tf.sparse.SparseTensor  |  TensorFlow v2.16.1 (original) (raw)

Represents a sparse tensor.

View aliases

Main aliases

tf.SparseTensor

Compat aliases for migration

SeeMigration guide for more details.

tf.compat.v1.SparseTensor, tf.compat.v1.sparse.SparseTensor

tf.sparse.SparseTensor(
    indices, values, dense_shape
)

Used in the notebooks

TensorFlow represents a sparse tensor as three separate dense tensors:indices, values, and dense_shape. In Python, the three tensors are collected into a SparseTensor class for ease of use. If you have separateindices, values, and dense_shape tensors, wrap them in a SparseTensorobject before passing to the ops below.

Concretely, the sparse tensor SparseTensor(indices, values, dense_shape)comprises the following components, where N and ndims are the number of values and number of dimensions in the SparseTensor, respectively:

• indices: A 2-D int64 tensor of shape [N, ndims], which specifies the indices of the elements in the sparse tensor that contain nonzero values (elements are zero-indexed). For example, indices=[[1,3], [2,4]] specifies that the elements with indexes of [1,3] and [2,4] have nonzero values.
• values: A 1-D tensor of any type and shape [N], which supplies the values for each element in indices. For example, given indices=[[1,3], [2,4]], the parameter values=[18, 3.6] specifies that element [1,3] of the sparse tensor has a value of 18, and element [2,4] of the tensor has a value of 3.6.
• dense_shape: A 1-D int64 tensor of shape [ndims], which specifies the dense_shape of the sparse tensor. Takes a list indicating the number of elements in each dimension. For example, dense_shape=[3,6] specifies a two-dimensional 3x6 tensor, dense_shape=[2,3,4] specifies a three-dimensional 2x3x4 tensor, and dense_shape=[9] specifies a one-dimensional tensor with 9 elements.

The corresponding dense tensor satisfies:

dense.shape = dense_shape
dense[tuple(indices[i])] = values[i]

By convention, indices should be sorted in row-major order (or equivalently lexicographic order on the tuples indices[i]). This is not enforced whenSparseTensor objects are constructed, but most ops assume correct ordering. If the ordering of sparse tensor st is wrong, a fixed version can be obtained by calling tf.sparse.reorder(st).

Example: The sparse tensor

SparseTensor(indices=[[0, 0], [1, 2]], values=[1, 2], dense_shape=[3, 4])

represents the dense tensor

[[1, 0, 0, 0]
 [0, 0, 2, 0]
 [0, 0, 0, 0]]

Methods

consumers

View source

consumers()

eval

View source

eval(
    feed_dict=None, session=None
)

Evaluates this sparse tensor in a Session.

Calling this method will execute all preceding operations that produce the inputs needed for the operation that produces this tensor.

from_value

View source

@classmethod from_value( sparse_tensor_value )

get_shape

View source

get_shape() -> tf.TensorShape

Get the TensorShape representing the shape of the dense tensor.

set_shape

View source

set_shape(
    shape
)

Updates the TensorShape representing the shape of the dense tensor.

With eager execution this operates as a shape assertion. Here the shapes match:

st = tf.SparseTensor( indices=[[0, 0], [1, 2]], values=[1, 2], dense_shape=[3, 4]) st.set_shape([3, 4])

Passing a None in the new shape allows any value for that axis:

st.set_shape([3, None])

An error is raised if an incompatible shape is passed.

st.set_shape([1, 4]) Traceback (most recent call last): `` ValueError: Tensor's shape (3, 4) is not compatible with supplied shape [1, 4]

When executing in a tf.function, or building a model usingtf.keras.Input, SparseTensor.set_shape will merge the given shapewith the current shape of this tensor, and set the tensor's shape to the merged value (see tf.TensorShape.merge_with for details):

st = tf.keras.Input(shape=[None, None, 3], sparse=True) print(st.shape) (None, None, None, 3)

Dimensions set to None are not updated:

st.set_shape([None, 224, 224, None]) print(st.shape) (None, 224, 224, 3)

The main use case for this is to provide additional shape information that cannot be inferred from the graph alone.

with_values

View source

with_values(
    new_values
)

Returns a copy of self with values replaced by new_values.

This method produces a new SparseTensor that has the same nonzeroindices and same dense_shape, but updated values.

Example usage:

st = tf.sparse.from_dense([[1, 0, 2, 0], [3, 0, 0, 4]]) tf.sparse.to_dense(st.with_values([10, 20, 30, 40])) # 4 nonzero values <tf.Tensor: shape=(2, 4), dtype=int32, numpy= array([[10, 0, 20, 0], [30, 0, 0, 40]], dtype=int32)>

__div__

View source

__div__(
    y
)

Component-wise divides a SparseTensor by a dense Tensor.

Limitation: this Op only broadcasts the dense side to the sparse side, but not the other direction.

__mul__

View source

__mul__(
    y
)

Component-wise multiplies a SparseTensor by a dense Tensor.

The output locations corresponding to the implicitly zero elements in the sparse tensor will be zero (i.e., will not take up storage space), regardless of the contents of the dense tensor (even if it's +/-INF and that INF*0 == NaN).

Limitation: this Op only broadcasts the dense side to the sparse side, but not the other direction.

__truediv__

View source

__truediv__(
    y
)

Internal helper function for 'sp_t / dense_t'.