Python common_layers.weights_all方法代码示例

# 需要导入模块: from tensor2tensor.layers import common_layers [as 别名]
# 或者: from tensor2tensor.layers.common_layers import weights_all [as 别名]
def create_eager_metrics(metric_names, weights_fn=common_layers.weights_all):
  """Create metrics accumulators and averager for Eager mode.

  Args:
    metric_names: list<str> from Metrics enum
    weights_fn: function that takes labels and returns a weights mask. Defaults
      to weights of all 1, i.e. common_layers.weights_all. Use
      common_layers.weights_nonzero if labels have 0-padding.

  Returns:
    (accum_fn(predictions, targets) => None,
     result_fn() => dict<str metric_name, float avg_val>
  """
  metric_fns = dict(
      [(name, METRICS_FNS[name]) for name in metric_names])
  return create_eager_metrics_internal(metric_fns, weights_fn) 

# 需要导入模块: from tensor2tensor.layers import common_layers [as 别名]
# 或者: from tensor2tensor.layers.common_layers import weights_all [as 别名]
def image_rmse(predictions, labels, weights_fn=common_layers.weights_all):
  """RMSE but will argmax if last dim is not 1."""
  if common_layers.shape_list(predictions)[-1] == 1:
    predictions = tf.squeeze(predictions, axis=[-1])
  else:
    predictions = tf.argmax(predictions, axis=-1)
  return padded_rmse(predictions, labels, weights_fn) 

# 需要导入模块: from tensor2tensor.layers import common_layers [as 别名]
# 或者: from tensor2tensor.layers.common_layers import weights_all [as 别名]
def padded_rmse(predictions, labels, weights_fn=common_layers.weights_all):
  predictions = tf.to_float(predictions)
  labels = tf.to_float(labels)
  predictions, labels = common_layers.pad_with_zeros(predictions, labels)
  weights = weights_fn(labels)
  error = tf.pow(predictions - labels, 2)
  error_sqrt = tf.sqrt(tf.reduce_sum(error * weights))
  return error_sqrt, tf.reduce_sum(weights) 

# 需要导入模块: from tensor2tensor.layers import common_layers [as 别名]
# 或者: from tensor2tensor.layers.common_layers import weights_all [as 别名]
def padded_log_poisson(predictions,
                       labels,
                       weights_fn=common_layers.weights_all):
  # Expects predictions to already be transformed into log space
  predictions, labels = common_layers.pad_with_zeros(predictions, labels)
  targets = labels
  weights = weights_fn(targets)

  lp_loss = tf.nn.log_poisson_loss(targets, predictions, compute_full_loss=True)
  return tf.reduce_sum(lp_loss * weights), tf.reduce_sum(weights) 

# 需要导入模块: from tensor2tensor.layers import common_layers [as 别名]
# 或者: from tensor2tensor.layers.common_layers import weights_all [as 别名]
def padded_variance_explained(predictions,
                              labels,
                              weights_fn=common_layers.weights_all):
  """Explained variance, also known as R^2."""
  predictions, labels = common_layers.pad_with_zeros(predictions, labels)
  targets = labels
  weights = weights_fn(targets)

  y_bar = tf.reduce_mean(weights * targets)
  tot_ss = tf.reduce_sum(weights * tf.pow(targets - y_bar, 2))
  res_ss = tf.reduce_sum(weights * tf.pow(targets - predictions, 2))
  r2 = 1. - res_ss / tot_ss
  return r2, tf.reduce_sum(weights) 

# 需要导入模块: from tensor2tensor.layers import common_layers [as 别名]
# 或者: from tensor2tensor.layers.common_layers import weights_all [as 别名]
def create_eager_metrics(metric_names, weights_fn=common_layers.weights_all):
  """Create metrics accumulators and averager for Eager mode.

  Args:
    metric_names: list<str> from Metrics enum
    weights_fn: function that takes labels and returns a weights mask. Defaults
      to weights of all 1, i.e. common_layers.weights_all. Use
      common_layers.weights_nonzero if labels have 0-padding.

  Returns:
    (accum_fn(predictions, targets) => None,
     result_fn() => dict<str metric_name, float avg_val>
  """
  metric_fns = dict(
      [(name, METRICS_FNS[name]) for name in metric_names])
  tfe_metrics = dict()

  for name in metric_names:
    tfe_metrics[name] = tfe.metrics.Mean(name=name)

  def metric_accum(predictions, targets):
    for name, metric_fn in metric_fns.items():
      val, weight = metric_fn(predictions, targets,
                              weights_fn=weights_fn)
      tfe_metrics[name](np.squeeze(val), np.squeeze(weight))

  def metric_means():
    avgs = {}
    for name in metric_names:
      avgs[name] = tfe_metrics[name].result().numpy()
    return avgs

  return metric_accum, metric_means


# Metrics are functions that take predictions and labels and return
# a tensor of metrics and a tensor of weights.
# If the function has "features" as an argument, it will receive the whole
# features dict as well.
# The results are passed to tf.metrics.mean to accumulate properly. 

