TensorFlow-Models/syntaxnet/g3doc/dragnn_ops/bulk_fixed_embeddings.md

dragnn_ops.bulk_fixed_embeddings(handle, embedding_matrix, component=None, pad_to_batch=None, pad_to_steps=None, name=None)

dragnn_ops.bulk_fixed_embeddings(handle, embedding_matrix, component=None, pad_to_batch=None, pad_to_steps=None, name=None)

Defined in tensorflow/dragnn/core/ops/gen_dragnn_bulk_ops.py.

This op is a more efficient version of BulkFixedFeatures to be run with large

batch sizes at inference time. The op takes a handle to ComputeSession and embedding matrices as tensor inputs, and directly outputs concatenated embedding vectors.

Args:

• handle: A Tensor of type string. handle to ComputeSession. embedding_matrix (num_channels matrices of float): embedding matrices, each shaped as vocab_dim[channel] x embedding_dim[channel].
• embedding_matrix: A list of at least 1 Tensor objects of the same type. embedding matrices.
• component: An optional string. Defaults to "".
• pad_to_batch: An optional int. Defaults to -1.
• pad_to_steps: An optional int. Defaults to -1.
• name: A name for the operation (optional).

Returns:

A tuple of Tensor objects (output_handle, embedding_vectors, num_steps). * output_handle: A Tensor of type string. handle to the same ComputeSession after advancement. embedding_vectors (matrix of float): output concatenated embeddings, shaped as (batch * beam * token) x sum_channel(embedding_dim[channel]). num_steps (int32 scalar): batch was unrolled for these many steps. * embedding_vectors: A Tensor. Has the same type as embedding_matrix. * num_steps: A Tensor of type int32.