DeepLearning - Maple Programming Help

Online Help

All Products    Maple    MapleSim


Home : Support : Online Help : Programming : DeepLearning Package : Tensors : Managing Tensors : DeepLearning/VariablesInitializer

DeepLearning

  

VariablesInitializer

  

initialize variables

 

Calling Sequence

Description

Details

Examples

Compatibility

Calling Sequence

VariablesInitializer()

Description

• 

The VariablesInitializer() command returns an Operation which can be run in a Session to initialize all the variables in the graph.

• 

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

Details

• 

The implementation of VariablesInitializer uses the tf.global_variables_initializer command from the TensorFlow Python API. Consult the TensorFlow Python API documentation for tf.global_variables_initializer for more information on random number generation during TensorFlow computations.

Examples

withDeepLearning:

vVariable0.3,datatype=float8

vDeepLearning TensorName: Variable:0Shape: [1]Data Type: float[8]

(1)

initVariablesInitializer

initDeepLearning TensorName: initShape: undefinedData Type: undefined

(2)

sessGetDefaultSession

sessDeepLearning Session<tensorflow.python.client.session.InteractiveSession object at 0x7f4d45706bd0>

(3)

sess:-Runinit

Python:−None

(4)

Compatibility

• 

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

• 

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

See Also

DeepLearning Overview