# tf.compat.v1.Variable

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/variable_v1.py#L54-L322) |

See the [Variables Guide](https://tensorflow.org/guide/variables).

Inherits From: [`Variable`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/Variable)

    tf.compat.v1.Variable(
        initial_value=None,
        trainable=None,
        collections=None,
        validate_shape=True,
        caching_device=None,
        name=None,
        variable_def=None,
        dtype=None,
        expected_shape=None,
        import_scope=None,
        constraint=None,
        use_resource=None,
        synchronization=https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/VariableSynchronization#AUTO,
        aggregation=https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/compat/v1/VariableAggregation#NONE,
        shape=None
    )

A variable maintains state in the graph across calls to `run()`. You add a
variable to the graph by constructing an instance of the class `Variable`.

The `Variable()` constructor requires an initial value for the variable,
which can be a `Tensor` of any type and shape. The initial value defines the
type and shape of the variable. After construction, the type and shape of
the variable are fixed. The value can be changed using one of the assign
methods.

If you want to change the shape of a variable later you have to use an
`assign` Op with `validate_shape=False`.

Just like any `Tensor`, variables created with `Variable()` can be used as
inputs for other Ops in the graph. Additionally, all the operators
overloaded for the `Tensor` class are carried over to variables, so you can
also add nodes to the graph by just doing arithmetic on variables.

    import tensorflow as tf

    # Create a variable.
    w = tf.Variable(<initial-value>, name=<optional-name>)

    # Use the variable in the graph like any Tensor.
    y = tf.matmul(w, ...another variable or tensor...)

    # The overloaded operators are available too.
    z = tf.sigmoid(w + y)

    # Assign a new value to the variable with `assign()` or a related method.
    w.assign(w + 1.0)
    w.assign_add(1.0)

When you launch the graph, variables have to be explicitly initialized before
you can run Ops that use their value. You can initialize a variable by
running its *initializer op* , restoring the variable from a save file, or
simply running an `assign` Op that assigns a value to the variable. In fact,
the variable *initializer op* is just an `assign` Op that assigns the
variable's initial value to the variable itself.

    # Launch the graph in a session.
    with tf.compat.v1.Session() as sess:
        # Run the variable initializer.
        sess.run(w.initializer)
        # ...you now can run ops that use the value of 'w'...

The most common initialization pattern is to use the convenience function
`global_variables_initializer()` to add an Op to the graph that initializes
all the variables. You then run that Op after launching the graph.

    # Add an Op to initialize global variables.
    init_op = tf.compat.v1.global_variables_initializer()

    # Launch the graph in a session.
    with tf.compat.v1.Session() as sess:
        # Run the Op that initializes global variables.
        sess.run(init_op)
        # ...you can now run any Op that uses variable values...

If you need to create a variable with an initial value dependent on another
variable, use the other variable's `initialized_value()`. This ensures that
variables are initialized in the right order.

All variables are automatically collected in the graph where they are
created. By default, the constructor adds the new variable to the graph
collection `GraphKeys.GLOBAL_VARIABLES`. The convenience function
`global_variables()` returns the contents of that collection.

When building a machine learning model it is often convenient to distinguish
between variables holding the trainable model parameters and other variables
such as a `global step` variable used to count training steps. To make this
easier, the variable constructor supports a `trainable=<bool>` parameter. If
`True`, the new variable is also added to the graph collection
`GraphKeys.TRAINABLE_VARIABLES`. The convenience function
`trainable_variables()` returns the contents of this collection. The
various `Optimizer` classes use this collection as the default list of
variables to optimize.

> [!WARNING]
> **Warning:** tf.Variable objects by default have a non-intuitive memory model. A Variable is represented internally as a mutable Tensor which can non-deterministically alias other Tensors in a graph. The set of operations which consume a Variable and can lead to aliasing is undetermined and can change across TensorFlow versions. Avoid writing code which relies on the value of a Variable either changing or not changing as other operations happen. For example, using Variable objects or simple functions thereof as predicates in a [`tf.cond`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/cond) is dangerous and error-prone:

    v = tf.Variable(True)
    tf.cond(v, lambda: v.assign(False), my_false_fn)  # Note: this is broken.

Here, adding `use_resource=True` when constructing the variable will
fix any nondeterminism issues:

    v = tf.Variable(True, use_resource=True)
    tf.cond(v, lambda: v.assign(False), my_false_fn)

To use the replacement for variables which does
not have these issues:

- Add `use_resource=True` when constructing [`tf.Variable`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/Variable);
- Call `tf.compat.v1.get_variable_scope().set_use_resource(True)` inside a [`tf.compat.v1.variable_scope`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/compat/v1/variable_scope) before the [`tf.compat.v1.get_variable()`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/compat/v1/get_variable) call.

<br />

<br />

<br />

| ## Args ||
|---|---|
| `initial_value` | A `Tensor`, or Python object convertible to a `Tensor`, which is the initial value for the Variable. The initial value must have a shape specified unless `validate_shape` is set to False. Can also be a callable with no argument that returns the initial value when called. In that case, `dtype` must be specified. (Note that initializer functions from init_ops.py must first be bound to a shape before being used here.) |
| `trainable` | If `True`, also adds the variable to the graph collection `GraphKeys.TRAINABLE_VARIABLES`. This collection is used as the default list of variables to use by the `Optimizer` classes. Defaults to `True`, unless `synchronization` is set to `ON_READ`, in which case it defaults to `False`. |
| `collections` | List of graph collections keys. The new variable is added to these collections. Defaults to `[GraphKeys.GLOBAL_VARIABLES]`. |
| `validate_shape` | If `False`, allows the variable to be initialized with a value of unknown shape. If `True`, the default, the shape of `initial_value` must be known. |
| `caching_device` | Optional device string describing where the Variable should be cached for reading. Defaults to the Variable's device. If not `None`, caches on another device. Typical use is to cache on the device where the Ops using the Variable reside, to deduplicate copying through `Switch` and other conditional statements. |
| `name` | Optional name for the variable. Defaults to `'Variable'` and gets uniquified automatically. |
| `variable_def` | `VariableDef` protocol buffer. If not `None`, recreates the Variable object with its contents, referencing the variable's nodes in the graph, which must already exist. The graph is not changed. `variable_def` and the other arguments are mutually exclusive. |
| `dtype` | If set, initial_value will be converted to the given type. If `None`, either the datatype will be kept (if `initial_value` is a Tensor), or `convert_to_tensor` will decide. |
| `expected_shape` | A TensorShape. If set, initial_value is expected to have this shape. |
| `import_scope` | Optional `string`. Name scope to add to the `Variable.` Only used when initializing from protocol buffer. |
| `constraint` | An optional projection function to be applied to the variable after being updated by an `Optimizer` (e.g. used to implement norm constraints or value constraints for layer weights). The function must take as input the unprojected Tensor representing the value of the variable and return the Tensor for the projected value (which must have the same shape). Constraints are not safe to use when doing asynchronous distributed training. |
| `use_resource` | whether to use resource variables. |
| `synchronization` | Indicates when a distributed a variable will be aggregated. Accepted values are constants defined in the class [`tf.VariableSynchronization`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/VariableSynchronization). By default the synchronization is set to `AUTO` and the current `DistributionStrategy` chooses when to synchronize. |
| `aggregation` | Indicates how a distributed variable will be aggregated. Accepted values are constants defined in the class [`tf.VariableAggregation`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/VariableAggregation). |
| `shape` | (optional) The shape of this variable. If None, the shape of `initial_value` will be used. When setting this argument to [`tf.TensorShape(None)`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/TensorShape) (representing an unspecified shape), the variable can be assigned with values of different shapes. |

