# tensorflow::ops::SparseApplyMomentum Class Reference

# tensorflow::
ops::
SparseApplyMomentum

`
#include <training_ops.h>
`


Update relevant entries in '\*var' and '\*accum' according to the momentum scheme.

## Summary


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


That is for rows we have grad for, we update var and accum as follows:


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

<br />


Args:

- scope: A [Scope](https://www.tensorflow.org/versions/r2.5/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope) object
- var: Should be from a Variable().
- accum: Should be from a Variable().
- lr: Learning rate. Must be a scalar.
- grad: The gradient.
- indices: A vector of indices into the first dimension of var and accum.
- momentum: Momentum. Must be a scalar.

<br />


Optional attributes (see
`
https://www.tensorflow.org/versions/r2.5/api_docs/cc/struct/tensorflow/ops/sparse-apply-momentum/attrs#structtensorflow_1_1ops_1_1_sparse_apply_momentum_1_1_attrs
`
):

- use_locking: 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: 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.

<br />


Returns:

- `
  https://www.tensorflow.org/versions/r2.5/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output
  ` : Same as "var".

<br />

| ### Constructors and Destructors ||
|---|---|
| ` https://www.tensorflow.org/versions/r2.5/api_docs/cc/class/tensorflow/ops/sparse-apply-momentum#classtensorflow_1_1ops_1_1_sparse_apply_momentum_1aad6f0afa69fbbc1896aceb60f9651bc8 (const :: https://www.tensorflow.org/versions/r2.5/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope & scope, :: https://www.tensorflow.org/versions/r2.5/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input var, :: https://www.tensorflow.org/versions/r2.5/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input accum, :: https://www.tensorflow.org/versions/r2.5/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input lr, :: https://www.tensorflow.org/versions/r2.5/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input grad, :: https://www.tensorflow.org/versions/r2.5/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input indices, :: https://www.tensorflow.org/versions/r2.5/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input momentum) ` ||
| ` https://www.tensorflow.org/versions/r2.5/api_docs/cc/class/tensorflow/ops/sparse-apply-momentum#classtensorflow_1_1ops_1_1_sparse_apply_momentum_1a769bc8a904000fccba7f122e985687c9 (const :: https://www.tensorflow.org/versions/r2.5/api_docs/cc/class/tensorflow/scope#classtensorflow_1_1_scope & scope, :: https://www.tensorflow.org/versions/r2.5/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input var, :: https://www.tensorflow.org/versions/r2.5/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input accum, :: https://www.tensorflow.org/versions/r2.5/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input lr, :: https://www.tensorflow.org/versions/r2.5/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input grad, :: https://www.tensorflow.org/versions/r2.5/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input indices, :: https://www.tensorflow.org/versions/r2.5/api_docs/cc/class/tensorflow/input#classtensorflow_1_1_input momentum, const https://www.tensorflow.org/versions/r2.5/api_docs/cc/struct/tensorflow/ops/sparse-apply-momentum/attrs#structtensorflow_1_1ops_1_1_sparse_apply_momentum_1_1_attrs & attrs) ` ||

| ### Public attributes ||
|---|---|
| ` https://www.tensorflow.org/versions/r2.5/api_docs/cc/class/tensorflow/ops/sparse-apply-momentum#classtensorflow_1_1ops_1_1_sparse_apply_momentum_1a30b8c7c6bf9f92ee2be7ac7297df6fa2 ` | ` https://www.tensorflow.org/versions/r2.5/api_docs/cc/class/tensorflow/operation#classtensorflow_1_1_operation ` |
| ` https://www.tensorflow.org/versions/r2.5/api_docs/cc/class/tensorflow/ops/sparse-apply-momentum#classtensorflow_1_1ops_1_1_sparse_apply_momentum_1a64f0643f05faf59221caf6fce9bbe4b5 ` | ` :: https://www.tensorflow.org/versions/r2.5/api_docs/cc/class/tensorflow/output#classtensorflow_1_1_output ` |

| ### Public functions ||
|---|---|
| ` https://www.tensorflow.org/versions/r2.5/api_docs/cc/class/tensorflow/ops/sparse-apply-momentum#classtensorflow_1_1ops_1_1_sparse_apply_momentum_1a79f23cdeb4f72f3271572314b76661a4 () const ` | ` ::tensorflow::Node * ` |
| ` https://www.tensorflow.org/versions/r2.5/api_docs/cc/class/tensorflow/ops/sparse-apply-momentum#classtensorflow_1_1ops_1_1_sparse_apply_momentum_1a1be0ad2b688da68c70f65c7ae802a258 () const ` | ` ` |
| ` https://www.tensorflow.org/versions/r2.5/api_docs/cc/class/tensorflow/ops/sparse-apply-momentum#classtensorflow_1_1ops_1_1_sparse_apply_momentum_1a8eb81a827b3a21e7a6feaef16e6df395 () const ` | ` ` |

| ### Public static functions ||
|---|---|
| ` https://www.tensorflow.org/versions/r2.5/api_docs/cc/class/tensorflow/ops/sparse-apply-momentum#classtensorflow_1_1ops_1_1_sparse_apply_momentum_1a91893d64df26bd060d9da800107c6e3c (bool x) ` | ` https://www.tensorflow.org/versions/r2.5/api_docs/cc/struct/tensorflow/ops/sparse-apply-momentum/attrs#structtensorflow_1_1ops_1_1_sparse_apply_momentum_1_1_attrs ` |
| ` https://www.tensorflow.org/versions/r2.5/api_docs/cc/class/tensorflow/ops/sparse-apply-momentum#classtensorflow_1_1ops_1_1_sparse_apply_momentum_1a90b8463d951fbf572ba63b9ec8ca3946 (bool x) ` | ` https://www.tensorflow.org/versions/r2.5/api_docs/cc/struct/tensorflow/ops/sparse-apply-momentum/attrs#structtensorflow_1_1ops_1_1_sparse_apply_momentum_1_1_attrs ` |

| ### Structs ||
|---|---|
| [tensorflow:: ops:: SparseApplyMomentum:: Attrs](https://www.tensorflow.org/versions/r2.5/api_docs/cc/struct/tensorflow/ops/sparse-apply-momentum/attrs) | Optional attribute setters for [SparseApplyMomentum](https://www.tensorflow.org/versions/r2.5/api_docs/cc/class/tensorflow/ops/sparse-apply-momentum#classtensorflow_1_1ops_1_1_sparse_apply_momentum) . |

## Public attributes

### operation

```
Operation operation
```

### out

```
::tensorflow::Output out
```

## Public functions

### SparseApplyMomentum

```
 SparseApplyMomentum(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input var,
  ::tensorflow::Input accum,
  ::tensorflow::Input lr,
  ::tensorflow::Input grad,
  ::tensorflow::Input indices,
  ::tensorflow::Input momentum
)
```

### SparseApplyMomentum

```
 SparseApplyMomentum(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input var,
  ::tensorflow::Input accum,
  ::tensorflow::Input lr,
  ::tensorflow::Input grad,
  ::tensorflow::Input indices,
  ::tensorflow::Input momentum,
  const SparseApplyMomentum::Attrs & attrs
)
```

### node

```
::tensorflow::Node * node() const 
```

### operator::tensorflow::Input

```
 operator::tensorflow::Input() const 
```

### operator::tensorflow::Output

```
 operator::tensorflow::Output() const 
```

## Public static functions

### UseLocking

```
Attrs UseLocking(
  bool x
)
```

### UseNesterov

```
Attrs UseNesterov(
  bool x
)
```