VariablesInitializer() returns an Operation which can be run in a Session to initialize all the variables in the graph.
Note that this command requires that eager execution be turned off beforehand using the SetEagerExecution command.
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](..).
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.
v ≔ Variable⁡0.3,datatype=float8
v≔DeepLearning VariableName: Variable:0Shape: Data Type: float
init ≔ VariablesInitializer⁡
init≔DeepLearning Operationname: "init"
sess ≔ GetDefaultSession⁡
sess≔DeepLearning Session<tensorflow.python.client.session.InteractiveSession object at 0x7f7e1cdbc5e0>
The DeepLearning[VariablesInitializer] command was introduced in Maple 2018.
For more information on Maple 2018 changes, see Updates in Maple 2018.
The DeepLearning[VariablesInitializer] command was updated in Maple 2021.
The option was updated in Maple 2021.
Download Help Document
What kind of issue would you like to report? (Optional)