python类to_float()的实例源码

def _lengths_to_masks(lengths, max_length):
  """Creates a binary matrix that can be used to mask away padding.

  Args:
    lengths: A vector of integers representing lengths.
    max_length: An integer indicating the maximum length. All values in
      lengths should be less than max_length.
  Returns:
    masks: Masks that can be used to get rid of padding.
  """
  tiled_ranges = array_ops.tile(
      array_ops.expand_dims(math_ops.range(max_length), 0),
      [array_ops.shape(lengths)[0], 1])
  lengths = array_ops.expand_dims(lengths, 1)
  masks = math_ops.to_float(
      math_ops.to_int64(tiled_ranges) < math_ops.to_int64(lengths))
  return masks

def insert_transformed_feature(self, columns_to_tensors):
    """Apply transformation and inserts it into columns_to_tensors.

    Args:
      columns_to_tensors: A mapping from feature columns to tensors. 'string'
        key means a base feature (not-transformed). It can have _FeatureColumn
        as a key too. That means that _FeatureColumn is already transformed.
    """
    # Transform the input tensor according to the normalizer function + reshape.
    input_tensor = self._normalized_input_tensor(columns_to_tensors[self.name])
    batch_size = input_tensor.get_shape().as_list()[0]
    batch_size = int(batch_size) if batch_size else -1
    flattened_shape = [batch_size, self.dimension]
    columns_to_tensors[self] = array_ops.reshape(
        math_ops.to_float(input_tensor), flattened_shape, name="reshape")

  # pylint: disable=unused-argument

def loss(self, data, labels):
    """The loss to minimize while training."""

    if self.is_regression:
      diff = self.training_inference_graph(data) - math_ops.to_float(labels)
      mean_squared_error = math_ops.reduce_mean(diff * diff)
      root_mean_squared_error = math_ops.sqrt(mean_squared_error, name="loss")
      loss = root_mean_squared_error
    else:
      loss = math_ops.reduce_mean(
          nn_ops.sparse_softmax_cross_entropy_with_logits(
              self.training_inference_graph(data),
              array_ops.squeeze(math_ops.to_int32(labels))),
          name="loss")
    if self.regularizer:
      loss += layers.apply_regularization(self.regularizer,
                                          variables.trainable_variables())
    return loss

def _lengths_to_masks(lengths, max_length):
  """Creates a binary matrix that can be used to mask away padding.

  Args:
    lengths: A vector of integers representing lengths.
    max_length: An integer indicating the maximum length. All values in
      lengths should be less than max_length.
  Returns:
    masks: Masks that can be used to get rid of padding.
  """
  tiled_ranges = array_ops.tile(
      array_ops.expand_dims(math_ops.range(max_length), 0),
      [array_ops.shape(lengths)[0], 1])
  lengths = array_ops.expand_dims(lengths, 1)
  masks = math_ops.to_float(
      math_ops.to_int64(tiled_ranges) < math_ops.to_int64(lengths))
  return masks

def hinge_loss(logits, labels=None, scope=None, target=None):
  """Method that returns the loss tensor for hinge loss.

  Args:
    logits: The logits, a float tensor.
    labels: The ground truth output tensor. Its shape should match the shape of
      logits. The values of the tensor are expected to be 0.0 or 1.0.
    scope: The scope for the operations performed in computing the loss.
    target: Deprecated alias for `labels`.

  Returns:
    A `Tensor` of same shape as logits and target representing the loss values
      across the batch.

  Raises:
    ValueError: If the shapes of `logits` and `labels` don't match.
  """
  labels = _labels(labels, target)
  with ops.name_scope(scope, "hinge_loss", [logits, labels]) as scope:
    logits.get_shape().assert_is_compatible_with(labels.get_shape())
    # We first need to convert binary labels to -1/1 labels (as floats).
    labels = math_ops.to_float(labels)
    all_ones = array_ops.ones_like(labels)
    labels = math_ops.sub(2 * labels, all_ones)
    return nn_ops.relu(math_ops.sub(all_ones, math_ops.mul(labels, logits)))

def _get_loss(self, features, labels, data_spec=None):
    """Constructs, caches, and returns the inference-based loss."""
    if self._loss is not None:
      return self._loss

    def _average_loss():
      probs = self.inference_graph(features, data_spec=data_spec)
      return math_ops.reduce_sum(self.loss_fn(
          probs, labels)) / math_ops.to_float(
              array_ops.shape(features)[0])

    self._loss = control_flow_ops.cond(
        self.average_size() > 0, _average_loss,
        lambda: constant_op.constant(sys.maxsize, dtype=dtypes.float32))

    return self._loss

def loss(self, data, labels):
    """The loss to minimize while training."""

