Python cifar10.loss方法代码示例

# 需要导入模块: import cifar10 [as 别名]
# 或者: from cifar10 import loss [as 别名]
def tower_loss(scope, images, labels):
  """Calculate the total loss on a single tower running the CIFAR model.

  Args:
    scope: unique prefix string identifying the CIFAR tower, e.g. 'tower_0'
    images: Images. 4D tensor of shape [batch_size, height, width, 3].
    labels: Labels. 1D tensor of shape [batch_size].

  Returns:
     Tensor of shape [] containing the total loss for a batch of data
  """

  # Build inference Graph.
  logits = cifar10.inference(images)

  # Build the portion of the Graph calculating the losses. Note that we will
  # assemble the total_loss using a custom function below.
  _ = cifar10.loss(logits, labels)

  # Assemble all of the losses for the current tower only.
  losses = tf.get_collection('losses', scope)

  # Calculate the total loss for the current tower.
  total_loss = tf.add_n(losses, name='total_loss')

  # Attach a scalar summary to all individual losses and the total loss; do the
  # same for the averaged version of the losses.
  for l in losses + [total_loss]:
    # Remove 'tower_[0-9]/' from the name in case this is a multi-GPU training
    # session. This helps the clarity of presentation on tensorboard.
    loss_name = re.sub('%s_[0-9]*/' % cifar10.TOWER_NAME, '', l.op.name)
    tf.summary.scalar(loss_name, l)

  return total_loss 

# 需要导入模块: import cifar10 [as 别名]
# 或者: from cifar10 import loss [as 别名]
def tower_loss(scope):
  """Calculate the total loss on a single tower running the CIFAR model.

  Args:
    scope: unique prefix string identifying the CIFAR tower, e.g. 'tower_0'

  Returns:
     Tensor of shape [] containing the total loss for a batch of data
  """
  # Get images and labels for CIFAR-10.
  images, labels = cifar10.distorted_inputs()

  # Build inference Graph.
  logits = cifar10.inference(images)

  # Build the portion of the Graph calculating the losses. Note that we will
  # assemble the total_loss using a custom function below.
  _ = cifar10.loss(logits, labels)

  # Assemble all of the losses for the current tower only.
  losses = tf.get_collection('losses', scope)

  # Calculate the total loss for the current tower.
  total_loss = tf.add_n(losses, name='total_loss')

  # Attach a scalar summary to all individual losses and the total loss; do the
  # same for the averaged version of the losses.
  for l in losses + [total_loss]:
    # Remove 'tower_[0-9]/' from the name in case this is a multi-GPU training
    # session. This helps the clarity of presentation on tensorboard.
    loss_name = re.sub('%s_[0-9]*/' % cifar10.TOWER_NAME, '', l.op.name)
    tf.summary.scalar(loss_name, l)

  return total_loss 

# 需要导入模块: import cifar10 [as 别名]
# 或者: from cifar10 import loss [as 别名]
def train():
  """Train CIFAR-10 for a number of steps."""
  with tf.Graph().as_default():
    global_step = tf.contrib.framework.get_or_create_global_step()

    # Get images and labels for CIFAR-10.
    # Force input pipeline to CPU:0 to avoid operations sometimes ending up on
    # GPU and resulting in a slow down.
    with tf.device('/cpu:0'):
      images, labels = cifar10.distorted_inputs()

    # Build a Graph that computes the logits predictions from the
    # inference model.
    logits = cifar10.inference(images)

    # Calculate loss.
    loss = cifar10.loss(logits, labels)

    # Build a Graph that trains the model with one batch of examples and
    # updates the model parameters.
    train_op = cifar10.train(loss, global_step)

    class _LoggerHook(tf.train.SessionRunHook):
      """Logs loss and runtime."""

      def begin(self):
        self._step = -1
        self._start_time = time.time()

      def before_run(self, run_context):
        self._step += 1
        return tf.train.SessionRunArgs(loss)  # Asks for loss value.

      def after_run(self, run_context, run_values):
        if self._step % FLAGS.log_frequency == 0:
          current_time = time.time()
          duration = current_time - self._start_time
          self._start_time = current_time

          loss_value = run_values.results
          examples_per_sec = FLAGS.log_frequency * FLAGS.batch_size / duration
          sec_per_batch = float(duration / FLAGS.log_frequency)

          format_str = ('%s: step %d, loss = %.2f (%.1f examples/sec; %.3f '
                        'sec/batch)')
          print (format_str % (datetime.now(), self._step, loss_value,
                               examples_per_sec, sec_per_batch))

    with tf.train.MonitoredTrainingSession(
        checkpoint_dir=FLAGS.train_dir,
        hooks=[tf.train.StopAtStepHook(last_step=FLAGS.max_steps),
               tf.train.NanTensorHook(loss),
               _LoggerHook()],
        config=tf.ConfigProto(
            log_device_placement=FLAGS.log_device_placement)) as mon_sess:
      while not mon_sess.should_stop():
        mon_sess.run(train_op) 

# 需要导入模块: import cifar10 [as 别名]
# 或者: from cifar10 import loss [as 别名]
def train():
  """Train CIFAR-10 for a number of steps."""
  with tf.Graph().as_default():
    global_step = tf.train.get_or_create_global_step()

    # Get images and labels for CIFAR-10.
    # Force input pipeline to CPU:0 to avoid operations sometimes ending up on
    # GPU and resulting in a slow down.
    with tf.device('/cpu:0'):
      images, labels = cifar10.distorted_inputs()

