tf.sparse.to_dense

Converts a SparseTensor into a dense tensor.

View aliases

Compat aliases for migration

tf.compat.v1.sparse.to_dense, tf.compat.v1.sparse_tensor_to_dense

tf.sparse.to_dense(
    sp_input, default_value=None, validate_indices=True, name=None
)

Used in the notebooks

Used in the guide	Used in the tutorials
Working with sparse tensors Migrate `tf.feature_column`s to Keras preprocessing layers Ragged tensors Introduction to Tensors Introduction to tensor slicing	Graph-based Neural Structured Learning in TFX Text generation with an RNN TFX Estimator Component Tutorial TFX Keras Component Tutorial

For this sparse tensor with three non-empty values:

sp_input = tf.sparse.SparseTensor(
  dense_shape=[3, 5],
  values=[7, 8, 9],
  indices =[[0, 1],
            [0, 3],
            [2, 0]])

The output will be a dense [3, 5] tensor with values:

tf.sparse.to_dense(sp_input).numpy()
array([[0, 7, 0, 8, 0],
       [0, 0, 0, 0, 0],
       [9, 0, 0, 0, 0]], dtype=int32)

Args

sp_input The input SparseTensor. default_value Scalar value to set for indices not specified in sp_input. Defaults to zero. validate_indices A boolean value. If True, indices are checked to make sure they are sorted in lexicographic order and that there are no repeats. name A name prefix for the returned tensors (optional).

Returns

A dense tensor with shape sp_input.dense_shape and values specified by the non-empty values in sp_input. Indices not in sp_input are assigned default_value.

Raises

TypeError If sp_input is not a SparseTensor.

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates. Some content is licensed under the numpy license.

Last updated 2024-04-26 UTC.