Python common_layers.weights_nonzero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_nonzero [as 别名]
def padded_accuracy_topk(predictions,
                         labels,
                         k,
                         weights_fn=common_layers.weights_nonzero):
  """Percentage of times that top-k predictions matches labels on non-0s."""
  with tf.variable_scope("padded_accuracy_topk", values=[predictions, labels]):
    padded_predictions, padded_labels = common_layers.pad_with_zeros(
        predictions, labels)
    weights = weights_fn(padded_labels)
    effective_k = tf.minimum(k,
                             common_layers.shape_list(padded_predictions)[-1])
    _, outputs = tf.nn.top_k(padded_predictions, k=effective_k)
    outputs = tf.to_int32(outputs)
    padded_labels = tf.to_int32(padded_labels)
    padded_labels = tf.expand_dims(padded_labels, axis=-1)
    padded_labels += tf.zeros_like(outputs)  # Pad to same shape.
    same = tf.to_float(tf.equal(outputs, padded_labels))
    same_topk = tf.reduce_sum(same, axis=-1)
    return same_topk, 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_nonzero [as 别名]
def set_precision(predictions, labels,
                  weights_fn=common_layers.weights_nonzero):
  """Precision of set predictions.

  Args:
    predictions : A Tensor of scores of shape [batch, nlabels].
    labels: A Tensor of int32s giving true set elements,
      of shape [batch, seq_length].
    weights_fn: A function to weight the elements.

  Returns:
    hits: A Tensor of shape [batch, nlabels].
    weights: A Tensor of shape [batch, nlabels].
  """
  with tf.variable_scope("set_precision", values=[predictions, labels]):
    labels = tf.squeeze(labels, [2, 3])
    weights = weights_fn(labels)
    labels = tf.one_hot(labels, predictions.shape[-1])
    labels = tf.reduce_max(labels, axis=1)
    labels = tf.cast(labels, tf.bool)
    return tf.to_float(tf.equal(labels, predictions)), 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_nonzero [as 别名]
def targets_weights_fn(self):
    weights_fn = common_layers.weights_nonzero

    hp = self._model_hparams
    if hp and hp.prepend_mode != "none":
      assert (hp.prepend_mode == "prepend_inputs_masked_attention" or
              hp.prepend_mode == "prepend_inputs_full_attention")

      if (
          # In masked attention mode, during training, the network try to
          # autoregressively predicting the inputs portion, while the
          # evaluation is only done on the output
          hp.prepend_mode != "prepend_inputs_masked_attention" or
          hp.mode != tf.estimator.ModeKeys.TRAIN):
        weights_fn = common_layers.weights_prepend_inputs_to_targets

    return 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_nonzero [as 别名]
def set_recall(predictions, labels, weights_fn=common_layers.weights_nonzero):
  """Recall of set predictions.

  Args:
    predictions : A Tensor of scores of shape [batch, nlabels].
    labels: A Tensor of int32s giving true set elements,
      of shape [batch, seq_length].
    weights_fn: A function to weight the elements.

  Returns:
    hits: A Tensor of shape [batch, nlabels].
    weights: A Tensor of shape [batch, nlabels].
  """
  with tf.variable_scope("set_recall", values=[predictions, labels]):
    labels = tf.squeeze(labels, [2, 3])
    weights = weights_fn(labels)
    labels = tf.one_hot(labels, predictions.shape[-1])
    labels = tf.reduce_max(labels, axis=1)
    labels = tf.cast(labels, tf.bool)
    return tf.to_float(tf.equal(labels, predictions)), 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_nonzero [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_nonzero [as 别名]
def padded_accuracy_top5(predictions,
                         labels,
                         weights_fn=common_layers.weights_nonzero):
  return padded_accuracy_topk(predictions, labels, 5, 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_nonzero [as 别名]
def rounding_sequence_accuracy(predictions,
                               labels,
                               weights_fn=common_layers.weights_nonzero):
  """Sequence accuracy for L1/L2 losses: round down the predictions to ints."""
  outputs = tf.squeeze(tf.to_int32(predictions), axis=-1)
  weights = weights_fn(labels)
  labels = tf.to_int32(labels)
  not_correct = tf.to_float(tf.not_equal(outputs, labels)) * weights
  axis = list(range(1, len(outputs.get_shape())))
  correct_seq = 1.0 - tf.minimum(1.0, tf.reduce_sum(not_correct, axis=axis))
  return correct_seq, tf.constant(1.0) 

# 需要导入模块: from tensor2tensor.layers import common_layers [as 别名]
# 或者: from tensor2tensor.layers.common_layers import weights_nonzero [as 别名]
def padded_sequence_accuracy(predictions,
                             labels,
                             weights_fn=common_layers.weights_nonzero):
  """Percentage of times that predictions matches labels everywhere (non-0)."""
  # If the last dimension is 1 then we're using L1/L2 loss.
  if common_layers.shape_list(predictions)[-1] == 1:
    return rounding_sequence_accuracy(
        predictions, labels, weights_fn=weights_fn)
  with tf.variable_scope(
      "padded_sequence_accuracy", values=[predictions, labels]):
    padded_predictions, padded_labels = common_layers.pad_with_zeros(
        predictions, labels)
    weights = weights_fn(padded_labels)

