The Restore(path) command loads a saved computation session to memory from a checkpoint file located at path.

The Save(path) command saves a computation session in memory to a checkpoint file located at path.

These functions are part of the DeepLearning package, so they can be used in the short form Restore(..) and Save(..) only after executing the command with(DeepLearning). However, they can always be accessed through the long form of the command by using DeepLearning[Restore](..) or DeepLearning[Save](..).

For more information about saving models, see the TensorFlow Python API documentation for saved models.

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

$v≔\mathrm{Variable}\left(\left[1.0\,0.5\right]\,\mathrm{datatype}=\mathrm{float}\left[8\right]\right)$

$v≔\left[\begin{array}{c}\mathrm{DeepLearning\; Tensor}\\ \mathrm{Name:\; Variable:0}\\ \mathrm{Shape:\; [2]}\\ \mathrm{Data\; Type:\; float[8]}\end{array}\right]$

$c≔\mathrm{Constant}\left(\left[1.5\,3.0\right]\,\mathrm{datatype}=\mathrm{float}\left[8\right]\right)$

$c≔\left[\begin{array}{c}\mathrm{DeepLearning\; Tensor}\\ \mathrm{Name:\; Const:0}\\ \mathrm{Shape:\; [2]}\\ \mathrm{Data\; Type:\; float[8]}\end{array}\right]$

$\mathrm{AssignAdd}\left(v\,c\right)$

$\left[\begin{array}{c}\mathrm{DeepLearning\; Tensor}\\ \mathrm{Name:\; AssignAdd:0}\\ \mathrm{Shape:\; [2]}\\ \mathrm{Data\; Type:\; float[8]}\end{array}\right]$

$\mathrm{sess}≔\mathrm{GetDefaultSession}\left(\right)$

$\mathrm{sess}≔\left[\begin{array}{c}\mathrm{DeepLearning\; Session}\\ \mathrm{<tensorflow.python.client.session.InteractiveSession\; object\; at\; 0x7f44d3804350>}\end{array}\right]$

$\mathrm{sess}:-\mathrm{Run}\left(\mathrm{VariablesInitializer}\left(\right)\right)$

$\mathrm{Python}:-\mathrm{None}$

$\mathrm{Save}\left(''/tmp/model.ckpt''\right)$

$\mathrm{Restore}\left(''/tmp/model.ckpt''\right)$

The DeepLearning[Restore] and DeepLearning[Save] commands were introduced in Maple 2018.

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