Stay organized with collections Save and categorize content based on your preferences.

View source on GitHub

A tf.contrib.layers style linear prediction builder based on FeatureColumn.

Generally a single example in training data is described with feature columns. This function generates weighted sum for each num_outputs. Weighted sum refers to logits in classification problems. It refers to prediction itself for linear regression problems.


# Building model for training
feature_columns = (
columns_to_tensor =
logits = weighted_sum_from_feature_columns(
loss = tf.nn.sigmoid_cross_entropy_with_logits(labels=labels,

columns_to_tensors A mapping from feature column 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 by input pipeline. For example, inflow may have handled transformations.
feature_columns A set containing all the feature columns. All items in the set should be instances of classes derived from FeatureColumn.
num_outputs An integer specifying number of outputs. Default value is 1.
weight_collections List of graph collections to which weights are added.
trainable If True also add variables to the graph collection GraphKeys.TRAINABLE_VARIABLES (see tf.Variable).
scope Optional scope for variable_scope.

A tuple containing:

  • A Tensor which represents predictions of a linear model.
  • A dictionary which maps feature_column to corresponding Variable.
  • A Variable which is used for bias.

ValueError if FeatureColumn cannot be used for linear predictions.