Python logging_ops.Print方法代碼示例

# 需要導入模塊: from tensorflow.python.ops import logging_ops [as 別名]
# 或者: from tensorflow.python.ops.logging_ops import Print [as 別名]
def add_image_summary(tensor, name=None, prefix=None, print_summary=False):
  """Adds an image summary for the given tensor.

  Args:
    tensor: a variable or op tensor with shape [batch,height,width,channels]
    name: the optional name for the summary.
    prefix: An optional prefix for the summary names.
    print_summary: If `True`, the summary is printed to stdout when the summary
      is computed.

  Returns:
    An image `Tensor` of type `string` whose contents are the serialized
    `Summary` protocol buffer.
  """
  summary_name = _get_summary_name(tensor, name, prefix)
  # If print_summary, then we need to make sure that this call doesn't add the
  # non-printing op to the collection. We'll add it to the collection later.
  collections = [] if print_summary else None
  op = summary.image(
      name=summary_name, tensor=tensor, collections=collections)
  if print_summary:
    op = logging_ops.Print(op, [tensor], summary_name)
    ops.add_to_collection(ops.GraphKeys.SUMMARIES, op)
  return op 

# 需要導入模塊: from tensorflow.python.ops import logging_ops [as 別名]
# 或者: from tensorflow.python.ops.logging_ops import Print [as 別名]
def add_scalar_summary(tensor, name=None, prefix=None, print_summary=False):
  """Adds a scalar summary for the given tensor.

  Args:
    tensor: a variable or op tensor.
    name: the optional name for the summary.
    prefix: An optional prefix for the summary names.
    print_summary: If `True`, the summary is printed to stdout when the summary
      is computed.

  Returns:
    A scalar `Tensor` of type `string` whose contents are the serialized
    `Summary` protocol buffer.
  """
  collections = [] if print_summary else None
  summary_name = _get_summary_name(tensor, name, prefix)

  # If print_summary, then we need to make sure that this call doesn't add the
  # non-printing op to the collection. We'll add it to the collection later.
  op = summary.scalar(
      name=summary_name, tensor=tensor, collections=collections)
  if print_summary:
    op = logging_ops.Print(op, [tensor], summary_name)
    ops.add_to_collection(ops.GraphKeys.SUMMARIES, op)
  return op 

# 需要導入模塊: from tensorflow.python.ops import logging_ops [as 別名]
# 或者: from tensorflow.python.ops.logging_ops import Print [as 別名]
def print_tensor(x, message=''):
  """Prints `message` and the tensor value when evaluated.

  Arguments:
      x: Tensor to print.
      message: Message to print jointly with the tensor.

  Returns:
      The same tensor `x`, unchanged.
  """
  return logging_ops.Print(x, [x], message)


# GRAPH MANIPULATION 

# 需要導入模塊: from tensorflow.python.ops import logging_ops [as 別名]
# 或者: from tensorflow.python.ops.logging_ops import Print [as 別名]
def npairs_loss(labels, embeddings_anchor, embeddings_positive,
                reg_lambda=0.002, print_losses=False):
  """Computes the npairs loss.

  Npairs loss expects paired data where a pair is composed of samples from the
  same labels and each pairs in the minibatch have different labels. The loss
  has two components. The first component is the L2 regularizer on the
  embedding vectors. The second component is the sum of cross entropy loss
  which takes each row of the pair-wise similarity matrix as logits and
  the remapped one-hot labels as labels.

  See: http://www.nec-labs.com/uploads/images/Department-Images/MediaAnalytics/papers/nips16_npairmetriclearning.pdf

  Args:
    labels: 1-D tf.int32 `Tensor` of shape [batch_size/2].
    embeddings_anchor: 2-D Tensor of shape [batch_size/2, embedding_dim] for the
      embedding vectors for the anchor images. Embeddings should not be
      l2 normalized.
    embeddings_positive: 2-D Tensor of shape [batch_size/2, embedding_dim] for the
      embedding vectors for the positive images. Embeddings should not be
      l2 normalized.
    reg_lambda: Float. L2 regularization term on the embedding vectors.
    print_losses: Boolean. Option to print the xent and l2loss.

