W3cubDocs

/TensorFlow Python

tf.contrib.framework.load_embedding_initializer

load_embedding_initializer(
    ckpt_path,
    embedding_tensor_name,
    new_vocab_size,
    embedding_dim,
    old_vocab_file,
    new_vocab_file,
    num_oov_buckets=0,
    initializer=None,
    max_rows_in_memory=-1
)

Defined in tensorflow/python/training/checkpoint_ops.py.

Returns a variable initializer for loading pre-trained embeddings.

Wrapper around load_and_remap_matrix_initializer() specialized for loading embedding weights and remapping according to the provided vocab files. See docs for load_and_remap_matrix_initializer() for more details.

NOTE: Only for use with div-partitioned variables / vocabularies.

Args:

  • ckpt_path: Path to the TensorFlow checkpoint (version 2, TensorBundle) from which the old matrix Tensor will be loaded.
  • embedding_tensor_name: Name of the 2-D Tensor to load from checkpoint.
  • new_vocab_size: Number of entries in the new vocab.
  • embedding_dim: int specifying the dimension of the embedding vectors from the checkpoint. Must match the number of columns in the old embedding matrix.
  • old_vocab_file: A scalar Tensor of type string containing the path to the old vocabulary file.
  • new_vocab_file: A scalar Tensor of type string containing the path to the new vocabulary file.
  • num_oov_buckets: int specifying the number of out-of-vocabulary buckets to use. Must be >= 0.
  • initializer: Initializer function that accepts a 1-D tensor as the arg to specify the shape of the returned tensor. If None, defaults to using truncated_normal_initializer().
  • max_rows_in_memory: int specifying the maximum number of rows to load from the checkpoint at once. If less than or equal to 0, the entire matrix will be loaded into memory. Setting this arg trades increased disk reads for lower memory usage.

Returns:

A variable initializer function.

© 2017 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.
https://www.tensorflow.org/api_docs/python/tf/contrib/framework/load_embedding_initializer