tf.raw_ops.ApplyMomentum

Update '*var' according to the momentum scheme.

tf.raw_ops.ApplyMomentum(
    var, accum, lr, grad, momentum, use_locking=False, use_nesterov=False, name=None
)

Set use_nesterov = True if you want to use Nesterov momentum.

accum = accum * momentum + grad var -= lr * accum

Args:

  • var: A mutable Tensor. Must be one of the following types: float32, float64, int32, uint8, int16, int8, complex64, int64, qint8, quint8, qint32, bfloat16, 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().
  • lr: A Tensor. Must have the same type as var. Scaling factor. Must be a scalar.
  • grad: A Tensor. Must have the same type as var. The gradient.
  • momentum: A Tensor. Must have the same type as var. Momentum. Must be a scalar.
  • use_locking: An optional bool. Defaults to False. If True, updating of the var and accum tensors will be protected by a lock; otherwise the behavior is undefined, but may exhibit less contention.
  • use_nesterov: An optional bool. Defaults to False. If True, the tensor passed to compute grad will be var - lr * momentum * accum, so in the end, the var you get is actually var - lr * momentum * accum.
  • name: A name for the operation (optional).

Returns:

A mutable Tensor. Has the same type as var.