    if self.is_regression:
      diff = self.training_inference_graph(data) - math_ops.to_float(labels)
      mean_squared_error = math_ops.reduce_mean(diff * diff)
      root_mean_squared_error = math_ops.sqrt(mean_squared_error, name="loss")
      loss = root_mean_squared_error
    else:
      loss = math_ops.reduce_mean(
          nn_ops.sparse_softmax_cross_entropy_with_logits(
              self.training_inference_graph(data),
              array_ops.squeeze(math_ops.to_int32(labels))),
          name="loss")
    if self.regularizer:
      loss += layers.apply_regularization(self.regularizer,
                                          variables.trainable_variables())
    return loss

def _lengths_to_masks(lengths, max_length):
  """Creates a binary matrix that can be used to mask away padding.

  Args:
    lengths: A vector of integers representing lengths.
    max_length: An integer indicating the maximum length. All values in
      lengths should be less than max_length.
  Returns:
    masks: Masks that can be used to get rid of padding.
  """

  tiled_ranges = array_ops.tile(
      array_ops.expand_dims(math_ops.range(max_length), 0),
      [array_ops.shape(lengths)[0], 1])
  lengths = array_ops.expand_dims(lengths, 1)
  masks = math_ops.to_float(
      math_ops.to_int64(tiled_ranges) < math_ops.to_int64(lengths))

  return masks

def PearsonCorrelationTF(x, y, prefix='pearson'):
  '''Create a TF network that calculates the Pearson Correlation on two input
  vectors.  Returns a scalar tensor with the correlation [-1:1].'''
  with tf.name_scope(prefix):
    n = tf.to_float(tf.shape(x)[0])
    x_sum = tf.reduce_sum(x)
    y_sum = tf.reduce_sum(y)
    xy_sum = tf.reduce_sum(tf.multiply(x, y))
    x2_sum = tf.reduce_sum(tf.multiply(x, x))
    y2_sum = tf.reduce_sum(tf.multiply(y, y))

    r_num = tf.subtract(tf.multiply(n, xy_sum), tf.multiply(x_sum, y_sum))
    r_den_x = tf.sqrt(tf.subtract(tf.multiply(n, x2_sum), tf.multiply(x_sum, x_sum)))
    r_den_y = tf.sqrt(tf.subtract(tf.multiply(n, y2_sum), tf.multiply(y_sum, y_sum)))
    r = tf.div(r_num, tf.multiply(r_den_x, r_den_y), name='r')
  return r

def _lengths_to_masks(lengths, max_length):
  """Creates a binary matrix that can be used to mask away padding.

  Args:
    lengths: A vector of integers representing lengths.
    max_length: An integer indicating the maximum length. All values in
      lengths should be less than max_length.
  Returns:
    masks: Masks that can be used to get rid of padding.
  """
  tiled_ranges = array_ops.tile(
      array_ops.expand_dims(math_ops.range(max_length), 0),
      [array_ops.shape(lengths)[0], 1])
  lengths = array_ops.expand_dims(lengths, 1)
  masks = math_ops.to_float(
      math_ops.to_int64(tiled_ranges) < math_ops.to_int64(lengths))
  return masks

def hinge_loss(logits, labels=None, scope=None):
  """Method that returns the loss tensor for hinge loss.

  Args:
    logits: The logits, a float tensor.
    labels: The ground truth output tensor. Its shape should match the shape of
      logits. The values of the tensor are expected to be 0.0 or 1.0.
    scope: The scope for the operations performed in computing the loss.

  Returns:
    A `Tensor` of same shape as `logits` and `labels` representing the loss
      values across the batch.

