Update '*var' according to the adadelta scheme.
tf.raw_ops.ApplyAdadelta(
var,
accum,
accum_update,
lr,
rho,
epsilon,
grad,
use_locking=False,
name=None
)
accum = rho() * accum + (1 - rho()) * grad.square();
update = (update_accum + epsilon).sqrt() * (accum + epsilon()).rsqrt() * grad;
update_accum = rho() * update_accum + (1 - rho()) * update.square();
var -= update;
Args |
var
|
A mutable Tensor . Must be one of the following types: float32 , float64 , int32 , uint8 , int16 , int8 , complex64 , int64 , qint8 , quint8 , qint32 , bfloat16 , qint16 , quint16 , uint16 , complex128 , half , uint32 , uint64 .
Should be from a Variable().
|
accum
|
A mutable Tensor . Must have the same type as var .
Should be from a Variable().
|
accum_update
|
A mutable Tensor . Must have the same type as var .
Should be from a Variable().
|
lr
|
A Tensor . Must have the same type as var .
Scaling factor. Must be a scalar.
|
rho
|
A Tensor . Must have the same type as var .
Decay factor. Must be a scalar.
|
epsilon
|
A Tensor . Must have the same type as var .
Constant factor. Must be a scalar.
|
grad
|
A Tensor . Must have the same type as var . The gradient.
|
use_locking
|
An optional bool . Defaults to False .
If True, updating of the var, accum and update_accum tensors will be protected by
a lock; otherwise the behavior is undefined, but may exhibit less contention.
|
name
|
A name for the operation (optional).
|
Returns |
A mutable Tensor . Has the same type as var .
|