Python losses.log_quaternion_loss() Examples

The following are 10 code examples of losses.log_quaternion_loss(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module losses , or try the search function .
Example #1
Source File: dsn.py    From DOTA_models with Apache License 2.0 5 votes vote down vote up 
def add_task_loss(source_images, source_labels, basic_tower, params):
  """Adds a classification and/or pose estimation loss to the model.

  Args:
    source_images: images from the source domain, a tensor of size
      [batch_size, height, width, channels]
    source_labels: labels from the source domain, a tensor of size [batch_size].
      or a tuple of (quaternions, class_labels)
    basic_tower: a function that creates the single tower of the model.
    params: A dictionary of parameters. Expecting 'weight_decay', 'pose_weight'.
  Returns:
    The source endpoints.

  Raises:
    RuntimeError: if basic tower does not support pose estimation.
  """
  with tf.variable_scope('towers'):
    source_logits, source_endpoints = basic_tower(
        source_images, weight_decay=params['weight_decay'], prefix='Source')

  if 'quaternions' in source_labels:  # We have pose estimation as well
    if 'quaternion_pred' not in source_endpoints:
      raise RuntimeError('Please use a model for estimation e.g. pose_mini')

    loss = losses.log_quaternion_loss(source_labels['quaternions'],
                                      source_endpoints['quaternion_pred'],
                                      params)

    assert_op = tf.Assert(tf.is_finite(loss), [loss])
    with tf.control_dependencies([assert_op]):
      quaternion_loss = loss
      tf.summary.histogram('log_quaternion_loss_hist', quaternion_loss)
    slim.losses.add_loss(quaternion_loss * params['pose_weight'])
    tf.summary.scalar('losses/quaternion_loss', quaternion_loss)

  classification_loss = tf.losses.softmax_cross_entropy(
      source_labels['classes'], source_logits)

  tf.summary.scalar('losses/classification_loss', classification_loss)
  return source_endpoints
Example #2
Source File: dsn.py    From yolo_v2 with Apache License 2.0 5 votes vote down vote up 
def add_task_loss(source_images, source_labels, basic_tower, params):
  """Adds a classification and/or pose estimation loss to the model.

  Args:
    source_images: images from the source domain, a tensor of size
      [batch_size, height, width, channels]
    source_labels: labels from the source domain, a tensor of size [batch_size].
      or a tuple of (quaternions, class_labels)
    basic_tower: a function that creates the single tower of the model.
    params: A dictionary of parameters. Expecting 'weight_decay', 'pose_weight'.
  Returns:
    The source endpoints.

  Raises:
    RuntimeError: if basic tower does not support pose estimation.
  """
  with tf.variable_scope('towers'):
    source_logits, source_endpoints = basic_tower(
        source_images, weight_decay=params['weight_decay'], prefix='Source')

  if 'quaternions' in source_labels:  # We have pose estimation as well
    if 'quaternion_pred' not in source_endpoints:
      raise RuntimeError('Please use a model for estimation e.g. pose_mini')

    loss = losses.log_quaternion_loss(source_labels['quaternions'],
                                      source_endpoints['quaternion_pred'],
                                      params)

    assert_op = tf.Assert(tf.is_finite(loss), [loss])
    with tf.control_dependencies([assert_op]):
      quaternion_loss = loss
      tf.summary.histogram('log_quaternion_loss_hist', quaternion_loss)
    slim.losses.add_loss(quaternion_loss * params['pose_weight'])
    tf.summary.scalar('losses/quaternion_loss', quaternion_loss)

  classification_loss = tf.losses.softmax_cross_entropy(
      source_labels['classes'], source_logits)

  tf.summary.scalar('losses/classification_loss', classification_loss)
  return source_endpoints
Example #3
Source File: dsn.py    From Gun-Detector with Apache License 2.0 5 votes vote down vote up 
def add_task_loss(source_images, source_labels, basic_tower, params):
  """Adds a classification and/or pose estimation loss to the model.

  Args:
    source_images: images from the source domain, a tensor of size
      [batch_size, height, width, channels]
    source_labels: labels from the source domain, a tensor of size [batch_size].
      or a tuple of (quaternions, class_labels)
    basic_tower: a function that creates the single tower of the model.
    params: A dictionary of parameters. Expecting 'weight_decay', 'pose_weight'.
  Returns:
    The source endpoints.