    # Flatten, keeping batch dim (and num_classes dim for predictions)
    # TPU argmax can only deal with a limited number of dimensions
    predictions_shape = common_layers.shape_list(padded_predictions)
    batch_size = predictions_shape[0]
    num_classes = predictions_shape[-1]
    flat_size = common_layers.list_product(
        common_layers.shape_list(padded_labels)[1:])
    padded_predictions = tf.reshape(
        padded_predictions,
        [batch_size, common_layers.list_product(predictions_shape[1:-1]),
         num_classes])
    padded_labels = tf.reshape(padded_labels, [batch_size, flat_size])
    weights = tf.reshape(weights, [batch_size, flat_size])

    outputs = tf.to_int32(tf.argmax(padded_predictions, axis=-1))
    padded_labels = tf.to_int32(padded_labels)
    not_correct = tf.to_float(tf.not_equal(outputs, padded_labels)) * weights
    axis = list(range(1, len(outputs.get_shape())))
    correct_seq = 1.0 - tf.minimum(1.0, tf.reduce_sum(not_correct, axis=axis))
    return correct_seq, tf.constant(1.0) 

# 需要导入模块: from tensor2tensor.layers import common_layers [as 别名]
# 或者: from tensor2tensor.layers.common_layers import weights_nonzero [as 别名]
def rounding_accuracy(predictions,
                      labels,
                      weights_fn=common_layers.weights_nonzero):
  """Rounding accuracy for L1/L2 losses: round down the predictions to ints."""
  outputs = tf.squeeze(tf.to_int32(predictions))
  labels = tf.squeeze(labels)
  weights = weights_fn(labels)
  labels = tf.to_int32(labels)
  return tf.to_float(tf.equal(outputs, labels)), 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_nonzero [as 别名]
def padded_accuracy(predictions,
                    labels,
                    weights_fn=common_layers.weights_nonzero):
  """Percentage of times that predictions matches labels on non-0s."""
  # If the last dimension is 1 then we're using L1/L2 loss.
  if common_layers.shape_list(predictions)[-1] == 1:
    return rounding_accuracy(predictions, labels, weights_fn=weights_fn)
  with tf.variable_scope("padded_accuracy", values=[predictions, labels]):
    padded_predictions, padded_labels = common_layers.pad_with_zeros(
        predictions, labels)
    weights = weights_fn(padded_labels)
    outputs = tf.to_int32(tf.argmax(padded_predictions, axis=-1))
    padded_labels = tf.to_int32(padded_labels)
    return tf.to_float(tf.equal(outputs, padded_labels)), 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_nonzero [as 别名]
def multilabel_accuracy_matchk(predictions,
                               labels,
                               k,
                               weights_fn=common_layers.weights_nonzero):
  """Used to evaluate the VQA accuracy.

  Let n be the times that predictions appear in labels, then final score
  is min(n/k, 1).
  Refer to https://arxiv.org/pdf/1505.00468.pdf.

  Args:
    predictions: A tensor with shape [batch_size, 1, 1, 1, vocab_size].
    labels: A tensor with shape [batch_size, length, 1, 1].
    k: A tensor constant.
    weights_fn: weight function.
  Returns:
    scores: min(n/k, 1).
    weights: returns all ones.

  """
  predictions = tf.to_int32(tf.argmax(predictions, axis=-1))
  scores = tf.to_float(tf.equal(predictions, labels))
  # those label == 0 do not count
  weights = weights_fn(labels)
  scores *= weights
  scores = tf.reduce_sum(scores, axis=[1, 2, 3])
  scores = tf.minimum(scores / tf.to_float(k), 1)
  # every sample count
  weights = tf.ones(tf.shape(scores), dtype=tf.float32)

  return scores, 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_nonzero [as 别名]
def multilabel_accuracy_match3(predictions, labels,
                               weights_fn=common_layers.weights_nonzero):
  return multilabel_accuracy_matchk(predictions, labels, 3, 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_nonzero [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_nonzero [as 别名]
def prefix_accuracy(predictions,
                    labels,
                    weights_fn=common_layers.weights_nonzero):
  """Average # of correct tokens at start of sequences, ignoring padding 0s.

  See section 4.3 of Learning to Transduce with Unbounded Memory,
  Grefenstette et al., 2015.

  Args:
    predictions: Tensor of shape [`batch_size`, `length`, 1, `num_classes`] and
        type tf.float32 representing the logits, 0-padded.
    labels: Tensor of shape [`batch_size`, `length`, 1, 1] and type tf.int32
        representing the labels of same length as logits and 0-padded.
    weights_fn: ignored. The weights returned are the total length of the ground
        truth labels, excluding 0-paddings.

  Returns:
    (prefix accuracy, 1.0)

  Raises:
    ValueError: if weights_fn is not common_layers.weights_nonzero.
  """
  if weights_fn is not common_layers.weights_nonzero:
    raise ValueError("Only weights_nonzero can be used for this metric.")

  predictions = tf.to_int32(tf.squeeze(tf.argmax(predictions, axis=-1), axis=2))
  labels = tf.squeeze(labels, axis=(2, 3))
  seq_len = tf.reduce_sum(
      tf.cast(tf.not_equal(labels, tf.constant(0)), dtype=tf.float32), axis=1)
  matching_elements = tf.equal(labels, predictions)
  prefix_len = tf.reduce_sum(
      tf.cumprod(tf.cast(matching_elements, tf.float32), axis=1), axis=1)
  return tf.reduce_mean(prefix_len / seq_len), tf.constant(1.0) 

# 需要导入模块: from tensor2tensor.layers import common_layers [as 别名]
# 或者: from tensor2tensor.layers.common_layers import weights_nonzero [as 别名]
def padded_neg_log_perplexity(predictions,
                              labels,
                              weights_fn=common_layers.weights_nonzero):
  """Average log-perplexity exluding padding 0s. No smoothing."""
  num, den = common_layers.padded_cross_entropy(
      predictions, labels, 0.0, weights_fn=weights_fn, reduce_sum=False)
  return (-num, den)