<br />

<br />

<br />

<br />

| ## Raises ||
|---|---|
| `ValueError` | If both `variable_def` and initial_value are specified. |
| `ValueError` | If the initial value is not specified, or does not have a shape and `validate_shape` is `True`. |
| `RuntimeError` | If eager execution is enabled. |

<br />

<br />

<br />

<br />

| ## Attributes ||
|---|---|
| `aggregation` | <br /> <br /> |
| `constraint` | Returns the constraint function associated with this variable. |
| `device` | The device of this variable. |
| `dtype` | The `DType` of this variable. |
| `graph` | The `Graph` of this variable. |
| `initial_value` | Returns the Tensor used as the initial value for the variable. <br /> Note that this is different from `initialized_value()` which runs the op that initializes the variable before returning its value. This method returns the tensor that is used by the op that initializes the variable. |
| `initializer` | The initializer operation for this variable. |
| `name` | The name of this variable. |
| `op` | The `Operation` of this variable. |
| `shape` | The `TensorShape` of this variable. |
| `synchronization` | <br /> <br /> |
| `trainable` | <br /> <br /> |

<br />

## Child Classes

[`class SaveSliceInfo`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/Variable/SaveSliceInfo)

## Methods

### `assign`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/variables.py#L516-L532)

    assign(
        value, use_locking=False, name=None, read_value=True
    )

Assigns a new value to the variable.

This is essentially a shortcut for `assign(self, value)`.

<br />

<br />

<br />

| Args ||
|---|---|
| `value` | A `Tensor`. The new value for this variable. |
| `use_locking` | If `True`, use locking during the assignment. |
| `name` | The name of the operation to be created |
| `read_value` | if True, will return something which evaluates to the new value of the variable; if False will return the assign op. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| The updated variable. If `read_value` is false, instead returns None in Eager mode and the assign op in graph mode. ||

<br />

### `assign_add`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/variables.py#L534-L550)

    assign_add(
        delta, use_locking=False, name=None, read_value=True
    )

Adds a value to this variable.

This is essentially a shortcut for `assign_add(self, delta)`.

<br />

<br />

<br />

| Args ||
|---|---|
| `delta` | A `Tensor`. The value to add to this variable. |
| `use_locking` | If `True`, use locking during the operation. |
| `name` | The name of the operation to be created |
| `read_value` | if True, will return something which evaluates to the new value of the variable; if False will return the assign op. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| The updated variable. If `read_value` is false, instead returns None in Eager mode and the assign op in graph mode. ||

<br />

### `assign_sub`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/variables.py#L552-L568)

    assign_sub(
        delta, use_locking=False, name=None, read_value=True
    )

Subtracts a value from this variable.

This is essentially a shortcut for `assign_sub(self, delta)`.

<br />

<br />

<br />

| Args ||
|---|---|
| `delta` | A `Tensor`. The value to subtract from this variable. |
| `use_locking` | If `True`, use locking during the operation. |
| `name` | The name of the operation to be created |
| `read_value` | if True, will return something which evaluates to the new value of the variable; if False will return the assign op. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| The updated variable. If `read_value` is false, instead returns None in Eager mode and the assign op in graph mode. ||

<br />

### `batch_scatter_update`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/variables.py#L684-L728)

    batch_scatter_update(
        sparse_delta, use_locking=False, name=None
    )

Assigns [`tf.IndexedSlices`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/IndexedSlices) to this variable batch-wise.

Analogous to `batch_gather`. This assumes that this variable and the
sparse_delta IndexedSlices have a series of leading dimensions that are the
same for all of them, and the updates are performed on the last dimension of
indices. In other words, the dimensions should be the following:

`num_prefix_dims = sparse_delta.indices.ndims - 1`
`batch_dim = num_prefix_dims + 1`
`sparse_delta.updates.shape = sparse_delta.indices.shape + var.shape[
batch_dim:]`

where

`sparse_delta.updates.shape[:num_prefix_dims]`
`== sparse_delta.indices.shape[:num_prefix_dims]`
`== var.shape[:num_prefix_dims]`

And the operation performed can be expressed as:

`var[i_1, ..., i_n,
sparse_delta.indices[i_1, ..., i_n, j]] = sparse_delta.updates[
i_1, ..., i_n, j]`

When sparse_delta.indices is a 1D tensor, this operation is equivalent to
`scatter_update`.

To avoid this operation one can looping over the first `ndims` of the
variable and using `scatter_update` on the subtensors that result of slicing
the first dimension. This is a valid option for `ndims = 1`, but less
efficient than this implementation.

<br />

<br />

<br />

| Args ||
|---|---|
| `sparse_delta` | [`tf.IndexedSlices`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/IndexedSlices) to be assigned to this variable. |
| `use_locking` | If `True`, use locking during the operation. |
| `name` | the name of the operation. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| The updated variable. ||

<br />

<br />

<br />

<br />

| Raises ||
|---|---|
| `TypeError` | if `sparse_delta` is not an `IndexedSlices`. |

<br />

### `count_up_to`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/variables.py#L899-L920)

    count_up_to(
        limit
    )

Increments this variable until it reaches `limit`. (deprecated)

> [!WARNING]
> **Deprecated:** THIS FUNCTION IS DEPRECATED. It will be removed in a future version. Instructions for updating: Prefer Dataset.range instead.

