Type IndexedSlices
Namespace tensorflow
Parent PythonObjectContainer
Interfaces _TensorLike, CompositeTensor, IIndexedSlices
A sparse representation of a set of tensor slices at given indices. This class is a simple wrapper for a pair of `Tensor` objects: * `values`: A `Tensor` of any dtype with shape `[D0, D1,..., Dn]`.
* `indices`: A 1-D integer `Tensor` with shape `[D0]`. An `IndexedSlices` is typically used to represent a subset of a larger
tensor `dense` of shape `[LARGE0, D1,.. , DN]` where `LARGE0 >> D0`.
The values in `indices` are the indices in the first dimension of
the slices that have been extracted from the larger tensor. The dense tensor `dense` represented by an `IndexedSlices` `slices` has
The `IndexedSlices` class is used principally in the definition of
gradients for operations that have sparse gradients
(e.g.
tf.gather). Contrast this representation with
tf.SparseTensor,
which uses multi-dimensional indices and scalar values.
Show Example
dense[slices.indices[i], :, :, :,...] = slices.values[i, :, :, :,...]
Methods
Properties
Public instance methods
object __neg__()
object __neg___dyn()
IList<object> consumers()
Returns a list of `Operation`s that consume this tensor.
Returns
-
IList<object> - A list of `Operation`s.
object consumers_dyn()
Returns a list of `Operation`s that consume this tensor.
Returns
-
object - A list of `Operation`s.
Public properties
object dense_shape get;
A 1-D `Tensor` containing the shape of the corresponding dense tensor.
object dense_shape_dyn get;
A 1-D `Tensor` containing the shape of the corresponding dense tensor.
object device get;
The name of the device on which `values` will be produced, or `None`.
object device_dyn get;
The name of the device on which `values` will be produced, or `None`.
object dtype get;
The `DType` of elements in this tensor.
object dtype_dyn get;
The `DType` of elements in this tensor.
object graph get;
The `Graph` that contains the values, indices, and shape tensors.
object graph_dyn get;
The `Graph` that contains the values, indices, and shape tensors.
object indices get;
A 1-D `Tensor` containing the indices of the slices.
object indices_dyn get;
A 1-D `Tensor` containing the indices of the slices.
object name get;
The name of this `IndexedSlices`.
object name_dyn get;
The name of this `IndexedSlices`.
object op get;
The `Operation` that produces `values` as an output.
object op_dyn get;
The `Operation` that produces `values` as an output.
object PythonObject get;
object values get;
A `Tensor` containing the values of the slices.
object values_dyn get;
A `Tensor` containing the values of the slices.