  Raises:
    ValueError: If the shapes of `logits` and `labels` don't match.
  """
  with ops.name_scope(scope, "hinge_loss", [logits, labels]) as scope:
    logits.get_shape().assert_is_compatible_with(labels.get_shape())
    # We first need to convert binary labels to -1/1 labels (as floats).
    labels = math_ops.to_float(labels)
    all_ones = array_ops.ones_like(labels)
    labels = math_ops.subtract(2 * labels, all_ones)
    return nn_ops.relu(
        math_ops.subtract(all_ones, math_ops.multiply(labels, logits)))

def testVars(self):
    metrics.streaming_pearson_correlation(
        predictions=math_ops.to_float(math_ops.range(10)) + array_ops.ones(
            [10, 10]),
        labels=math_ops.to_float(math_ops.range(10)) + array_ops.ones([10, 10]))
    _assert_local_variables(self, (
        'pearson_r/covariance/comoment:0',
        'pearson_r/covariance/count:0',
        'pearson_r/covariance/mean_label:0',
        'pearson_r/covariance/mean_prediction:0',
        'pearson_r/variance_labels/count:0',
        'pearson_r/variance_labels/comoment:0',
        'pearson_r/variance_labels/mean_label:0',
        'pearson_r/variance_labels/mean_prediction:0',
        'pearson_r/variance_predictions/comoment:0',
        'pearson_r/variance_predictions/count:0',
        'pearson_r/variance_predictions/mean_label:0',
        'pearson_r/variance_predictions/mean_prediction:0',))

def _covariance(x, diag):
  """Defines the covariance operation of a matrix.

  Args:
    x: a matrix Tensor. Dimension 0 should contain the number of examples.
    diag: if True, it computes the diagonal covariance.

  Returns:
    A Tensor representing the covariance of x. In the case of
  diagonal matrix just the diagonal is returned.
  """
  num_points = math_ops.to_float(array_ops.shape(x)[0])
  x -= math_ops.reduce_mean(x, 0, keep_dims=True)
  if diag:
    cov = math_ops.reduce_sum(
        math_ops.square(x), 0, keep_dims=True) / (num_points - 1)
  else:
    cov = math_ops.matmul(x, x, transpose_a=True) / (num_points - 1)
  return cov

def _define_diag_covariance_probs(self, shard_id, shard):
    """Defines the diagonal covariance probabilities per example in a class.

    Args:
      shard_id: id of the current shard.
      shard: current data shard, 1 X num_examples X dimensions.

    Returns a matrix num_examples * num_classes.
    """
    # num_classes X 1
    # TODO(xavigonzalvo): look into alternatives to log for
    # reparametrization of variance parameters.
    det_expanded = math_ops.reduce_sum(
        math_ops.log(self._covs + 1e-3), 1, keep_dims=True)
    diff = shard - self._means
    x2 = math_ops.square(diff)
    cov_expanded = array_ops.expand_dims(1.0 / (self._covs + 1e-3), 2)
    # num_classes X num_examples
    x2_cov = math_ops.matmul(x2, cov_expanded)
    x2_cov = array_ops.transpose(array_ops.squeeze(x2_cov, [2]))
    self._probs[shard_id] = -0.5 * (
        math_ops.to_float(self._dimensions) * math_ops.log(2.0 * np.pi) +
        array_ops.transpose(det_expanded) + x2_cov)

def compute_weighted_loss(losses, weight=1.0):
  """Computes the weighted loss.

  Args:
    losses: A tensor of size [batch_size, d1, ... dN].
    weight: A tensor of size [1] or [batch_size, d1, ... dK] where K < N.

  Returns:
    A scalar `Tensor` that returns the weighted loss.

  Raises:
    ValueError: If the weight is None or the shape is not compatible with the
      losses shape or if the number of dimensions (rank) of either losses or
      weight is missing.
  """
  if weight is None:
    raise ValueError("`weight` cannot be None")
  input_dtype = losses.dtype
  losses = math_ops.to_float(losses)
  weight = math_ops.to_float(ops.convert_to_tensor(weight))

  if losses.get_shape().ndims is None:
    raise ValueError("losses.get_shape().ndims cannot be None")
  if weight.get_shape().ndims is None:
    raise ValueError("weight.get_shape().ndims cannot be None")

  total_loss = _scale_losses(losses, weight)
  num_present = _num_present(losses, weight)
  mean_loss = _safe_mean(total_loss, num_present)
  # convert the result back to the input type
  mean_loss = math_ops.cast(mean_loss, input_dtype)
  add_loss(mean_loss)
  return mean_loss

def absolute_difference(predictions, targets, weight=1.0, scope=None):
  """Adds an Absolute Difference loss to the training procedure.