When that Op is run it tries to increment the variable by `1`. If
incrementing the variable would bring it above `limit` then the Op raises
the exception `OutOfRangeError`.

If no error is raised, the Op outputs the value of the variable before
the increment.

This is essentially a shortcut for `count_up_to(self, limit)`.

<br />

<br />

<br />

| Args ||
|---|---|
| `limit` | value at which incrementing the variable raises an error. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| A `Tensor` that will hold the variable value before the increment. If no other Op modifies this variable, the values produced will all be distinct. ||

<br />

### `eval`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/variables.py#L436-L466)

    eval(
        session=None
    )

In a session, computes and returns the value of this variable.

This is not a graph construction method, it does not add ops to the graph.

This convenience method requires a session where the graph
containing this variable has been launched. If no session is
passed, the default session is used. See [`tf.compat.v1.Session`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/compat/v1/Session) for more
information on launching a graph and on sessions.

    v = tf.Variable([1, 2])
    init = tf.compat.v1.global_variables_initializer()

    with tf.compat.v1.Session() as sess:
        sess.run(init)
        # Usage passing the session explicitly.
        print(v.eval(sess))
        # Usage with the default session.  The 'with' block
        # above makes 'sess' the default session.
        print(v.eval())

<br />

<br />

<br />

| Args ||
|---|---|
| `session` | The session to use to evaluate this variable. If none, the default session is used. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| A numpy `ndarray` with a copy of the value of this variable. ||

<br />

### `experimental_ref`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/variables.py#L1142-L1144)

    experimental_ref()

DEPRECATED FUNCTION

> [!WARNING]
> **Deprecated:** THIS FUNCTION IS DEPRECATED. It will be removed in a future version. Instructions for updating: Use ref() instead.

### `from_proto`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/variable_v1.py#L269-L272)

    @staticmethod
    from_proto(
        variable_def, import_scope=None
    )

Returns a `Variable` object created from `variable_def`.

### `gather_nd`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/variables.py#L884-L897)

    gather_nd(
        indices, name=None
    )

Gather slices from `params` into a Tensor with shape specified by `indices`.

See tf.gather_nd for details.

<br />

<br />

<br />

| Args ||
|---|---|
| `indices` | A `Tensor`. Must be one of the following types: `int32`, `int64`. Index tensor. |
| `name` | A name for the operation (optional). |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| A `Tensor`. Has the same type as `params`. ||

<br />

### `get_shape`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/variables.py#L1106-L1108)

    get_shape()

Alias of [`Variable.shape`](https://www.tensorflow.org/api_docs/python/tf/Variable#shape).

### `initialized_value`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/variable_v1.py#L263-L267)

    initialized_value()

Returns the value of the initialized variable. (deprecated)

> [!WARNING]
> **Deprecated:** THIS FUNCTION IS DEPRECATED. It will be removed in a future version. Instructions for updating: Use Variable.read_value. Variables in 2.X are initialized automatically both in eager and graph (inside tf.defun) contexts.

You should use this instead of the variable itself to initialize another
variable with a value that depends on the value of this variable.

    # Initialize 'v' with a random tensor.
    v = tf.Variable(tf.random.truncated_normal([10, 40]))
    # Use `initialized_value` to guarantee that `v` has been
    # initialized before its value is used to initialize `w`.
    # The random values are picked only once.
    w = tf.Variable(v.initialized_value() * 2.0)

<br />

<br />

<br />

| Returns ||
|---|---|
| A `Tensor` holding the value of this variable after its initializer has run. ||

<br />

### `load`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/variables.py#L922-L965)

    load(
        value, session=None
    )

Load new value into this variable. (deprecated)

> [!WARNING]
> **Deprecated:** THIS FUNCTION IS DEPRECATED. It will be removed in a future version. Instructions for updating: Prefer Variable.assign which has equivalent behavior in 2.X.

Writes new value to variable's memory. Doesn't add ops to the graph.

This convenience method requires a session where the graph
containing this variable has been launched. If no session is
passed, the default session is used. See [`tf.compat.v1.Session`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/compat/v1/Session) for more
information on launching a graph and on sessions.

    v = tf.Variable([1, 2])
    init = tf.compat.v1.global_variables_initializer()

    with tf.compat.v1.Session() as sess:
        sess.run(init)
        # Usage passing the session explicitly.
        v.load([2, 3], sess)
        print(v.eval(sess)) # prints [2 3]
        # Usage with the default session.  The 'with' block
        # above makes 'sess' the default session.
        v.load([3, 4], sess)
        print(v.eval()) # prints [3 4]

<br />

<br />

<br />

| Args ||
|---|---|
| `value` | New variable value |
| `session` | The session to use to evaluate this variable. If none, the default session is used. |

<br />

<br />

<br />

<br />

| Raises ||
|---|---|
| `ValueError` | Session is not passed and no default session |

<br />

### `read_value`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/variables.py#L405-L414)

    read_value()

Returns the value of this variable, read in the current context.

Can be different from value() if it's on another device, with control
dependencies, etc.

<br />

<br />

<br />

| Returns ||
|---|---|
| A `Tensor` containing the value of the variable. ||

<br />

### `ref`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/variables.py#L1146-L1185)

    ref()

Returns a hashable reference object to this Variable.

The primary use case for this API is to put variables in a set/dictionary.
We can't put variables in a set/dictionary as `variable.__hash__()` is no
longer available starting Tensorflow 2.0.

The following will raise an exception starting 2.0

    x = tf.Variable(5)
    y = tf.Variable(10)
    z = tf.Variable(10)
    variable_set = {x, y, z}
    Traceback (most recent call last):

    TypeError: Variable is unhashable. Instead, use tensor.ref() as the key.
    variable_dict = {x: 'five', y: 'ten'}
    Traceback (most recent call last):

    TypeError: Variable is unhashable. Instead, use tensor.ref() as the key.

