Python multi_class_head Examples

Example #1

File: random_forest.py Project: AnishShah/tensorflow

def _get_default_head(params, weights_name, output_type, name=None):
  """Creates a default head based on a type of a problem."""
  if output_type == ModelBuilderOutputType.MODEL_FN_OPS:
    if params.regression:
      return head_lib.regression_head(
          weight_column_name=weights_name,
          label_dimension=params.num_outputs,
          enable_centered_bias=False,
          head_name=name)
    else:
      return head_lib.multi_class_head(
          params.num_classes,
          weight_column_name=weights_name,
          enable_centered_bias=False,
          head_name=name)
  else:
    if params.regression:
      return core_head_lib.regression_head(
          weight_column=weights_name,
          label_dimension=params.num_outputs,
          name=name,
          loss_reduction=losses.Reduction.SUM_OVER_BATCH_SIZE)
    else:
      if params.num_classes == 2:
        return core_head_lib.binary_classification_head(
            weight_column=weights_name,
            name=name,
            loss_reduction=losses.Reduction.SUM_OVER_BATCH_SIZE)
      else:
        return core_head_lib.multi_class_head(
            n_classes=params.num_classes,
            weight_column=weights_name,
            name=name,
            loss_reduction=losses.Reduction.SUM_OVER_BATCH_SIZE)

Example #2

File: random_forest.py Project: dsadulla/tensorflow

def _get_default_head(params, weights_name, output_type, name=None):
    """Creates a default head based on a type of a problem."""
    if output_type == ModelBuilderOutputType.MODEL_FN_OPS:
        if params.regression:
            return head_lib.regression_head(weight_column_name=weights_name,
                                            label_dimension=params.num_outputs,
                                            enable_centered_bias=False,
                                            head_name=name)
        else:
            return head_lib.multi_class_head(params.num_classes,
                                             weight_column_name=weights_name,
                                             enable_centered_bias=False,
                                             head_name=name)
    else:
        if params.regression:
            return core_head_lib.regression_head(
                weight_column=weights_name,
                label_dimension=params.num_outputs,
                name=name,
                loss_reduction=losses.Reduction.SUM_OVER_BATCH_SIZE)
        else:
            if params.num_classes == 2:
                return core_head_lib.binary_classification_head(
                    weight_column=weights_name,
                    name=name,
                    loss_reduction=losses.Reduction.SUM_OVER_BATCH_SIZE)
            else:
                return core_head_lib.multi_class_head(
                    n_classes=params.num_classes,
                    weight_column=weights_name,
                    name=name,
                    loss_reduction=losses.Reduction.SUM_OVER_BATCH_SIZE)

Example #3

File: rnn_test.py Project: ThunderQi/tensorflow

def _rnn_estimator_fn(feature_columns, n_classes, cell_units, model_dir):
  return rnn.RNNEstimator(
      head=head_lib.multi_class_head(n_classes=n_classes),
      num_units=cell_units,
      sequence_feature_columns=feature_columns,
      model_dir=model_dir)

Example #4

File: rnn_test.py Project: ShubhamSrivastava93/shubham-tensorflow

def _rnn_estimator_fn(feature_columns, n_classes, cell_units, model_dir):
  return rnn.RNNEstimator(
      head=head_lib.multi_class_head(n_classes=n_classes),
      num_units=cell_units,
      sequence_feature_columns=feature_columns,
      model_dir=model_dir)

Example #5

File: dnn_test.py Project: AnishShah/tensorflow

def _dnn_estimator_classifier_fn(n_classes=3, *args, **kwargs):  # pylint: disable=keyword-arg-before-vararg
  """Returns a DNNEstimator that uses multi_class_head."""
  return dnn.DNNEstimator(head=head_lib.multi_class_head(n_classes=n_classes),
                          *args, **kwargs)

Example #6

File: dnn_test.py Project: kuo1220/verbose-barnacle

def _dnn_estimator_classifier_fn(n_classes=3, *args, **kwargs):  # pylint: disable=keyword-arg-before-vararg
    """Returns a DNNEstimator that uses multi_class_head."""
    return dnn.DNNEstimator(
        head=head_lib.multi_class_head(n_classes=n_classes), *args, **kwargs)