DeepLearning - Maple Programming Help

Online Help

All Products    Maple    MapleSim


Home : Support : Online Help : Programming : DeepLearning Package : Managing Sessions : DeepLearning/Session

DeepLearning

  

Session

  

get a new computation session

 

Calling Sequence

Description

Note

Examples

Compatibility

Calling Sequence

Session()

Description

• 

The Session() command returns a new Session object for the current DataflowGraph.

• 

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

Note

• 

To obtain the default computation session for the current DataFlowGraph rather than a new session, use GetDefaultSession.

Examples

Here we execute the same simple graph (which just multiplies two Tensors) in the default computation session and in a new session.

withDeepLearning:

aVariable21.5,72.0,datatype=float8

aDeepLearning TensorName: Variable:0Shape: [2]Data Type: float[8]

(1)

bVariable32.5,86.0,datatype=float8

bDeepLearning TensorName: Variable_1:0Shape: [2]Data Type: float[8]

(2)

cVariable17.2,94.2,datatype=float8

cDeepLearning TensorName: Variable_2:0Shape: [2]Data Type: float[8]

(3)

initVariablesInitializer

initDeepLearning TensorName: initShape: undefinedData Type: undefined

(4)

new_sessSession

new_sessDeepLearning Session<tensorflow.python.client.session.Session object at 0x7f7c3a1d9f50>

(5)

new_sess:-Runinit

Python:−None

(6)

new_sess:-Runa2+b2+c2

1814.3400000000021453.6400000000

(7)

Compatibility

• 

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

• 

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

See Also

DeepLearning Overview

GetDefaultSession