Instead, we can use `variable.ref()`.

    variable_set = {x.ref(), y.ref(), z.ref()}
    x.ref() in variable_set
    True
    variable_dict = {x.ref(): 'five', y.ref(): 'ten', z.ref(): 'ten'}
    variable_dict[y.ref()]
    'ten'

Also, the reference object provides `.deref()` function that returns the
original Variable.

    x = tf.Variable(5)
    x.ref().deref()
    <tf.Variable 'Variable:0' shape=() dtype=int32, numpy=5>

### `scatter_add`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/variables.py#L586-L600)

    scatter_add(
        sparse_delta, use_locking=False, name=None
    )

Adds [`tf.IndexedSlices`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/IndexedSlices) to this variable.

<br />

<br />

<br />

| Args ||
|---|---|
| `sparse_delta` | [`tf.IndexedSlices`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/IndexedSlices) to be added to this variable. |
| `use_locking` | If `True`, use locking during the operation. |
| `name` | the name of the operation. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| The updated variable. ||

<br />

<br />

<br />

<br />

| Raises ||
|---|---|
| `TypeError` | if `sparse_delta` is not an `IndexedSlices`. |

<br />

### `scatter_div`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/variables.py#L652-L666)

    scatter_div(
        sparse_delta, use_locking=False, name=None
    )

Divide this variable by [`tf.IndexedSlices`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/IndexedSlices).

<br />

<br />

<br />

| Args ||
|---|---|
| `sparse_delta` | [`tf.IndexedSlices`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/IndexedSlices) to divide this variable by. |
| `use_locking` | If `True`, use locking during the operation. |
| `name` | the name of the operation. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| The updated variable. ||

<br />

<br />

<br />

<br />

| Raises ||
|---|---|
| `TypeError` | if `sparse_delta` is not an `IndexedSlices`. |

<br />

### `scatter_max`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/variables.py#L602-L617)

    scatter_max(
        sparse_delta, use_locking=False, name=None
    )

Updates this variable with the max of [`tf.IndexedSlices`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/IndexedSlices) and itself.

<br />

<br />

<br />

| Args ||
|---|---|
| `sparse_delta` | [`tf.IndexedSlices`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/IndexedSlices) to use as an argument of max with this variable. |
| `use_locking` | If `True`, use locking during the operation. |
| `name` | the name of the operation. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| The updated variable. ||

<br />

<br />

<br />

<br />

| Raises ||
|---|---|
| `TypeError` | if `sparse_delta` is not an `IndexedSlices`. |

<br />

### `scatter_min`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/variables.py#L619-L634)

    scatter_min(
        sparse_delta, use_locking=False, name=None
    )

Updates this variable with the min of [`tf.IndexedSlices`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/IndexedSlices) and itself.

<br />

<br />

<br />

| Args ||
|---|---|
| `sparse_delta` | [`tf.IndexedSlices`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/IndexedSlices) to use as an argument of min with this variable. |
| `use_locking` | If `True`, use locking during the operation. |
| `name` | the name of the operation. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| The updated variable. ||

<br />

<br />

<br />

<br />

| Raises ||
|---|---|
| `TypeError` | if `sparse_delta` is not an `IndexedSlices`. |

<br />

### `scatter_mul`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/variables.py#L636-L650)

    scatter_mul(
        sparse_delta, use_locking=False, name=None
    )

Multiply this variable by [`tf.IndexedSlices`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/IndexedSlices).

<br />

<br />

<br />

| Args ||
|---|---|
| `sparse_delta` | [`tf.IndexedSlices`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/IndexedSlices) to multiply this variable by. |
| `use_locking` | If `True`, use locking during the operation. |
| `name` | the name of the operation. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| The updated variable. ||

<br />

<br />

<br />

<br />

| Raises ||
|---|---|
| `TypeError` | if `sparse_delta` is not an `IndexedSlices`. |

<br />

### `scatter_nd_add`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/variables.py#L776-L820)

    scatter_nd_add(
        indices, updates, name=None
    )

Applies sparse addition to individual values or slices in a Variable.

The Variable has rank `P` and `indices` is a `Tensor` of rank `Q`.

`indices` must be integer tensor, containing indices into self.
It must be shape `[d_0, ..., d_{Q-2}, K]` where `0 < K <= P`.

The innermost dimension of `indices` (with length `K`) corresponds to
indices into elements (if `K = P`) or slices (if `K < P`) along the `K`th
dimension of self.

`updates` is `Tensor` of rank `Q-1+P-K` with shape:

    [d_0, ..., d_{Q-2}, self.shape[K], ..., self.shape[P-1]].

For example, say we want to add 4 scattered elements to a rank-1 tensor to
8 elements. In Python, that update would look like this:

        v = tf.Variable([1, 2, 3, 4, 5, 6, 7, 8])
        indices = tf.constant([[4], [3], [1] ,[7]])
        updates = tf.constant([9, 10, 11, 12])
        v.scatter_nd_add(indices, updates)
        print(v)

The resulting update to v would look like this:

    [1, 13, 3, 14, 14, 6, 7, 20]

See [`tf.scatter_nd`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/scatter_nd) for more details about how to make updates to
slices.

<br />

<br />

<br />

| Args ||
|---|---|
| `indices` | The indices to be used in the operation. |
| `updates` | The values to be used in the operation. |
| `name` | the name of the operation. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| The updated variable. ||

<br />

### `scatter_nd_sub`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/variables.py#L730-L774)

    scatter_nd_sub(
        indices, updates, name=None
    )

Applies sparse subtraction to individual values or slices in a Variable.

Assuming the variable has rank `P` and `indices` is a `Tensor` of rank `Q`.

`indices` must be integer tensor, containing indices into self.
It must be shape `[d_0, ..., d_{Q-2}, K]` where `0 < K <= P`.

The innermost dimension of `indices` (with length `K`) corresponds to
indices into elements (if `K = P`) or slices (if `K < P`) along the `K`th
dimension of self.

`updates` is `Tensor` of rank `Q-1+P-K` with shape:

    [d_0, ..., d_{Q-2}, self.shape[K], ..., self.shape[P-1]].

For example, say we want to add 4 scattered elements to a rank-1 tensor to
8 elements. In Python, that update would look like this:

        v = tf.Variable([1, 2, 3, 4, 5, 6, 7, 8])
        indices = tf.constant([[4], [3], [1] ,[7]])
        updates = tf.constant([9, 10, 11, 12])
        v.scatter_nd_sub(indices, updates)
        print(v)

After the update `v` would look like this:

    [1, -9, 3, -6, -4, 6, 7, -4]

See [`tf.scatter_nd`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/scatter_nd) for more details about how to make updates to
slices.