  Returns:
    npairs_loss: tf.float32 scalar.
  """
  # pylint: enable=line-too-long
  # Add the regularizer on the embedding.
  reg_anchor = math_ops.reduce_mean(
      math_ops.reduce_sum(math_ops.square(embeddings_anchor), 1))
  reg_positive = math_ops.reduce_mean(
      math_ops.reduce_sum(math_ops.square(embeddings_positive), 1))
  l2loss = math_ops.multiply(
      0.25 * reg_lambda, reg_anchor + reg_positive, name='l2loss')

  # Get per pair similarities.
  similarity_matrix = math_ops.matmul(
      embeddings_anchor, embeddings_positive, transpose_a=False,
      transpose_b=True)

  # Reshape [batch_size] label tensor to a [batch_size, 1] label tensor.
  lshape = array_ops.shape(labels)
  assert lshape.shape == 1
  labels = array_ops.reshape(labels, [lshape[0], 1])

  labels_remapped = math_ops.cast(
      math_ops.equal(labels, array_ops.transpose(labels)), dtypes.float32)
  labels_remapped /= math_ops.reduce_sum(labels_remapped, 1, keepdims=True)

  # Add the softmax loss.
  xent_loss = nn.softmax_cross_entropy_with_logits(
      logits=similarity_matrix, labels=labels_remapped)
  xent_loss = math_ops.reduce_mean(xent_loss, name='xentropy')

  if print_losses:
    xent_loss = logging_ops.Print(
        xent_loss, ['cross entropy:', xent_loss, 'l2loss:', l2loss])

  return l2loss + xent_loss 

# 需要導入模塊: from tensorflow.python.ops import logging_ops [as 別名]
# 或者: from tensorflow.python.ops.logging_ops import Print [as 別名]
def npairs_loss(labels, embeddings_anchor, embeddings_positive,
                reg_lambda=0.002, print_losses=False):
  """Computes the npairs loss.

  Npairs loss expects paired data where a pair is composed of samples from the
  same labels and each pairs in the minibatch have different labels. The loss
  has two components. The first component is the L2 regularizer on the
  embedding vectors. The second component is the sum of cross entropy loss
  which takes each row of the pair-wise similarity matrix as logits and
  the remapped one-hot labels as labels.

  See: http://www.nec-labs.com/uploads/images/Department-Images/MediaAnalytics/papers/nips16_npairmetriclearning.pdf

  Args:
    labels: 1-D tf.int32 `Tensor` of shape [batch_size/2].
    embeddings_anchor: 2-D Tensor of shape [batch_size/2, embedding_dim] for the
      embedding vectors for the anchor images. Embeddings should not be
      l2 normalized.
    embeddings_positive: 2-D Tensor of shape [batch_size/2, embedding_dim] for the
      embedding vectors for the positive images. Embeddings should not be
      l2 normalized.
    reg_lambda: Float. L2 regularization term on the embedding vectors.
    print_losses: Boolean. Option to print the xent and l2loss.

  Returns:
    npairs_loss: tf.float32 scalar.
  """
  # pylint: enable=line-too-long
  # Add the regularizer on the embedding.
  reg_anchor = math_ops.reduce_mean(
      math_ops.reduce_sum(math_ops.square(embeddings_anchor), 1))
  reg_positive = math_ops.reduce_mean(
      math_ops.reduce_sum(math_ops.square(embeddings_positive), 1))
  l2loss = math_ops.multiply(
      0.25 * reg_lambda, reg_anchor + reg_positive, name='l2loss')

  # Get per pair similarities.
  similarity_matrix = math_ops.matmul(
      embeddings_anchor, embeddings_positive, transpose_a=False,
      transpose_b=True)

  # Reshape [batch_size] label tensor to a [batch_size, 1] label tensor.
  lshape = array_ops.shape(labels)
  assert lshape.shape == 1
  labels = array_ops.reshape(labels, [lshape[0], 1])

  labels_remapped = math_ops.to_float(
      math_ops.equal(labels, array_ops.transpose(labels)))
  labels_remapped /= math_ops.reduce_sum(labels_remapped, 1, keep_dims=True)

  # Add the softmax loss.
  xent_loss = nn.softmax_cross_entropy_with_logits(
      logits=similarity_matrix, labels=labels_remapped)
  xent_loss = math_ops.reduce_mean(xent_loss, name='xentropy')

  if print_losses:
    xent_loss = logging_ops.Print(
        xent_loss, ['cross entropy:', xent_loss, 'l2loss:', l2loss])

  return l2loss + xent_loss