  Raises:
    RuntimeError: if basic tower does not support pose estimation.
  """
  with tf.variable_scope('towers'):
    source_logits, source_endpoints = basic_tower(
        source_images, weight_decay=params['weight_decay'], prefix='Source')

  if 'quaternions' in source_labels:  # We have pose estimation as well
    if 'quaternion_pred' not in source_endpoints:
      raise RuntimeError('Please use a model for estimation e.g. pose_mini')

    loss = losses.log_quaternion_loss(source_labels['quaternions'],
                                      source_endpoints['quaternion_pred'],
                                      params)

    assert_op = tf.Assert(tf.is_finite(loss), [loss])
    with tf.control_dependencies([assert_op]):
      quaternion_loss = loss
      tf.summary.histogram('log_quaternion_loss_hist', quaternion_loss)
    slim.losses.add_loss(quaternion_loss * params['pose_weight'])
    tf.summary.scalar('losses/quaternion_loss', quaternion_loss)

  classification_loss = tf.losses.softmax_cross_entropy(
      source_labels['classes'], source_logits)

  tf.summary.scalar('losses/classification_loss', classification_loss)
  return source_endpoints
Example #4
Source File: dsn.py    From hands-detection with MIT License 5 votes vote down vote up 
def add_task_loss(source_images, source_labels, basic_tower, params):
  """Adds a classification and/or pose estimation loss to the model.

  Args:
    source_images: images from the source domain, a tensor of size
      [batch_size, height, width, channels]
    source_labels: labels from the source domain, a tensor of size [batch_size].
      or a tuple of (quaternions, class_labels)
    basic_tower: a function that creates the single tower of the model.
    params: A dictionary of parameters. Expecting 'weight_decay', 'pose_weight'.
  Returns:
    The source endpoints.

  Raises:
    RuntimeError: if basic tower does not support pose estimation.
  """
  with tf.variable_scope('towers'):
    source_logits, source_endpoints = basic_tower(
        source_images, weight_decay=params['weight_decay'], prefix='Source')

  if 'quaternions' in source_labels:  # We have pose estimation as well
    if 'quaternion_pred' not in source_endpoints:
      raise RuntimeError('Please use a model for estimation e.g. pose_mini')

    loss = losses.log_quaternion_loss(source_labels['quaternions'],
                                      source_endpoints['quaternion_pred'],
                                      params)

    assert_op = tf.Assert(tf.is_finite(loss), [loss])
    with tf.control_dependencies([assert_op]):
      quaternion_loss = loss
      tf.summary.histogram('log_quaternion_loss_hist', quaternion_loss)
    slim.losses.add_loss(quaternion_loss * params['pose_weight'])
    tf.summary.scalar('losses/quaternion_loss', quaternion_loss)

  classification_loss = tf.losses.softmax_cross_entropy(
      source_labels['classes'], source_logits)

  tf.summary.scalar('losses/classification_loss', classification_loss)
  return source_endpoints
Example #5
Source File: dsn.py    From object_detection_kitti with Apache License 2.0 5 votes vote down vote up 
def add_task_loss(source_images, source_labels, basic_tower, params):
  """Adds a classification and/or pose estimation loss to the model.

  Args:
    source_images: images from the source domain, a tensor of size
      [batch_size, height, width, channels]
    source_labels: labels from the source domain, a tensor of size [batch_size].
      or a tuple of (quaternions, class_labels)
    basic_tower: a function that creates the single tower of the model.
    params: A dictionary of parameters. Expecting 'weight_decay', 'pose_weight'.
  Returns:
    The source endpoints.

  Raises:
    RuntimeError: if basic tower does not support pose estimation.
  """
  with tf.variable_scope('towers'):
    source_logits, source_endpoints = basic_tower(
        source_images, weight_decay=params['weight_decay'], prefix='Source')

  if 'quaternions' in source_labels:  # We have pose estimation as well
    if 'quaternion_pred' not in source_endpoints:
      raise RuntimeError('Please use a model for estimation e.g. pose_mini')

    loss = losses.log_quaternion_loss(source_labels['quaternions'],
                                      source_endpoints['quaternion_pred'],
                                      params)

    assert_op = tf.Assert(tf.is_finite(loss), [loss])
    with tf.control_dependencies([assert_op]):
      quaternion_loss = loss
      tf.summary.histogram('log_quaternion_loss_hist', quaternion_loss)
    slim.losses.add_loss(quaternion_loss * params['pose_weight'])
    tf.summary.scalar('losses/quaternion_loss', quaternion_loss)

  classification_loss = tf.losses.softmax_cross_entropy(
      source_labels['classes'], source_logits)

  tf.summary.scalar('losses/classification_loss', classification_loss)
  return source_endpoints
Example #6
Source File: dsn.py    From object_detection_with_tensorflow with MIT License 5 votes vote down vote up 
def add_task_loss(source_images, source_labels, basic_tower, params):
  """Adds a classification and/or pose estimation loss to the model.