<br />

<br />

<br />

| Args ||
|---|---|
| `indices` | The indices to be used in the operation. |
| `updates` | The values to be used in the operation. |
| `name` | the name of the operation. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| The updated variable. ||

<br />

### `scatter_nd_update`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/variables.py#L822-L866)

    scatter_nd_update(
        indices, updates, name=None
    )

Applies sparse assignment to individual values or slices in a Variable.

The Variable has rank `P` and `indices` is a `Tensor` of rank `Q`.

`indices` must be integer tensor, containing indices into self.
It must be shape `[d_0, ..., d_{Q-2}, K]` where `0 < K <= P`.

The innermost dimension of `indices` (with length `K`) corresponds to
indices into elements (if `K = P`) or slices (if `K < P`) along the `K`th
dimension of self.

`updates` is `Tensor` of rank `Q-1+P-K` with shape:

    [d_0, ..., d_{Q-2}, self.shape[K], ..., self.shape[P-1]].

For example, say we want to add 4 scattered elements to a rank-1 tensor to
8 elements. In Python, that update would look like this:

        v = tf.Variable([1, 2, 3, 4, 5, 6, 7, 8])
        indices = tf.constant([[4], [3], [1] ,[7]])
        updates = tf.constant([9, 10, 11, 12])
        v.scatter_nd_update(indices, updates)
        print(v)

The resulting update to v would look like this:

    [1, 11, 3, 10, 9, 6, 7, 12]

See [`tf.scatter_nd`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/scatter_nd) for more details about how to make updates to
slices.

<br />

<br />

<br />

| Args ||
|---|---|
| `indices` | The indices to be used in the operation. |
| `updates` | The values to be used in the operation. |
| `name` | the name of the operation. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| The updated variable. ||

<br />

### `scatter_sub`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/variables.py#L570-L584)

    scatter_sub(
        sparse_delta, use_locking=False, name=None
    )

Subtracts [`tf.IndexedSlices`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/IndexedSlices) from this variable.

<br />

<br />

<br />

| Args ||
|---|---|
| `sparse_delta` | [`tf.IndexedSlices`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/IndexedSlices) to be subtracted from this variable. |
| `use_locking` | If `True`, use locking during the operation. |
| `name` | the name of the operation. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| The updated variable. ||

<br />

<br />

<br />

<br />

| Raises ||
|---|---|
| `TypeError` | if `sparse_delta` is not an `IndexedSlices`. |

<br />

### `scatter_update`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/variables.py#L668-L682)

    scatter_update(
        sparse_delta, use_locking=False, name=None
    )

Assigns [`tf.IndexedSlices`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/IndexedSlices) to this variable.

<br />

<br />

<br />

| Args ||
|---|---|
| `sparse_delta` | [`tf.IndexedSlices`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/IndexedSlices) to be assigned to this variable. |
| `use_locking` | If `True`, use locking during the operation. |
| `name` | the name of the operation. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| The updated variable. ||

<br />

<br />

<br />

<br />

| Raises ||
|---|---|
| `TypeError` | if `sparse_delta` is not an `IndexedSlices`. |

<br />

### `set_shape`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/variables.py#L416-L422)

    set_shape(
        shape
    )

Overrides the shape for this variable.

<br />

<br />

<br />

| Args ||
|---|---|
| `shape` | the `TensorShape` representing the overridden shape. |

<br />

### `sparse_read`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/variables.py#L868-L882)

    sparse_read(
        indices, name=None
    )

Gather slices from params axis axis according to indices.

This function supports a subset of tf.gather, see tf.gather for details on
usage.

<br />

<br />

<br />

| Args ||
|---|---|
| `indices` | The index `Tensor`. Must be one of the following types: `int32`, `int64`. Must be in range `[0, params.shape[axis])`. |
| `name` | A name for the operation (optional). |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| A `Tensor`. Has the same type as `params`. ||

<br />

### `to_proto`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/variables.py#L1114-L1124)

    to_proto(
        export_scope=None
    )

Converts a `Variable` to a `VariableDef` protocol buffer.

<br />

<br />

<br />

| Args ||
|---|---|
| `export_scope` | Optional `string`. Name scope to remove. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| A `VariableDef` protocol buffer, or `None` if the `Variable` is not in the specified name scope. ||

<br />

### `value`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/variables.py#L386-L403)

    value()

Returns the last snapshot of this variable.

You usually do not need to call this method as all ops that need the value
of the variable call it automatically through a `convert_to_tensor()` call.

Returns a `Tensor` which holds the value of the variable. You can not
assign a new value to this tensor as it is not a reference to the variable.

To avoid copies, if the consumer of the returned value is on the same device
as the variable, this actually returns the live value of the variable, not
a copy. Updates to the variable are seen by the consumer. If the consumer
is on a different device it will get a copy of the variable.

<br />

<br />

<br />

| Returns ||
|---|---|
| A `Tensor` containing the value of the variable. ||

<br />

### `__abs__`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/math_ops.py#L365-L409)

    __abs__(
        name=None
    )

Computes the absolute value of a tensor.

Given a tensor of integer or floating-point values, this operation returns a
tensor of the same type, where each element contains the absolute value of the
corresponding element in the input.

Given a tensor `x` of complex numbers, this operation returns a tensor of type
`float32` or `float64` that is the absolute value of each element in `x`. For
a complex number \\(a + bj\\), its absolute value is computed as
\\(\\sqrt{a\^2 + b\^2}\\).

#### For example:

    # real number
    x = tf.constant([-2.25, 3.25])
    tf.abs(x)
    <tf.Tensor: shape=(2,), dtype=float32,
    numpy=array([2.25, 3.25], dtype=float32)>

    # complex number
    x = tf.constant([[-2.25 + 4.75j], [-3.25 + 5.75j]])
    tf.abs(x)
    <tf.Tensor: shape=(2, 1), dtype=float64, numpy=
    array([[5.25594901],
           [6.60492241]])>

<br />

<br />

<br />

| Args ||
|---|---|
| `x` | A `Tensor` or `SparseTensor` of type `float16`, `float32`, `float64`, `int32`, `int64`, `complex64` or `complex128`. |
| `name` | A name for the operation (optional). |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| A `Tensor` or `SparseTensor` of the same size, type and sparsity as `x`, with absolute values. Note, for `complex64` or `complex128` input, the returned `Tensor` will be of type `float32` or `float64`, respectively. ||

<br />

### `__add__`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/math_ops.py#L1458-L1484)

    __add__(
        y
    )

The operation invoked by the [`Tensor.add`](https://www.tensorflow.org/api_docs/python/tf/Tensor#__add__) operator.

