Python standard_ops.multiply方法代码示例

# 需要导入模块: from tensorflow.python.ops import standard_ops [as 别名]
# 或者: from tensorflow.python.ops.standard_ops import multiply [as 别名]
def cosine_similarity(v1, v2):
    """Cosine similarity [-1, 1], `wiki <https://en.wikipedia.org/wiki/Cosine_similarity>`_.

    Parameters
    -----------
    v1, v2 : tensor of [batch_size, n_feature], with the same number of features.

    Returns
    -----------
    a tensor of [batch_size, ]
    """
    try: ## TF1.0
        cost = tf.reduce_sum(tf.multiply(v1, v2), 1) / (tf.sqrt(tf.reduce_sum(tf.multiply(v1, v1), 1)) * tf.sqrt(tf.reduce_sum(tf.multiply(v2, v2), 1)))
    except: ## TF0.12
        cost = tf.reduce_sum(tf.mul(v1, v2), reduction_indices=1) / (tf.sqrt(tf.reduce_sum(tf.mul(v1, v1), reduction_indices=1)) * tf.sqrt(tf.reduce_sum(tf.mul(v2, v2), reduction_indices=1)))
    return cost


## Regularization Functions 

# 需要导入模块: from tensorflow.python.ops import standard_ops [as 别名]
# 或者: from tensorflow.python.ops.standard_ops import multiply [as 别名]
def l1_regularizer(scale, scope=None):
  """Returns a function that can be used to apply L1 regularization to weights.

  L1 regularization encourages sparsity.

  Args:
    scale: A scalar multiplier `Tensor`. 0.0 disables the regularizer.
    scope: An optional scope name.

  Returns:
    A function with signature `l1(weights)` that apply L1 regularization.

  Raises:
    ValueError: If scale is negative or if scale is not a float.
  """
  if isinstance(scale, numbers.Integral):
    raise ValueError('scale cannot be an integer: %s' % scale)
  if isinstance(scale, numbers.Real):
    if scale < 0.:
      raise ValueError('Setting a scale less than 0 on a regularizer: %g' %
                       scale)
    if scale == 0.:
      logging.info('Scale of 0 disables regularizer.')
      return lambda _: None

  def l1(weights, name=None):
    """Applies L1 regularization to weights."""
    with ops.name_scope(scope, 'l1_regularizer', [weights]) as name:
      my_scale = ops.convert_to_tensor(scale,
                                       dtype=weights.dtype.base_dtype,
                                       name='scale')
      return standard_ops.multiply(
          my_scale,
          standard_ops.reduce_sum(standard_ops.abs(weights)),
          name=name)

  return l1 

# 需要导入模块: from tensorflow.python.ops import standard_ops [as 别名]
# 或者: from tensorflow.python.ops.standard_ops import multiply [as 别名]
def l2_regularizer(scale, scope=None):
  """Returns a function that can be used to apply L2 regularization to weights.

  Small values of L2 can help prevent overfitting the training data.

  Args:
    scale: A scalar multiplier `Tensor`. 0.0 disables the regularizer.
    scope: An optional scope name.

  Returns:
    A function with signature `l2(weights)` that applies L2 regularization.

  Raises:
    ValueError: If scale is negative or if scale is not a float.
  """
  if isinstance(scale, numbers.Integral):
    raise ValueError('scale cannot be an integer: %s' % (scale,))
  if isinstance(scale, numbers.Real):
    if scale < 0.:
      raise ValueError('Setting a scale less than 0 on a regularizer: %g.' %
                       scale)
    if scale == 0.:
      logging.info('Scale of 0 disables regularizer.')
      return lambda _: None

  def l2(weights):
    """Applies l2 regularization to weights."""
    with ops.name_scope(scope, 'l2_regularizer', [weights]) as name:
      my_scale = ops.convert_to_tensor(scale,
                                       dtype=weights.dtype.base_dtype,
                                       name='scale')
      return standard_ops.multiply(my_scale, nn.l2_loss(weights), name=name)