  Args:
    source_images: images from the source domain, a tensor of size
      [batch_size, height, width, channels]
    source_labels: labels from the source domain, a tensor of size [batch_size].
      or a tuple of (quaternions, class_labels)
    basic_tower: a function that creates the single tower of the model.
    params: A dictionary of parameters. Expecting 'weight_decay', 'pose_weight'.
  Returns:
    The source endpoints.

  Raises:
    RuntimeError: if basic tower does not support pose estimation.
  """
  with tf.variable_scope('towers'):
    source_logits, source_endpoints = basic_tower(
        source_images, weight_decay=params['weight_decay'], prefix='Source')

  if 'quaternions' in source_labels:  # We have pose estimation as well
    if 'quaternion_pred' not in source_endpoints:
      raise RuntimeError('Please use a model for estimation e.g. pose_mini')

    loss = losses.log_quaternion_loss(source_labels['quaternions'],
                                      source_endpoints['quaternion_pred'],
                                      params)

    assert_op = tf.Assert(tf.is_finite(loss), [loss])
    with tf.control_dependencies([assert_op]):
      quaternion_loss = loss
      tf.summary.histogram('log_quaternion_loss_hist', quaternion_loss)
    slim.losses.add_loss(quaternion_loss * params['pose_weight'])
    tf.summary.scalar('losses/quaternion_loss', quaternion_loss)

  classification_loss = tf.losses.softmax_cross_entropy(
      source_labels['classes'], source_logits)

  tf.summary.scalar('losses/classification_loss', classification_loss)
  return source_endpoints
Example #7
Source File: dsn.py    From HumanRecognition with MIT License 5 votes vote down vote up 
def add_task_loss(source_images, source_labels, basic_tower, params):
  """Adds a classification and/or pose estimation loss to the model.

  Args:
    source_images: images from the source domain, a tensor of size
      [batch_size, height, width, channels]
    source_labels: labels from the source domain, a tensor of size [batch_size].
      or a tuple of (quaternions, class_labels)
    basic_tower: a function that creates the single tower of the model.
    params: A dictionary of parameters. Expecting 'weight_decay', 'pose_weight'.
  Returns:
    The source endpoints.

  Raises:
    RuntimeError: if basic tower does not support pose estimation.
  """
  with tf.variable_scope('towers'):
    source_logits, source_endpoints = basic_tower(
        source_images, weight_decay=params['weight_decay'], prefix='Source')

  if 'quaternions' in source_labels:  # We have pose estimation as well
    if 'quaternion_pred' not in source_endpoints:
      raise RuntimeError('Please use a model for estimation e.g. pose_mini')

    loss = losses.log_quaternion_loss(source_labels['quaternions'],
                                      source_endpoints['quaternion_pred'],
                                      params)

    assert_op = tf.Assert(tf.is_finite(loss), [loss])
    with tf.control_dependencies([assert_op]):
      quaternion_loss = loss
      tf.summary.histogram('log_quaternion_loss_hist', quaternion_loss)
    slim.losses.add_loss(quaternion_loss * params['pose_weight'])
    tf.summary.scalar('losses/quaternion_loss', quaternion_loss)

  classification_loss = tf.losses.softmax_cross_entropy(
      source_labels['classes'], source_logits)

  tf.summary.scalar('losses/classification_loss', classification_loss)
  return source_endpoints
Example #8
Source File: dsn.py    From g-tensorflow-models with Apache License 2.0 5 votes vote down vote up 
def add_task_loss(source_images, source_labels, basic_tower, params):
  """Adds a classification and/or pose estimation loss to the model.

  Args:
    source_images: images from the source domain, a tensor of size
      [batch_size, height, width, channels]
    source_labels: labels from the source domain, a tensor of size [batch_size].
      or a tuple of (quaternions, class_labels)
    basic_tower: a function that creates the single tower of the model.
    params: A dictionary of parameters. Expecting 'weight_decay', 'pose_weight'.
  Returns:
    The source endpoints.