# 需要导入模块: from tensor2tensor.layers import common_layers [as 别名]
# 或者: from tensor2tensor.layers.common_layers import weights_all [as 别名]
def padded_rmse(predictions, labels, weights_fn=common_layers.weights_all):
  predictions = tf.to_float(predictions)
  labels = tf.to_float(labels)
  predictions, labels = common_layers.pad_with_zeros(predictions, labels)
  weights = weights_fn(labels)
  error = tf.pow(predictions - labels, 2)
  error_sqrt = tf.sqrt(tf.reduce_mean(error * weights))
  return error_sqrt, tf.reduce_sum(weights) 

# 需要导入模块: from tensor2tensor.layers import common_layers [as 别名]
# 或者: from tensor2tensor.layers.common_layers import weights_all [as 别名]
def unpadded_mse(predictions, labels, weights_fn=common_layers.weights_all):
  predictions = tf.to_float(predictions)
  labels = tf.to_float(labels)
  weights = weights_fn(labels)
  error = tf.pow(predictions - labels, 2)
  mean_error = tf.reduce_mean(error * weights)
  return mean_error, tf.reduce_sum(weights) 

# 需要导入模块: from tensor2tensor.layers import common_layers [as 别名]
# 或者: from tensor2tensor.layers.common_layers import weights_all [as 别名]
def create_eager_metrics_internal(metric_fns,
                                  weights_fn=common_layers.weights_all):
  """Create metrics accumulators and averager for Eager mode.

  Args:
    metric_fns: dict<metric name, metric function>
    weights_fn: function that takes labels and returns a weights mask. Defaults
      to weights of all 1, i.e. common_layers.weights_all. Use
      common_layers.weights_nonzero if labels have 0-padding.

  Returns:
    (accum_fn(predictions, targets) => None,
     result_fn() => dict<str metric_name, float avg_val>
  """

  from tensorflow.contrib.eager.python import tfe  # pylint: disable=g-import-not-at-top

  tfe_metrics = {}

  for name in metric_fns:
    tfe_metrics[name] = tfe.metrics.Mean(name=name)

  def metric_accum(predictions, targets):
    for name, metric_fn in metric_fns.items():
      val, weight = metric_fn(predictions, targets,
                              weights_fn=weights_fn)
      tfe_metrics[name](np.squeeze(val), np.squeeze(weight))

  def metric_means():
    avgs = {}
    for name in metric_fns:
      avgs[name] = tfe_metrics[name].result().numpy()
    return avgs

  return metric_accum, metric_means 

# 需要导入模块: from tensor2tensor.layers import common_layers [as 别名]
# 或者: from tensor2tensor.layers.common_layers import weights_all [as 别名]
def get_weights_fn(modality_type, value=None):
  """Gets default weights function; if none available, return value."""
  if modality_type in (ModalityType.CTC_SYMBOL,
                       ModalityType.IDENTITY_SYMBOL,
                       ModalityType.MULTI_LABEL,
                       ModalityType.SYMBOL,
                       ModalityType.SYMBOL_ONE_HOT):
    return common_layers.weights_nonzero
  elif modality_type in ModalityType.get_choices():
    return common_layers.weights_all
  return value 

# 需要导入模块: from tensor2tensor.layers import common_layers [as 别名]
# 或者: from tensor2tensor.layers.common_layers import weights_all [as 别名]
def create_eager_metrics(metric_names, weights_fn=common_layers.weights_all):
  """Create metrics accumulators and averager for Eager mode.

  Args:
    metric_names: list<str> from Metrics enum
    weights_fn: function that takes labels and returns a weights mask. Defaults
      to weights of all 1, i.e. common_layers.weights_all. Use
      common_layers.weights_nonzero if labels have 0-padding.

  Returns:
    (accum_fn(predictions, targets) => None,
     result_fn() => dict<str metric_name, float avg_val>
  """
  metric_fns = dict(
      [(name, METRICS_FNS[name]) for name in metric_names])
  tfe_metrics = dict()

  for name in metric_names:
    tfe_metrics[name] = tfe.metrics.Mean(name=name)

  def metric_accum(predictions, targets):
    for name, metric_fn in metric_fns.items():
      val, weight = metric_fn(predictions, targets,
                              weights_fn=weights_fn)
      tfe_metrics[name](np.squeeze(val), np.squeeze(weight))

  def metric_means():
    avgs = {}
    for name in metric_names:
      avgs[name] = tfe_metrics[name].result().numpy()
    return avgs

  return metric_accum, metric_means 

# 需要导入模块: from tensor2tensor.layers import common_layers [as 别名]
# 或者: from tensor2tensor.layers.common_layers import weights_all [as 别名]
def loss(self, logits, features):
    # logits should be dict with 'outputs', which is image.
    targets = tf.reshape(features['targets'], [-1, 64, 64, 1])
    weights = common_layers.weights_all(targets)
    loss_num = tf.pow(logits - targets, 2)
    return tf.reduce_sum(loss_num * weights), tf.reduce_sum(weights)