Type RMSPropOptimizer
Namespace tensorflow.train
Parent Optimizer
Interfaces IRMSPropOptimizer
Optimizer that implements the RMSProp algorithm. See the
[paper](http://www.cs.toronto.edu/~tijmen/csc321/slides/lecture_slides_lec6.pdf).
Methods
Properties
Public static methods
RMSPropOptimizer NewDyn(object learning_rate, ImplicitContainer<T> decay, ImplicitContainer<T> momentum, ImplicitContainer<T> epsilon, ImplicitContainer<T> use_locking, ImplicitContainer<T> centered, ImplicitContainer<T> name)
Construct a new RMSProp optimizer. Note that in the dense implementation of this algorithm, variables and their
corresponding accumulators (momentum, gradient moving average, square
gradient moving average) will be updated even if the gradient is zero
(i.e. accumulators will decay, momentum will be applied). The sparse
implementation (used when the gradient is an `IndexedSlices` object,
typically because of
tf.gather or an embedding lookup in the forward pass)
will not update variable slices or their accumulators unless those slices
were used in the forward pass (nor is there an "eventual" correction to
account for these omitted updates). This leads to more efficient updates for
large embedding lookup tables (where most of the slices are not accessed in
a particular graph execution), but differs from the published algorithm.
Parameters
-
objectlearning_rate - A Tensor or a floating point value. The learning rate.
-
ImplicitContainer<T>decay - Discounting factor for the history/coming gradient
-
ImplicitContainer<T>momentum - A scalar tensor.
-
ImplicitContainer<T>epsilon - Small value to avoid zero denominator.
-
ImplicitContainer<T>use_locking - If True use locks for update operation.
-
ImplicitContainer<T>centered - If True, gradients are normalized by the estimated variance of the gradient; if False, by the uncentered second moment. Setting this to True may help with training, but is slightly more expensive in terms of computation and memory. Defaults to False.
-
ImplicitContainer<T>name - Optional name prefix for the operations created when applying gradients. Defaults to "RMSProp".