.examples.tutorials.mnist.mnist import evaluation [as 別名]
def do_eval(sess,
            eval_correct,
            images_placeholder,
            labels_placeholder,
            data_set):
  """Runs one evaluation against the full epoch of data.

  Args:
    sess: The session in which the model has been trained.
    eval_correct: The Tensor that returns the number of correct predictions.
    images_placeholder: The images placeholder.
    labels_placeholder: The labels placeholder.
    data_set: The set of images and labels to evaluate, from
      input_data.read_data_sets().
  """
  # And run one epoch of eval.
  true_count = 0  # Counts the number of correct predictions.
  steps_per_epoch = data_set.num_examples // FLAGS.batch_size
  num_examples = steps_per_epoch * FLAGS.batch_size
  for step in xrange(steps_per_epoch):
    feed_dict = fill_feed_dict(data_set,
                               images_placeholder,
                               labels_placeholder)
    true_count += sess.run(eval_correct, feed_dict=feed_dict)
  precision = float(true_count) / num_examples
  print('  Num examples: %d  Num correct: %d  Precision @ 1: %0.04f' %
        (num_examples, true_count, precision))

開發者ID:DiamonJoy，項目名稱:TensorFlow，代碼行數:29，代碼來源:fully_connected_feed.py

示例6: do_eval

# 需要導入模塊: from tensorflow.examples.tutorials.mnist import mnist [as 別名]
# 或者: from tensorflow.examples.tutorials.mnist.mnist import evaluation [as 別名]
def do_eval(sess, eval_correct, images_placeholder, labels_placeholder, data_set):
	'''
		Run one evaluation against full epoch of data
	'''
	#Number of Correct Predictions
	true_count = 0
	steps_per_epoch = data_set.num_examples // FLAGS.batch_size
	num_examples = steps_per_epoch * FLAGS.batch_size
	
	for step in xrange(steps_per_epoch):
		feed_dict = fill_feed_dict(data_set, images_placeholder, labels_placeholder)
		true_count += sess.run(eval_correct, feed_dict = feed_dict)

	precision = float(true_count) / num_examples
	print(' Number of Examples : %d, Number of Correct : %d, Precision @ 1 : %0.04f'%(num_examples, true_count, precision))

開發者ID:Ram81，項目名稱:Tensorflow_Practice，代碼行數:17，代碼來源:fully_connected_mnist.py

示例7: do_eval

# 需要導入模塊: from tensorflow.examples.tutorials.mnist import mnist [as 別名]
# 或者: from tensorflow.examples.tutorials.mnist.mnist import evaluation [as 別名]
def do_eval(sess,
            eval_correct,
            images_placeholder,
            labels_placeholder,
            data_set):
  """Runs one evaluation against the full epoch of data.

  Args:
    sess: The session in which the model has been trained.
    eval_correct: The Tensor that returns the number of correct predictions.
    images_placeholder: The images placeholder.
    labels_placeholder: The labels placeholder.
    data_set: The set of images and labels to evaluate, from
      input_data.read_data_sets().
  Returns:
    Precision value on the dataset.
  """
  # And run one epoch of eval.
  true_count = 0  # Counts the number of correct predictions.
  steps_per_epoch = data_set.num_examples // FLAGS.batch_size
  num_examples = steps_per_epoch * FLAGS.batch_size
  for step in xrange(steps_per_epoch):
    feed_dict = fill_feed_dict(data_set,
                               images_placeholder,
                               labels_placeholder,
                               FLAGS.batch_size)
    true_count += sess.run(eval_correct, feed_dict=feed_dict)
  precision = true_count / num_examples
  print('  Num examples: %d  Num correct: %d  Precision @ 1: %0.04f' %
        (num_examples, true_count, precision))
  return precision

開發者ID:rashmitripathi，項目名稱:DeepLearning_VirtualReality_BigData_Project，代碼行數:33，代碼來源:mnist.py

注：本文中的tensorflow.examples.tutorials.mnist.mnist.evaluation方法示例由純淨天空整理自Github/MSDocs等開源代碼及文檔管理平台，相關代碼片段篩選自各路編程大神貢獻的開源項目，源碼版權歸原作者所有，傳播和使用請參考對應項目的License；未經允許，請勿轉載。