LostTech.TensorFlow : API Documentation

String to Id table wrapper that assigns out-of-vocabulary keys to buckets.

For example, if an instance of `StaticVocabularyTable` is initialized with a string-to-id initializer that maps:

* `emerson -> 0` * `lake -> 1` * `palmer -> 2`

The `Vocabulary` object will performs the following mapping:

* `emerson -> 0` * `lake -> 1` * `palmer -> 2` * ` -> bucket_id`, where bucket_id will be between `3` and `3 + num_oov_buckets - 1`, calculated by: `hash() % num_oov_buckets + vocab_size`

If input_tensor is `["emerson", "lake", "palmer", "king", "crimson"]`, the lookup result is `[0, 1, 2, 4, 7]`.

If `initializer` is None, only out-of-vocabulary buckets are used.

Example usage: The hash function used for generating out-of-vocabulary buckets ID is Fingerprint64.

Show Example

num_oov_buckets = 3
            input_tensor = tf.constant(["emerson", "lake", "palmer", "king", "crimnson"])
            table = tf.lookup.StaticVocabularyTable(
                tf.TextFileIdTableInitializer(filename), num_oov_buckets)
            out = table.lookup(input_tensor).
            table.init.run()
            print(out.eval())