object for DeepLearning computation session
Creating and Using Sessions
Operations with Sessions
A Session is an object which encapsulates the context in which Tensor objects within a DataflowGraph are evaluated.
There can be more than one Session for the same DataflowGraph, and each Session has its own state and resources.
To obtain the default computation session for the current graph, use the GetDefaultSession command.
To obtain a new session, use the Session command.
The following functions can be performed with a Session.
Here we execute the same simple graph (which performs arithmetic with three Tensors) in the default computation session and in a new session.
t1 ≔ Variable⁡1.5,2.0,datatype=float8
t1≔DeepLearning VariableName: Variable:0Shape: Data Type: float
t2 ≔ Variable⁡2.5,6.0,datatype=float8
t2≔DeepLearning VariableName: Variable:0Shape: Data Type: float
t3 ≔ Variable⁡7.2,4.2,datatype=float8
t3≔DeepLearning VariableName: Variable:0Shape: Data Type: float
The DeepLearning[SessionObject] command was introduced in Maple 2018.
For more information on Maple 2018 changes, see Updates in Maple 2018.
Download Help Document