  return l2 

# 需要导入模块: from tensorflow.python.ops import standard_ops [as 别名]
# 或者: from tensorflow.python.ops.standard_ops import multiply [as 别名]
def weight_l2_regularizer(initial_weights, scale, scope=None):
  """Returns a function that can be used to apply L2 regularization to weights.
  Small values of L2 can help prevent overfitting the training data.
  Args:
    scale: A scalar multiplier `Tensor`. 0.0 disables the regularizer.
    scope: An optional scope name.
  Returns:
    A function with signature `l2(weights)` that applies L2 regularization.
  Raises:
    ValueError: If scale is negative or if scale is not a float.
  """
  if isinstance(scale, numbers.Integral):
    raise ValueError('scale cannot be an integer: %s' % (scale,))
  if isinstance(scale, numbers.Real):
    if scale < 0.:
      raise ValueError('Setting a scale less than 0 on a regularizer: %g.' %
                       scale)
    if scale == 0.:
      logging.info('Scale of 0 disables regularizer.')
      return lambda _: None

  def l2(weights):
    """Applies l2 regularization to weights."""
    with ops.name_scope(scope, 'l2_regularizer', [weights]) as name:
      my_scale = ops.convert_to_tensor(scale,
                                       dtype=weights.dtype.base_dtype,
                                       name='scale')
      weight_diff = initial_weights - weights
      return standard_ops.multiply(my_scale, nn.l2_loss(weight_diff), name=name)

  return l2 

# 需要导入模块: from tensorflow.python.ops import standard_ops [as 别名]
# 或者: from tensorflow.python.ops.standard_ops import multiply [as 别名]
def orthogonal_regularizer(scale, scope=None):
    """ Return a function that computes orthogonal regularization.
    :param scale: A scalar multiplier `Tensor`. 0.0 disables the regularizer.
    :param scope: An optional scope name.
    :return: A function with signature `orthogonal_sum(weights)` that applies orthogonal regularization.
    """
    if isinstance(scale, numbers.Integral):
        raise ValueError('scale cannot be an integer: %s' % (scale,))
    if isinstance(scale, numbers.Real):
        if scale < 0.:
            raise ValueError('Setting a scale less than 0 on a regularizer: %g.' %
                             scale)
        if scale == 0.:
            logging.info('Scale of 0 disables regularizer.')
            return lambda _: None

    def orthogonal_sum(weights):
        """ Applies orthogonal regularization to weights. """
        with ops.name_scope(scope, 'orthogonal_regularizer', [weights]) as name:
            tensor_scale = ops.convert_to_tensor(scale,
                                                 dtype=weights.dtype.base_dtype,
                                                 name='scale')

            norm_weights = tf.nn.l2_normalize(weights, axis=1)
            anchor_weights_t = tf.transpose(norm_weights)
            det_reg = tf.matmul(anchor_weights_t, norm_weights)
            identity = tf.eye(tf.shape(det_reg)[0])
            det_reg = tf.subtract(det_reg, identity)
            det_reg = tf.reduce_sum(tf.abs(det_reg))

            # Print sum value before scaling
            det_reg = tf.Print(det_reg, [det_reg], "Orthogonal sum for \"{}\" :".format(name))

            return standard_ops.multiply(tensor_scale, det_reg, name=name)

    return orthogonal_sum 

# 需要导入模块: from tensorflow.python.ops import standard_ops [as 别名]
# 或者: from tensorflow.python.ops.standard_ops import multiply [as 别名]
def li_regularizer(scale, scope=None):
  """li regularization removes the neurons of previous layer, `i` represents `inputs`.\n
  Returns a function that can be used to apply group li regularization to weights.\n
  The implementation follows `TensorFlow contrib <https://github.com/tensorflow/tensorflow/blob/master/tensorflow/contrib/layers/python/layers/regularizers.py>`_.

  Parameters
  ----------
  scale : float
    A scalar multiplier `Tensor`. 0.0 disables the regularizer.
  scope: An optional scope name for TF12+.

