A Tensor is an object representing a node in a DataflowGraph.

A Tensor corresponds to a partially-defined computation which, when executed in a Session, produces a concrete instance of multidimensional data.

By performing mathematical or other operations with Tensors, you are implicitly creating additional Tensors and extending the computation graph.

All Tensors have a datatype and a shape. The datatype is always known. The shape may be either fully or partially specified when the Tensor is created.

The following commands query properties of a Tensor.

The following functions operate elementwise on a Tensor.

The following functions operate on Tensors as matrices.

$\mathrm{with}\left(\mathrm{DeepLearning}\right)\:$

$V≔\mathrm{Variable}\left(\left[1.5\,7.2\,2.3\right]\,\mathrm{datatype}=\mathrm{float}\left[8\right]\right)$

$V≔\left[\begin{array}{c}\mathrm{DeepLearning\; Tensor}\\ \mathrm{Name:\; Variable:0}\\ \mathrm{Shape:\; undefined}\\ \mathrm{Data\; Type:\; float[8]}\end{array}\right]$

$P≔\mathrm{Placeholder}\left(\mathrm{float}\left[4\right]\,\left[3\,2\right]\right)$

$C≔\mathrm{Constant}\left(⟨⟨0.4\,0.7⟩|⟨0.7\,-0.3⟩⟩\right)$

$C≔\left[\begin{array}{c}\mathrm{DeepLearning\; Tensor}\\ \mathrm{Name:\; none}\\ \mathrm{Shape:\; undefined}\\ \mathrm{Data\; Type:\; float[8]}\end{array}\right]$

The DeepLearning[Tensor] command was introduced in Maple 2018.

For more information on Maple 2018 changes, see Updates in Maple 2018.