  Raises:
    RuntimeError: if basic tower does not support pose estimation.
  """
  with tf.variable_scope('towers'):
    source_logits, source_endpoints = basic_tower(
        source_images, weight_decay=params['weight_decay'], prefix='Source')

  if 'quaternions' in source_labels:  # We have pose estimation as well
    if 'quaternion_pred' not in source_endpoints:
      raise RuntimeError('Please use a model for estimation e.g. pose_mini')

    loss = losses.log_quaternion_loss(source_labels['quaternions'],
                                      source_endpoints['quaternion_pred'],
                                      params)

    assert_op = tf.Assert(tf.is_finite(loss), [loss])
    with tf.control_dependencies([assert_op]):
      quaternion_loss = loss
      tf.summary.histogram('log_quaternion_loss_hist', quaternion_loss)
    slim.losses.add_loss(quaternion_loss * params['pose_weight'])
    tf.summary.scalar('losses/quaternion_loss', quaternion_loss)

  classification_loss = tf.losses.softmax_cross_entropy(
      source_labels['classes'], source_logits)

  tf.summary.scalar('losses/classification_loss', classification_loss)
  return source_endpoints
Example #9
Source File: dsn.py    From models with Apache License 2.0 5 votes vote down vote up 
def add_task_loss(source_images, source_labels, basic_tower, params):
  """Adds a classification and/or pose estimation loss to the model.

  Args:
    source_images: images from the source domain, a tensor of size
      [batch_size, height, width, channels]
    source_labels: labels from the source domain, a tensor of size [batch_size].
      or a tuple of (quaternions, class_labels)
    basic_tower: a function that creates the single tower of the model.
    params: A dictionary of parameters. Expecting 'weight_decay', 'pose_weight'.
  Returns:
    The source endpoints.

  Raises:
    RuntimeError: if basic tower does not support pose estimation.
  """
  with tf.variable_scope('towers'):
    source_logits, source_endpoints = basic_tower(
        source_images, weight_decay=params['weight_decay'], prefix='Source')

  if 'quaternions' in source_labels:  # We have pose estimation as well
    if 'quaternion_pred' not in source_endpoints:
      raise RuntimeError('Please use a model for estimation e.g. pose_mini')

    loss = losses.log_quaternion_loss(source_labels['quaternions'],
                                      source_endpoints['quaternion_pred'],
                                      params)

    assert_op = tf.Assert(tf.is_finite(loss), [loss])
    with tf.control_dependencies([assert_op]):
      quaternion_loss = loss
      tf.summary.histogram('log_quaternion_loss_hist', quaternion_loss)
    slim.losses.add_loss(quaternion_loss * params['pose_weight'])
    tf.summary.scalar('losses/quaternion_loss', quaternion_loss)

  classification_loss = tf.losses.softmax_cross_entropy(
      source_labels['classes'], source_logits)

  tf.summary.scalar('losses/classification_loss', classification_loss)
  return source_endpoints
Example #10
Source File: dsn.py    From multilabel-image-classification-tensorflow with MIT License 5 votes vote down vote up 
def add_task_loss(source_images, source_labels, basic_tower, params):
  """Adds a classification and/or pose estimation loss to the model.

  Args:
    source_images: images from the source domain, a tensor of size
      [batch_size, height, width, channels]
    source_labels: labels from the source domain, a tensor of size [batch_size].
      or a tuple of (quaternions, class_labels)
    basic_tower: a function that creates the single tower of the model.
    params: A dictionary of parameters. Expecting 'weight_decay', 'pose_weight'.
  Returns:
    The source endpoints.

  Raises:
    RuntimeError: if basic tower does not support pose estimation.
  """
  with tf.variable_scope('towers'):
    source_logits, source_endpoints = basic_tower(
        source_images, weight_decay=params['weight_decay'], prefix='Source')

  if 'quaternions' in source_labels:  # We have pose estimation as well
    if 'quaternion_pred' not in source_endpoints:
      raise RuntimeError('Please use a model for estimation e.g. pose_mini')

    loss = losses.log_quaternion_loss(source_labels['quaternions'],
                                      source_endpoints['quaternion_pred'],
                                      params)

    assert_op = tf.Assert(tf.is_finite(loss), [loss])
    with tf.control_dependencies([assert_op]):
      quaternion_loss = loss
      tf.summary.histogram('log_quaternion_loss_hist', quaternion_loss)
    slim.losses.add_loss(quaternion_loss * params['pose_weight'])
    tf.summary.scalar('losses/quaternion_loss', quaternion_loss)

  classification_loss = tf.losses.softmax_cross_entropy(
      source_labels['classes'], source_logits)

  tf.summary.scalar('losses/classification_loss', classification_loss)
  return source_endpoints