TensorFlow

API

 tf.experimental / Overview


Public API for tf.feature_column namespace.

Functions

bucketized_column(...): Represents discretized dense input bucketed by boundaries.

categorical_column_with_hash_bucket(...): Represents sparse feature where ids are set by hashing.

categorical_column_with_identity(...): A CategoricalColumn that returns identity values.

categorical_column_with_vocabulary_file(...): A CategoricalColumn with a vocabulary file.

categorical_column_with_vocabulary_list(...): A CategoricalColumn with in-memory vocabulary.

crossed_column(...): Returns a column for performing crosses of categorical features.

embedding_column(...): DenseColumn that converts from sparse, categorical input.

indicator_column(...): Represents multi-hot representation of given categorical column.

make_parse_example_spec(...): Creates parsing spec dictionary from input feature_columns.

numeric_column(...): Represents real valued or numerical features.

sequence_categorical_column_with_hash_bucket(...): A sequence of categorical terms where ids are set by hashing.

sequence_categorical_column_with_identity(...): Returns a feature column that represents sequences of integers.

sequence_categorical_column_with_vocabulary_file(...): A sequence of categorical terms where ids use a vocabulary file.

sequence_categorical_column_with_vocabulary_list(...): A sequence of categorical terms where ids use an in-memory list.

sequence_numeric_column(...): Returns a feature column that represents sequences of numeric data.

shared_embeddings(...): List of dense columns that convert from sparse, categorical input.

weighted_categorical_column(...): Applies weight values to a CategoricalColumn.


此页内容是否对您有帮助