  `weight` acts as a coefficient for the loss. If a scalar is provided, then the
  loss is simply scaled by the given value. If `weight` is a tensor of size
  [batch_size], then the total loss for each sample of the batch is rescaled
  by the corresponding element in the `weight` vector. If the shape of
  `weight` matches the shape of `predictions`, then the loss of each
  measurable element of `predictions` is scaled by the corresponding value of
  `weight`.

  Args:
    predictions: The predicted outputs.
    targets: The ground truth output tensor, same dimensions as 'predictions'.
    weight: Coefficients for the loss a scalar, a tensor of shape
      [batch_size] or a tensor whose shape matches `predictions`.
    scope: The scope for the operations performed in computing the loss.

  Returns:
    A scalar `Tensor` representing the loss value.

  Raises:
    ValueError: If the shape of `predictions` doesn't match that of `targets` or
      if the shape of `weight` is invalid.
  """
  with ops.name_scope(scope, "absolute_difference",
                      [predictions, targets]) as scope:
    predictions.get_shape().assert_is_compatible_with(targets.get_shape())
    if weight is None:
      raise ValueError("`weight` cannot be None")
    predictions = math_ops.to_float(predictions)
    targets = math_ops.to_float(targets)
    losses = math_ops.abs(math_ops.sub(predictions, targets))
    return compute_weighted_loss(losses, weight)

def log_loss(predictions, targets, weight=1.0, epsilon=1e-7, scope=None):
  """Adds a Log Loss term to the training procedure.

  `weight` acts as a coefficient for the loss. If a scalar is provided, then the
  loss is simply scaled by the given value. If `weight` is a tensor of size
  [batch_size], then the total loss for each sample of the batch is rescaled
  by the corresponding element in the `weight` vector. If the shape of
  `weight` matches the shape of `predictions`, then the loss of each
  measurable element of `predictions` is scaled by the corresponding value of
  `weight`.

  Args:
    predictions: The predicted outputs.
    targets: The ground truth output tensor, same dimensions as 'predictions'.
    weight: Coefficients for the loss a scalar, a tensor of shape
      [batch_size] or a tensor whose shape matches `predictions`.
    epsilon: A small increment to add to avoid taking a log of zero.
    scope: The scope for the operations performed in computing the loss.

  Returns:
    A scalar `Tensor` representing the loss value.

  Raises:
    ValueError: If the shape of `predictions` doesn't match that of `targets` or
      if the shape of `weight` is invalid.
  """
  with ops.name_scope(scope, "log_loss",
                      [predictions, targets]) as scope:
    predictions.get_shape().assert_is_compatible_with(targets.get_shape())
    if weight is None:
      raise ValueError("`weight` cannot be None")
    predictions = math_ops.to_float(predictions)
    targets = math_ops.to_float(targets)
    losses = -math_ops.mul(
        targets,
        math_ops.log(predictions + epsilon)) - math_ops.mul(
            (1 - targets), math_ops.log(1 - predictions + epsilon))
    return compute_weighted_loss(losses, weight)

def sum_of_squares(predictions, targets, weight=1.0, scope=None):
  """Adds a Sum-of-Squares loss to the training procedure.

  `weight` acts as a coefficient for the loss. If a scalar is provided, then the
  loss is simply scaled by the given value. If `weight` is a tensor of size
  [batch_size], then the total loss for each sample of the batch is rescaled
  by the corresponding element in the `weight` vector. If the shape of
  `weight` matches the shape of `predictions`, then the loss of each
  measurable element of `predictions` is scaled by the corresponding value of
  `weight`.

  Args:
    predictions: The predicted outputs.
    targets: The ground truth output tensor, same dimensions as 'predictions'.
    weight: Coefficients for the loss a scalar, a tensor of shape
      [batch_size] or a tensor whose shape matches `predictions`.
    scope: The scope for the operations performed in computing the loss.

