datatype = one of string, truefalse, integer[4], integer[8], float[4], float[8], complex[4], or complex[8]

Specifies the type of data this Tensor will hold. By default, the datatype is inferred from the initial data val.

name = string

Specifies an optional name for this Tensor to be displayed in output.

trainable = truefalse

Specifies whether GradientTapes should watch this Variable automatically. The default is true.

The Variable(val,opts) command creates a Tensor variable in the active dataflow graph with initial value given by val.

This function is part of the DeepLearning package, so it can be used in the short form Variable(..) only after executing the command with(DeepLearning). However, it can always be accessed through the long form of the command by using DeepLearning[Variable](..).

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

$V≔\mathrm{Variable}\left(\left[2.0\right]\,\mathrm{datatype}=\mathrm{float}\left[8\right]\right)$

$V≔\left[\begin{array}{c}\mathrm{DeepLearning\; Variable}\\ \mathrm{Name:\; Variable:0}\\ \mathrm{Shape:\; [1]}\\ \mathrm{Data\; Type:\; float[8]}\end{array}\right]$

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

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

The DeepLearning[Variable] command was updated in Maple 2022.

The trainable option was introduced in Maple 2022.

For more information on Maple 2022 changes, see Updates in Maple 2022.