<br />

<br />

<br />

| Purpose in the API ||
|---|---|
| This method is exposed in TensorFlow's API so that library developers can register dispatching for [`Tensor.add`](https://www.tensorflow.org/api_docs/python/tf/Tensor#__add__) to allow it to handle custom composite tensors \& other custom objects. <br /> The API symbol is not intended to be called by users directly and does appear in TensorFlow's generated documentation. ||

<br />

<br />

<br />

<br />

| Args ||
|---|---|
| `x` | The left-hand side of the `+` operator. |
| `y` | The right-hand side of the `+` operator. |
| `name` | an optional name for the operation. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| The result of the elementwise `+` operation. ||

<br />

### `__and__`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/math_ops.py#L1458-L1484)

    __and__(
        y
    )

### `__div__`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/math_ops.py#L1458-L1484)

    __div__(
        y
    )

Divides x / y elementwise (using Python 2 division operator semantics). (deprecated)

<br />

#### Migrate to TF2

<br />

> [!CAUTION]
> **Caution:** This API was designed for TensorFlow v1. Continue reading for details on how to migrate from this API to a native TensorFlow v2 equivalent. See the [TensorFlow v1 to TensorFlow v2 migration guide](https://www.tensorflow.org/guide/migrate) for instructions on how to migrate the rest of your code.

This function is deprecated in TF2. Prefer using the Tensor division operator,
[`tf.divide`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/math/divide), or [`tf.math.divide`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/math/divide), which obey the Python 3 division operator
semantics.

<br />

<br />

#### Description

> [!WARNING]
> **Deprecated:** THIS FUNCTION IS DEPRECATED. It will be removed in a future version. Instructions for updating: Deprecated in favor of operator or tf.math.divide.

This function divides `x` and `y`, forcing Python 2 semantics. That is, if `x`
and `y` are both integers then the result will be an integer. This is in
contrast to Python 3, where division with `/` is always a float while division
with `//` is always an integer.

<br />

<br />

<br />

| Args ||
|---|---|
| `x` | `Tensor` numerator of real numeric type. |
| `y` | `Tensor` denominator of real numeric type. |
| `name` | A name for the operation (optional). |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| `x / y` returns the quotient of x and y. ||

<br />

### `__eq__`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/variables.py#L1025-L1031)

    __eq__(
        other
    )

Compares two variables element-wise for equality.

### `__floordiv__`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/math_ops.py#L1458-L1484)

    __floordiv__(
        y
    )

Divides `x / y` elementwise, rounding toward the most negative integer.

Mathematically, this is equivalent to floor(x / y). For example:
floor(8.4 / 4.0) = floor(2.1) = 2.0
floor(-8.4 / 4.0) = floor(-2.1) = -3.0
This is equivalent to the '//' operator in Python 3.0 and above.

> [!NOTE]
> **Note:** `x` and `y` must have the same type, and the result will have the same type as well.

<br />

<br />

<br />

| Args ||
|---|---|
| `x` | `Tensor` numerator of real numeric type. |
| `y` | `Tensor` denominator of real numeric type. |
| `name` | A name for the operation (optional). |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| `x / y` rounded toward -infinity. ||

<br />

<br />

<br />

<br />

| Raises ||
|---|---|
| `TypeError` | If the inputs are complex. |

<br />

### `__ge__`

    __ge__(
        y, name=None
    )

Returns the truth value of (x \>= y) element-wise.

> [!NOTE]
> **Note:** [`math.greater_equal`](https://www.tensorflow.org/api_docs/python/tf/math/greater_equal) supports broadcasting. More about broadcasting [here](http://docs.scipy.org/doc/numpy/user/basics.broadcasting.html)

#### Example:

    x = tf.constant([5, 4, 6, 7])
    y = tf.constant([5, 2, 5, 10])
    tf.math.greater_equal(x, y) ==> [True, True, True, False]

    x = tf.constant([5, 4, 6, 7])
    y = tf.constant([5])
    tf.math.greater_equal(x, y) ==> [True, False, True, True]

<br />

<br />

<br />

| Args ||
|---|---|
| `x` | A `Tensor`. Must be one of the following types: `float32`, `float64`, `int32`, `uint8`, `int16`, `int8`, `int64`, `bfloat16`, `uint16`, `half`, `uint32`, `uint64`. |
| `y` | A `Tensor`. Must have the same type as `x`. |
| `name` | A name for the operation (optional). |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| A `Tensor` of type `bool`. ||

<br />

### `__getitem__`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/array_ops.py#L1329-L1370)

    __getitem__(
        slice_spec
    )

Creates a slice helper object given a variable.

This allows creating a sub-tensor from part of the current contents
of a variable. See [`tf.Tensor.getitem`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/Tensor#__getitem__) for detailed examples
of slicing.

This function in addition also allows assignment to a sliced range.
This is similar to `__setitem__` functionality in Python. However,
the syntax is different so that the user can capture the assignment
operation for grouping or passing to `sess.run()` in TF1.
For example,

    import tensorflow as tf
    A = tf.Variable([[1,2,3], [4,5,6], [7,8,9]], dtype=tf.float32)
    print(A[:2, :2])  # => [[1,2], [4,5]]

    A[:2,:2].assign(22. * tf.ones((2, 2))))
    print(A) # => [[22, 22, 3], [22, 22, 6], [7,8,9]]

Note that assignments currently do not support NumPy broadcasting
semantics.

<br />

<br />

<br />

| Args ||
|---|---|
| `var` | An `ops.Variable` object. |
| `slice_spec` | The arguments to [`Tensor.getitem`](https://www.tensorflow.org/api_docs/python/tf/Tensor#__getitem__). |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| The appropriate slice of "tensor", based on "slice_spec". As an operator. The operator also has a `assign()` method that can be used to generate an assignment operator. ||

<br />

<br />

<br />

<br />

| Raises ||
|---|---|
| `ValueError` | If a slice range is negative size. |
| `TypeError` | TypeError: If the slice indices aren't int, slice, ellipsis, tf.newaxis or int32/int64 tensors. |

<br />

### `__gt__`

    __gt__(
        y, name=None
    )

Returns the truth value of (x \> y) element-wise.