  Returns
  --------
  A function with signature `li(weights, name=None)` that apply Li regularization.

  Raises
  ------
  ValueError : if scale is outside of the range [0.0, 1.0] or if scale is not a float.
  """
  import numbers
  from tensorflow.python.framework import ops
  from tensorflow.python.ops import standard_ops
  # from tensorflow.python.platform import tf_logging as logging

  if isinstance(scale, numbers.Integral):
    raise ValueError('scale cannot be an integer: %s' % scale)
  if isinstance(scale, numbers.Real):
    if scale < 0.:
      raise ValueError('Setting a scale less than 0 on a regularizer: %g' %
                       scale)
    if scale >= 1.:
      raise ValueError('Setting a scale greater than 1 on a regularizer: %g' %
                       scale)
    if scale == 0.:
      logging.info('Scale of 0 disables regularizer.')
      return lambda _, name=None: None

  def li(weights, name=None):
    """Applies li regularization to weights."""
    with tf.name_scope('li_regularizer') as scope:
        my_scale = ops.convert_to_tensor(scale,
                                           dtype=weights.dtype.base_dtype,
                                           name='scale')
        if tf.__version__ <= '0.12':
            standard_ops_fn = standard_ops.mul
        else:
            standard_ops_fn = standard_ops.multiply
            return standard_ops_fn(
              my_scale,
              standard_ops.reduce_sum(standard_ops.sqrt(standard_ops.reduce_sum(tf.square(weights), 1))),
              name=scope)
  return li 

# 需要导入模块: from tensorflow.python.ops import standard_ops [as 别名]
# 或者: from tensorflow.python.ops.standard_ops import multiply [as 别名]
def lo_regularizer(scale, scope=None):
  """lo regularization removes the neurons of current layer, `o` represents `outputs`\n
  Returns a function that can be used to apply group lo regularization to weights.\n
  The implementation follows `TensorFlow contrib <https://github.com/tensorflow/tensorflow/blob/master/tensorflow/contrib/layers/python/layers/regularizers.py>`_.

  Parameters
  ----------
  scale : float
    A scalar multiplier `Tensor`. 0.0 disables the regularizer.
  scope: An optional scope name for TF12+.

  Returns
  -------
  A function with signature `lo(weights, name=None)` that apply Lo regularization.

  Raises
  ------
  ValueError : If scale is outside of the range [0.0, 1.0] or if scale is not a float.
  """
  import numbers
  from tensorflow.python.framework import ops
  from tensorflow.python.ops import standard_ops
  # from tensorflow.python.platform import tf_logging as logging

  if isinstance(scale, numbers.Integral):
    raise ValueError('scale cannot be an integer: %s' % scale)
  if isinstance(scale, numbers.Real):
    if scale < 0.:
      raise ValueError('Setting a scale less than 0 on a regularizer: %g' %
                       scale)
    if scale >= 1.:
      raise ValueError('Setting a scale greater than 1 on a regularizer: %g' %
                       scale)
    if scale == 0.:
      logging.info('Scale of 0 disables regularizer.')
      return lambda _, name=None: None

  def lo(weights, name='lo_regularizer'):
    """Applies group column regularization to weights."""
    with tf.name_scope(name) as scope:
        my_scale = ops.convert_to_tensor(scale,
                                       dtype=weights.dtype.base_dtype,
                                       name='scale')
        if tf.__version__ <= '0.12':
            standard_ops_fn = standard_ops.mul
        else:
            standard_ops_fn = standard_ops.multiply
        return standard_ops_fn(
          my_scale,
          standard_ops.reduce_sum(standard_ops.sqrt(standard_ops.reduce_sum(tf.square(weights), 0))),
          name=scope)
  return lo 

# 需要导入模块: from tensorflow.python.ops import standard_ops [as 别名]
# 或者: from tensorflow.python.ops.standard_ops import multiply [as 别名]
def maxnorm_regularizer(scale=1.0, scope=None):
  """Max-norm regularization returns a function that can be used
  to apply max-norm regularization to weights.
  About max-norm: `wiki <https://en.wikipedia.org/wiki/Matrix_norm#Max_norm>`_.\n
  The implementation follows `TensorFlow contrib <https://github.com/tensorflow/tensorflow/blob/master/tensorflow/contrib/layers/python/layers/regularizers.py>`_.

