DeepLearning
Restore
save and restore sessions
Save
Calling Sequence
Parameters
Description
Details
Examples
Compatibility
Restore(path)
Save(path,model)
path
-
string; path to saved model
model
model object
The Restore(path) command loads a saved model or computation session to memory from a file located at path.
The Save(path) command saves a model or computation session in memory to a 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.
Examples of Einstein summation on vectors
with⁡DeepLearning:
v≔Variable⁡1.0,0.5,datatype=float8
v≔DeepLearning TensorName: Variable:0Shape: undefinedData Type: float[8]
c≔Constant⁡1.5,3.0,datatype=float8
c≔DeepLearning TensorName: noneShape: undefinedData Type: float[8]
AssignAdd⁡v,c
sess≔GetDefaultSession⁡
sess:-Run⁡VariablesInitializer⁡
Save⁡/tmp/model.ckpt
Restore⁡/tmp/model.ckpt
The DeepLearning[Restore] and DeepLearning[Save] commands were introduced in Maple 2018.
For more information on Maple 2018 changes, see Updates in Maple 2018.
See Also
DeepLearning Overview
Download Help Document
What kind of issue would you like to report? (Optional)