> [!NOTE]
> **Note:** [`math.greater`](https://www.tensorflow.org/api_docs/python/tf/math/greater) supports broadcasting. More about broadcasting [here](http://docs.scipy.org/doc/numpy/user/basics.broadcasting.html)

#### Example:

    x = tf.constant([5, 4, 6])
    y = tf.constant([5, 2, 5])
    tf.math.greater(x, y) ==> [False, True, True]

    x = tf.constant([5, 4, 6])
    y = tf.constant([5])
    tf.math.greater(x, y) ==> [False, False, True]

<br />

<br />

<br />

| Args ||
|---|---|
| `x` | A `Tensor`. Must be one of the following types: `float32`, `float64`, `int32`, `uint8`, `int16`, `int8`, `int64`, `bfloat16`, `uint16`, `half`, `uint32`, `uint64`. |
| `y` | A `Tensor`. Must have the same type as `x`. |
| `name` | A name for the operation (optional). |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| A `Tensor` of type `bool`. ||

<br />

### `__invert__`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/math_ops.py#L1940-L1943)

    __invert__(
        name=None
    )

### `__iter__`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/variables.py#L1042-L1044)

    __iter__()

When executing eagerly, iterates over the value of the variable.

### `__le__`

    __le__(
        y, name=None
    )

Returns the truth value of (x \<= y) element-wise.

> [!NOTE]
> **Note:** [`math.less_equal`](https://www.tensorflow.org/api_docs/python/tf/math/less_equal) supports broadcasting. More about broadcasting [here](http://docs.scipy.org/doc/numpy/user/basics.broadcasting.html)

#### Example:

    x = tf.constant([5, 4, 6])
    y = tf.constant([5])
    tf.math.less_equal(x, y) ==> [True, True, False]

    x = tf.constant([5, 4, 6])
    y = tf.constant([5, 6, 6])
    tf.math.less_equal(x, y) ==> [True, True, True]

<br />

<br />

<br />

| Args ||
|---|---|
| `x` | A `Tensor`. Must be one of the following types: `float32`, `float64`, `int32`, `uint8`, `int16`, `int8`, `int64`, `bfloat16`, `uint16`, `half`, `uint32`, `uint64`. |
| `y` | A `Tensor`. Must have the same type as `x`. |
| `name` | A name for the operation (optional). |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| A `Tensor` of type `bool`. ||

<br />

### `__lt__`

    __lt__(
        y, name=None
    )

Returns the truth value of (x \< y) element-wise.

> [!NOTE]
> **Note:** [`math.less`](https://www.tensorflow.org/api_docs/python/tf/math/less) supports broadcasting. More about broadcasting [here](http://docs.scipy.org/doc/numpy/user/basics.broadcasting.html)

#### Example:

    x = tf.constant([5, 4, 6])
    y = tf.constant([5])
    tf.math.less(x, y) ==> [False, True, False]

    x = tf.constant([5, 4, 6])
    y = tf.constant([5, 6, 7])
    tf.math.less(x, y) ==> [False, True, True]

<br />

<br />

<br />

| Args ||
|---|---|
| `x` | A `Tensor`. Must be one of the following types: `float32`, `float64`, `int32`, `uint8`, `int16`, `int8`, `int64`, `bfloat16`, `uint16`, `half`, `uint32`, `uint64`. |
| `y` | A `Tensor`. Must have the same type as `x`. |
| `name` | A name for the operation (optional). |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| A `Tensor` of type `bool`. ||

<br />

### `__matmul__`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/math_ops.py#L1458-L1484)

    __matmul__(
        y
    )

Multiplies matrix `a` by matrix `b`, producing `a` \* `b`.

The inputs must, following any transpositions, be tensors of rank \>= 2
where the inner 2 dimensions specify valid matrix multiplication dimensions,
and any further outer dimensions specify matching batch size.

Both matrices must be of the same type. The supported types are:
`bfloat16`, `float16`, `float32`, `float64`, `int32`, `int64`,
`complex64`, `complex128`.

Either matrix can be transposed or adjointed (conjugated and transposed) on
the fly by setting one of the corresponding flag to `True`. These are `False`
by default.

If one or both of the matrices contain a lot of zeros, a more efficient
multiplication algorithm can be used by setting the corresponding
`a_is_sparse` or `b_is_sparse` flag to `True`. These are `False` by default.
This optimization is only available for plain matrices (rank-2 tensors) with
datatypes `bfloat16` or `float32`.

A simple 2-D tensor matrix multiplication:

    a = tf.constant([1, 2, 3, 4, 5, 6], shape=[2, 3])
    a  # 2-D tensor
    <tf.Tensor: shape=(2, 3), dtype=int32, numpy=
    array([[1, 2, 3],
           [4, 5, 6]], dtype=int32)>
    b = tf.constant([7, 8, 9, 10, 11, 12], shape=[3, 2])
    b  # 2-D tensor
    <tf.Tensor: shape=(3, 2), dtype=int32, numpy=
    array([[ 7,  8],
           [ 9, 10],
           [11, 12]], dtype=int32)>
    c = tf.matmul(a, b)
    c  # `a` * `b`
    <tf.Tensor: shape=(2, 2), dtype=int32, numpy=
    array([[ 58,  64],
           [139, 154]], dtype=int32)>

A batch matrix multiplication with batch shape \[2\]:

    a = tf.constant(np.arange(1, 13, dtype=np.int32), shape=[2, 2, 3])
    a  # 3-D tensor
    <tf.Tensor: shape=(2, 2, 3), dtype=int32, numpy=
    array([[[ 1,  2,  3],
            [ 4,  5,  6]],
           [[ 7,  8,  9],
            [10, 11, 12]]], dtype=int32)>
    b = tf.constant(np.arange(13, 25, dtype=np.int32), shape=[2, 3, 2])
    b  # 3-D tensor
    <tf.Tensor: shape=(2, 3, 2), dtype=int32, numpy=
    array([[[13, 14],
            [15, 16],
            [17, 18]],
           [[19, 20],
            [21, 22],
            [23, 24]]], dtype=int32)>
    c = tf.matmul(a, b)
    c  # `a` * `b`
    <tf.Tensor: shape=(2, 2, 2), dtype=int32, numpy=
    array([[[ 94, 100],
            [229, 244]],
           [[508, 532],
            [697, 730]]], dtype=int32)>

