Type AdadeltaOptimizer
Namespace tensorflow.train
Parent Optimizer
Interfaces IAdadeltaOptimizer
Optimizer that implements the Adadelta algorithm. See [M. D. Zeiler](http://arxiv.org/abs/1212.5701)
([pdf](http://arxiv.org/pdf/1212.5701v1.pdf))
Methods
Properties
Public static methods
AdadeltaOptimizer NewDyn(ImplicitContainer<T> learning_rate, ImplicitContainer<T> rho, ImplicitContainer<T> epsilon, ImplicitContainer<T> use_locking, ImplicitContainer<T> name)
Construct a new Adadelta optimizer.
Parameters
-
ImplicitContainer<T>learning_rate - A `Tensor` or a floating point value. The learning rate. To match the exact form in the original paper use 1.0.
-
ImplicitContainer<T>rho - A `Tensor` or a floating point value. The decay rate.
-
ImplicitContainer<T>epsilon - A `Tensor` or a floating point value. A constant epsilon used to better conditioning the grad update.
-
ImplicitContainer<T>use_locking - If `True` use locks for update operations.
-
ImplicitContainer<T>name - Optional name prefix for the operations created when applying gradients. Defaults to "Adadelta".