  Parameters
  ----------
  scale : float
    A scalar multiplier `Tensor`. 0.0 disables the regularizer.
  scope: An optional scope name.

  Returns
  ---------
  A function with signature `mn(weights, name=None)` that apply Lo regularization.

  Raises
  --------
  ValueError : If scale is outside of the range [0.0, 1.0] or if scale is not a float.
  """
  import numbers
  from tensorflow.python.framework import ops
  from tensorflow.python.ops import standard_ops

  if isinstance(scale, numbers.Integral):
    raise ValueError('scale cannot be an integer: %s' % scale)
  if isinstance(scale, numbers.Real):
    if scale < 0.:
      raise ValueError('Setting a scale less than 0 on a regularizer: %g' %
                       scale)
    # if scale >= 1.:
    #   raise ValueError('Setting a scale greater than 1 on a regularizer: %g' %
    #                    scale)
    if scale == 0.:
      logging.info('Scale of 0 disables regularizer.')
      return lambda _, name=None: None

  def mn(weights, name='max_regularizer'):
    """Applies max-norm regularization to weights."""
    with tf.name_scope(name) as scope:
          my_scale = ops.convert_to_tensor(scale,
                                           dtype=weights.dtype.base_dtype,
                                           name='scale')
          if tf.__version__ <= '0.12':
              standard_ops_fn = standard_ops.mul
          else:
              standard_ops_fn = standard_ops.multiply
          return standard_ops_fn(my_scale, standard_ops.reduce_max(standard_ops.abs(weights)), name=scope)
  return mn 

# 需要导入模块: from tensorflow.python.ops import standard_ops [as 别名]
# 或者: from tensorflow.python.ops.standard_ops import multiply [as 别名]
def maxnorm_o_regularizer(scale, scope):
  """Max-norm output regularization removes the neurons of current layer.\n
  Returns a function that can be used to apply max-norm regularization to each column of weight matrix.\n
  The implementation follows `TensorFlow contrib <https://github.com/tensorflow/tensorflow/blob/master/tensorflow/contrib/layers/python/layers/regularizers.py>`_.

  Parameters
  ----------
  scale : float
    A scalar multiplier `Tensor`. 0.0 disables the regularizer.
  scope: An optional scope name.

  Returns
  ---------
  A function with signature `mn_o(weights, name=None)` that apply Lo regularization.

  Raises
  ---------
  ValueError : If scale is outside of the range [0.0, 1.0] or if scale is not a float.
  """
  import numbers
  from tensorflow.python.framework import ops
  from tensorflow.python.ops import standard_ops

  if isinstance(scale, numbers.Integral):
    raise ValueError('scale cannot be an integer: %s' % scale)
  if isinstance(scale, numbers.Real):
    if scale < 0.:
      raise ValueError('Setting a scale less than 0 on a regularizer: %g' %
                       scale)
    # if scale >= 1.:
    #   raise ValueError('Setting a scale greater than 1 on a regularizer: %g' %
    #                    scale)
    if scale == 0.:
      logging.info('Scale of 0 disables regularizer.')
      return lambda _, name=None: None

  def mn_o(weights, name='maxnorm_o_regularizer'):
     """Applies max-norm regularization to weights."""
     with tf.name_scope(name) as scope:
          my_scale = ops.convert_to_tensor(scale,
                                           dtype=weights.dtype.base_dtype,
                                                   name='scale')
          if tf.__version__ <= '0.12':
             standard_ops_fn = standard_ops.mul
          else:
             standard_ops_fn = standard_ops.multiply
          return standard_ops_fn(my_scale, standard_ops.reduce_sum(standard_ops.reduce_max(standard_ops.abs(weights), 0)), name=scope)
  return mn_o