  Returns:
    A scalar `Tensor` representing the loss value.

  Raises:
    ValueError: If the shape of `predictions` doesn't match that of `targets` or
      if the shape of `weight` is invalid.
  """
  with ops.name_scope(scope, "sum_of_squares_loss",
                      [predictions, targets]) as scope:
    predictions.get_shape().assert_is_compatible_with(targets.get_shape())
    if weight is None:
      raise ValueError("`weight` cannot be None")
    predictions = math_ops.to_float(predictions)
    targets = math_ops.to_float(targets)
    losses = math_ops.square(math_ops.sub(predictions, targets))
    return compute_weighted_loss(losses, weight)

def cosine_distance(predictions, targets, dim, weight=1.0, scope=None):
  """Adds a cosine-distance loss to the training procedure.

  Note that the function assumes that the predictions and targets are already
  unit-normalized.

  Args:
    predictions: An arbitrary matrix.
    targets: A `Tensor` whose shape matches 'predictions'
    dim: The dimension along which the cosine distance is computed.
    weight: Coefficients for the loss a scalar, a tensor of shape
      [batch_size] or a tensor whose shape matches `predictions`.
    scope: The scope for the operations performed in computing the loss.

  Returns:
    A scalar `Tensor` representing the loss value.

  Raises:
    ValueError: If predictions.shape doesn't match targets.shape, if the ignore
                mask is provided and its shape doesn't match targets.shape or if
                the ignore mask is not boolean valued.
  """
  with ops.name_scope(scope, "cosine_distance_loss",
                      [predictions, targets]) as scope:
    predictions.get_shape().assert_is_compatible_with(targets.get_shape())
    if weight is None:
      raise ValueError("`weight` cannot be None")

    predictions = math_ops.to_float(predictions)
    targets = math_ops.to_float(targets)

    radial_diffs = math_ops.mul(predictions, targets)
    losses = 1 - math_ops.reduce_sum(radial_diffs, reduction_indices=[dim,])
    return compute_weighted_loss(losses, weight)

def _get_weight_tensor(features, weight_column_name):
  """Returns the weight tensor of shape [batch_size] or 1."""
  if weight_column_name is None:
    return 1.0
  else:
    return array_ops.reshape(
        math_ops.to_float(features[weight_column_name]),
        shape=(-1,))

def _make_streaming_with_threshold(streaming_metrics_fn, threshold):

  def _streaming_metrics(predictions, targets):
    return streaming_metrics_fn(predictions=math_ops.to_float(
        math_ops.greater_equal(predictions, threshold)),
                                labels=targets)

  return _streaming_metrics

def _wrap_metric(metric):
  """Wraps metrics for mismatched prediction/target types."""
  def wrapped(preds, targets):
    targets = math_ops.cast(targets, preds.dtype)
    return metric(preds, targets)

  def wrapped_weights(preds, targets, weights=None):
    targets = math_ops.cast(targets, preds.dtype)
    if weights is not None:
      weights = array_ops.reshape(math_ops.to_float(weights), shape=(-1,))
    return metric(preds, targets, weights)

  return wrapped_weights if "weights" in _get_metric_args(metric) else wrapped

def _weighted_loss(loss, weight_tensor):
  unweighted_loss = array_ops.reshape(loss, shape=(-1,))
  weighted_loss = math_ops.mul(
      unweighted_loss, array_ops.reshape(weight_tensor, shape=(-1,)))
  return math_ops.div(
      math_ops.reduce_sum(weighted_loss),
      math_ops.to_float(math_ops.reduce_sum(weight_tensor)),
      name="loss")

def get_weight_tensor(self, features):
    if not self._weight_column_name:
      return None
    else:
      return array_ops.reshape(
          math_ops.to_float(features[self._weight_column_name]),
          shape=(-1,))

def loss(self, logits, target, features):
    """Returns loss tensor for this head.

    The loss returned is the weighted average.

      L = sum_{i} w_{i} * l_{i} / sum_{i} w_{i}

    Args:
      logits: logits, a float tensor.
      target: either a tensor for labels or in multihead case, a dict of string
        to target tensor.
      features: features dict.

