A Tensor or a floating point value. The learning rate.
Discounting factor for the history/coming gradient
A scalar tensor.
Small value to avoid zero denominator.
If True use locks for update operation.
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.
Optional name prefix for the operations created when applying
gradients. Defaults to "RMSProp".
Compute gradients of loss for the variables in var_list.
This is the first part of minimize(). It returns a list
of (gradient, variable) pairs where "gradient" is the gradient
for "variable". Note that "gradient" can be a Tensor, an
IndexedSlices, or None if there is no gradient for the
A Tensor containing the value to minimize or a callable taking
no arguments which returns the value to minimize. When eager execution
is enabled it must be a callable.
Optional list or tuple of tf.Variable to update to minimize
loss. Defaults to the list of variables collected in the graph
under the key GraphKeys.TRAINABLE_VARIABLES.
How to gate the computation of gradients. Can be
GATE_NONE, GATE_OP, or GATE_GRAPH.
Specifies the method used to combine gradient terms.
Valid values are defined in the class AggregationMethod.
If True, try colocating gradients with
the corresponding op.
Optional. A Tensor holding the gradient computed for loss.
A list of (gradient, variable) pairs. Variable is always present, but
gradient can be None.
If var_list contains anything else than Variable objects.
If some arguments are invalid.
If called with eager execution enabled and loss is