    # Build a Graph that computes the logits predictions from the
    # inference model.
    logits = cifar10.inference(images)

    # Calculate loss.
    loss = cifar10.loss(logits, labels)

    # Build a Graph that trains the model with one batch of examples and
    # updates the model parameters.
    train_op = cifar10.train(loss, global_step)

    class _LoggerHook(tf.train.SessionRunHook):
      """Logs loss and runtime."""

      def begin(self):
        self._step = -1
        self._start_time = time.time()

      def before_run(self, run_context):
        self._step += 1
        return tf.train.SessionRunArgs(loss)  # Asks for loss value.

      def after_run(self, run_context, run_values):
        if self._step % FLAGS.log_frequency == 0:
          current_time = time.time()
          duration = current_time - self._start_time
          self._start_time = current_time

          loss_value = run_values.results
          examples_per_sec = FLAGS.log_frequency * FLAGS.batch_size / duration
          sec_per_batch = float(duration / FLAGS.log_frequency)

          format_str = ('%s: step %d, loss = %.2f (%.1f examples/sec; %.3f '
                        'sec/batch)')
          print (format_str % (datetime.now(), self._step, loss_value,
                               examples_per_sec, sec_per_batch))

    with tf.train.MonitoredTrainingSession(
        checkpoint_dir=FLAGS.train_dir,
        hooks=[tf.train.StopAtStepHook(last_step=FLAGS.max_steps),
               tf.train.NanTensorHook(loss),
               _LoggerHook()],
        config=tf.ConfigProto(
            log_device_placement=FLAGS.log_device_placement)) as mon_sess:
      while not mon_sess.should_stop():
        mon_sess.run(train_op) 

# 需要导入模块: import cifar10 [as 别名]
# 或者: from cifar10 import loss [as 别名]
def train():
  """Train CIFAR-10 for a number of steps."""
  with tf.Graph().as_default():
    global_step = tf.contrib.framework.get_or_create_global_step()

    # Get images and labels for CIFAR-10.
    images, labels = cifar10.distorted_inputs()

    # Build a Graph that computes the logits predictions from the
    # inference model.
    logits = cifar10.inference(images)

    # Calculate loss.
    loss = cifar10.loss(logits, labels)

    # Build a Graph that trains the model with one batch of examples and
    # updates the model parameters.
    train_op = cifar10.train(loss, global_step)

    class _LoggerHook(tf.train.SessionRunHook):
      """Logs loss and runtime."""

      def begin(self):
        self._step = -1
        self._start_time = time.time()

      def before_run(self, run_context):
        self._step += 1
        return tf.train.SessionRunArgs(loss)  # Asks for loss value.

      def after_run(self, run_context, run_values):
        if self._step % FLAGS.log_frequency == 0:
          current_time = time.time()
          duration = current_time - self._start_time
          self._start_time = current_time

          loss_value = run_values.results
          examples_per_sec = FLAGS.log_frequency * FLAGS.batch_size / duration
          sec_per_batch = float(duration / FLAGS.log_frequency)

          format_str = ('%s: step %d, loss = %.2f (%.1f examples/sec; %.3f '
                        'sec/batch)')
          print (format_str % (datetime.now(), self._step, loss_value,
                               examples_per_sec, sec_per_batch))

    with tf.train.MonitoredTrainingSession(
        checkpoint_dir=FLAGS.train_dir,
        hooks=[tf.train.StopAtStepHook(last_step=FLAGS.max_steps),
               tf.train.NanTensorHook(loss),
               _LoggerHook()],
        config=tf.ConfigProto(
            log_device_placement=FLAGS.log_device_placement)) as mon_sess:
      while not mon_sess.should_stop():
        mon_sess.run(train_op) 

# 需要导入模块: import cifar10 [as 别名]
# 或者: from cifar10 import loss [as 别名]
def tower_loss(scope):
  """Calculate the total loss on a single tower running the CIFAR model.

  Args:
    scope: unique prefix string identifying the CIFAR tower, e.g. 'tower_0'

  Returns:
     Tensor of shape [] containing the total loss for a batch of data
  """
  # Get images and labels for CIFAR-10.
  images, labels = cifar10.distorted_inputs()

  # Build inference Graph.
  logits = cifar10.inference(images)

  # Build the portion of the Graph calculating the losses. Note that we will
  # assemble the total_loss using a custom function below.
  _ = cifar10.loss(logits, labels)

  # Assemble all of the losses for the current tower only.
  losses = tf.get_collection('losses', scope)

  # Calculate the total loss for the current tower.
  total_loss = tf.add_n(losses, name='total_loss')

  # Compute the moving average of all individual losses and the total loss.
#  loss_averages = tf.train.ExponentialMovingAverage(0.9, name='avg')
#  loss_averages_op = loss_averages.apply(losses + [total_loss])

  # Attach a scalar summary to all individual losses and the total loss; do the
  # same for the averaged version of the losses.
#  for l in losses + [total_loss]:
    # Remove 'tower_[0-9]/' from the name in case this is a multi-GPU training
    # session. This helps the clarity of presentation on tensorboard.
#    loss_name = re.sub('%s_[0-9]*/' % cifar10.TOWER_NAME, '', l.op.name)
    # Name each loss as '(raw)' and name the moving average version of the loss
    # as the original loss name.
#    tf.scalar_summary(loss_name +' (raw)', l)
#    tf.scalar_summary(loss_name, loss_averages.average(l))

#  with tf.control_dependencies([loss_averages_op]):
#    total_loss = tf.identity(total_loss)
  return total_loss