tf.raw_ops.ResourceApplyAdam

Update '*var' according to the Adam algorithm.

\[\text{lr}_t := \mathrm{lr} \cdot \frac{\sqrt{1 - \beta_2^t} }{1 - \beta_1^t}\]

\[m_t := \beta_1 \cdot m_{t-1} + (1 - \beta_1) \cdot g\]

\[v_t := \beta_2 \cdot v_{t-1} + (1 - \beta_2) \cdot g^2\]

\[\text{var} := \begin{cases} \text{var} - (m_t \beta_1 + g \cdot (1 - \beta_1))\cdot\text{lr}_t/(\sqrt{v_t} + \epsilon), &\text{if use_nesterov}\\\\ \text{var} - m_t \cdot \text{lr}_t /(\sqrt{v_t} + \epsilon), &\text{otherwise} \end{cases}\]

varA Tensor of type resource. Should be from a Variable().
mA Tensor of type resource. Should be from a Variable().
vA Tensor of type resource. Should be from a Variable().
beta1_powerA 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. Must be a scalar.
beta2_powerA Tensor. Must have the same type as beta1_power. Must be a scalar.
lrA Tensor. Must have the same type as beta1_power. Scaling factor. Must be a scalar.
beta1A Tensor. Must have the same type as beta1_power. Momentum factor. Must be a scalar.
beta2A Tensor. Must have the same type as beta1_power. Momentum factor. Must be a scalar.
epsilonA Tensor. Must have the same type as beta1_power. Ridge term. Must be a scalar.
gradA Tensor. Must have the same type as beta1_power. The gradient.
use_lockingAn optional bool. Defaults to False. If True, updating of the var, m, and v tensors will be protected by a lock; otherwise the behavior is undefined, but may exhibit less contention.
use_nesterovAn optional bool. Defaults to False. If True, uses the nesterov update.
nameA name for the operation (optional).

The created Operation.