    Returns:
      Loss tensor.
    """
    target = target[self.name] if isinstance(target, dict) else target
    loss_unweighted = self._loss_fn(logits, target)

    weight_tensor = self.get_weight_tensor(features)
    if weight_tensor is None:
      return math_ops.reduce_mean(loss_unweighted, name="loss")
    loss_weighted = self._weighted_loss(loss_unweighted, weight_tensor)
    return math_ops.div(
        math_ops.reduce_sum(loss_weighted),
        math_ops.to_float(math_ops.reduce_sum(weight_tensor)),
        name="loss")

def _mean_squared_loss(logits, target):
  # To prevent broadcasting inside "-".
  if len(target.get_shape()) == 1:
    target = array_ops.expand_dims(target, dim=[1])

  logits.get_shape().assert_is_compatible_with(target.get_shape())
  return math_ops.square(logits - math_ops.to_float(target))

def _float_weights_or_none(weights):
  if weights is None:
    return None
  return math_ops.to_float(weights)

def _accuracy_at_threshold(threshold):

  def _accuracy_metric(predictions, targets, weights=None):
    threshold_predictions = math_ops.to_float(
        math_ops.greater_equal(predictions, threshold))
    return metrics_lib.streaming_accuracy(predictions=threshold_predictions,
                                          labels=targets,
                                          weights=weights)

  return _accuracy_metric

def _count_condition(values, weights=None, metrics_collections=None,
                     updates_collections=None):
  """Sums the weights of cases where the given values are True.

  If `weights` is `None`, weights default to 1. Use weights of 0 to mask values.

  Args:
    values: A `bool` `Tensor` of arbitrary size.
    weights: An optional `Tensor` whose shape is broadcastable to `values`.
    metrics_collections: An optional list of collections that the metric
      value variable should be added to.
    updates_collections: An optional list of collections that the metric update
      ops should be added to.

  Returns:
    value_tensor: A tensor representing the current value of the metric.
    update_op: An operation that accumulates the error from a batch of data.

  Raises:
    ValueError: If `weights` is not `None` and its shape doesn't match `values`,
      or if either `metrics_collections` or `updates_collections` are not a list
      or tuple.
  """
  check_ops.assert_type(values, dtypes.bool)
  count = _create_local('count', shape=[])

  values = math_ops.to_float(values)
  if weights is not None:
    weights = math_ops.to_float(weights)
    values = math_ops.mul(values, weights)

  value_tensor = array_ops.identity(count)
  update_op = state_ops.assign_add(count, math_ops.reduce_sum(values))

  if metrics_collections:
    ops.add_to_collections(metrics_collections, value_tensor)

  if updates_collections:
    ops.add_to_collections(updates_collections, update_op)

  return value_tensor, update_op

def compute_weighted_loss(
    losses, weights=_WEIGHT_SENTINEL, weight=_WEIGHT_SENTINEL):
  """Computes the weighted loss.

  Args:
    losses: A tensor of size [batch_size, d1, ... dN].
    weights: A tensor of size [1] or [batch_size, d1, ... dK] where K < N.
    weight: Deprecated alias for `weights`.

  Returns:
    A scalar `Tensor` that returns the weighted loss.

  Raises:
    ValueError: If `weights` is `None` or the shape is not compatible with
      `losses`, or if the number of dimensions (rank) of either `losses` or
      `weights` is missing.
  """
  weights = _weights(weights, weight)
  losses = ops.convert_to_tensor(losses)
  input_dtype = losses.dtype
  losses = math_ops.to_float(losses)
  weights = math_ops.to_float(ops.convert_to_tensor(weights))

  if losses.get_shape().ndims is None:
    raise ValueError("losses.get_shape().ndims cannot be None")
  weights_shape = weights.get_shape()
  if weights_shape.ndims is None:
    raise ValueError("weight.get_shape().ndims cannot be None")

  if weights_shape.ndims > 1 and weights_shape.dims[-1].is_compatible_with(1):
    weights = array_ops.squeeze(weights, [-1])

  total_loss = _scale_losses(losses, weights)
  num_present = _num_present(losses, weights)
  mean_loss = _safe_mean(total_loss, num_present)
  # convert the result back to the input type
  mean_loss = math_ops.cast(mean_loss, input_dtype)
  add_loss(mean_loss)
  return mean_loss