Since python \>= 3.5 the @ operator is supported
(see [PEP 465](https://www.python.org/dev/peps/pep-0465/)). In TensorFlow,
it simply calls the [`tf.matmul()`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/linalg/matmul) function, so the following lines are
equivalent:

    d = a @ b @ [[10], [11]]
    d = tf.matmul(tf.matmul(a, b), [[10], [11]])

<br />

<br />

<br />

| Args ||
|---|---|
| `a` | [`tf.Tensor`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/Tensor) of type `float16`, `float32`, `float64`, `int32`, `complex64`, `complex128` and rank \> 1. |
| `b` | [`tf.Tensor`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/Tensor) with same type and rank as `a`. |
| `transpose_a` | If `True`, `a` is transposed before multiplication. |
| `transpose_b` | If `True`, `b` is transposed before multiplication. |
| `adjoint_a` | If `True`, `a` is conjugated and transposed before multiplication. |
| `adjoint_b` | If `True`, `b` is conjugated and transposed before multiplication. |
| `a_is_sparse` | If `True`, `a` is treated as a sparse matrix. Notice, this **does not support [`tf.sparse.SparseTensor`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/sparse/SparseTensor)** , it just makes optimizations that assume most values in `a` are zero. See [`tf.sparse.sparse_dense_matmul`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/sparse/sparse_dense_matmul) for some support for [`tf.sparse.SparseTensor`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/sparse/SparseTensor) multiplication. |
| `b_is_sparse` | If `True`, `b` is treated as a sparse matrix. Notice, this **does not support [`tf.sparse.SparseTensor`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/sparse/SparseTensor)** , it just makes optimizations that assume most values in `b` are zero. See [`tf.sparse.sparse_dense_matmul`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/sparse/sparse_dense_matmul) for some support for [`tf.sparse.SparseTensor`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/sparse/SparseTensor) multiplication. |
| `output_type` | The output datatype if needed. Defaults to None in which case the output_type is the same as input type. Currently only works when input tensors are type (u)int8 and output_type can be int32. |
| `name` | Name for the operation (optional). |

<br />

<br />

| Returns ||
|---|---|
| A [`tf.Tensor`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/Tensor) of the same type as `a` and `b` where each inner-most matrix is the product of the corresponding matrices in `a` and `b`, e.g. if all transpose or adjoint attributes are `False`: <br /> `output[..., i, j] = sum_k (a[..., i, k] * b[..., k, j])`, for all indices `i`, `j`. ||
| `Note` | This is matrix product, not element-wise product. |

<br />

<br />

<br />

<br />

| Raises ||
|---|---|
| `ValueError` | If `transpose_a` and `adjoint_a`, or `transpose_b` and `adjoint_b` are both set to `True`. |
| `TypeError` | If output_type is specified but the types of `a`, `b` and `output_type` is not (u)int8, (u)int8 and int32. |

<br />

### `__mod__`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/math_ops.py#L1458-L1484)

    __mod__(
        y
    )

Returns element-wise remainder of division.

This follows Python semantics in that the
result here is consistent with a flooring divide. E.g.
`floor(x / y) * y + floormod(x, y) = x`, regardless of the signs of x and y.

> [!NOTE]
> **Note:** [`math.floormod`](https://www.tensorflow.org/api_docs/python/tf/math/floormod) supports broadcasting. More about broadcasting [here](http://docs.scipy.org/doc/numpy/user/basics.broadcasting.html)

<br />

<br />

<br />

| Args ||
|---|---|
| `x` | A `Tensor`. Must be one of the following types: `int8`, `int16`, `int32`, `int64`, `uint8`, `uint16`, `uint32`, `uint64`, `bfloat16`, `half`, `float32`, `float64`. |
| `y` | A `Tensor`. Must have the same type as `x`. |
| `name` | A name for the operation (optional). |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| A `Tensor`. Has the same type as `x`. ||

<br />

### `__mul__`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/math_ops.py#L1458-L1484)

    __mul__(
        y
    )

Dispatches cwise mul for "Dense*Dense" and "Dense*Sparse".

### `__ne__`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/variables.py#L1034-L1040)

    __ne__(
        other
    )

Compares two variables element-wise for equality.

### `__neg__`

    __neg__(
        name=None
    )

Computes numerical negative value element-wise.

I.e., \\(y = -x\\).

<br />

<br />

<br />

| Args ||
|---|---|
| `x` | A `Tensor`. Must be one of the following types: `bfloat16`, `half`, `float32`, `float64`, `int8`, `int16`, `int32`, `int64`, `complex64`, `complex128`. |
| `name` | A name for the operation (optional). |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| A `Tensor`. Has the same type as `x`. ||

<br />

### `__or__`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/math_ops.py#L1458-L1484)

    __or__(
        y
    )

### `__pow__`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/math_ops.py#L1458-L1484)

    __pow__(
        y
    )

Computes the power of one value to another.

Given a tensor `x` and a tensor `y`, this operation computes \\(x\^y\\) for
corresponding elements in `x` and `y`. For example:

    x = tf.constant([[2, 2], [3, 3]])
    y = tf.constant([[8, 16], [2, 3]])
    tf.pow(x, y)  # [[256, 65536], [9, 27]]

<br />

<br />

<br />

| Args ||
|---|---|
| `x` | A `Tensor` of type `float16`, `float32`, `float64`, `int32`, `int64`, `complex64`, or `complex128`. |
| `y` | A `Tensor` of type `float16`, `float32`, `float64`, `int32`, `int64`, `complex64`, or `complex128`. |
| `name` | A name for the operation (optional). |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| A `Tensor`. ||

<br />

### `__radd__`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/math_ops.py#L1495-L1501)

    __radd__(
        x
    )

The operation invoked by the [`Tensor.add`](https://www.tensorflow.org/api_docs/python/tf/Tensor#__add__) operator.

<br />

<br />

<br />

| Purpose in the API ||
|---|---|
| This method is exposed in TensorFlow's API so that library developers can register dispatching for [`Tensor.add`](https://www.tensorflow.org/api_docs/python/tf/Tensor#__add__) to allow it to handle custom composite tensors \& other custom objects. <br /> The API symbol is not intended to be called by users directly and does appear in TensorFlow's generated documentation. ||

<br />

<br />

<br />

<br />

| Args ||
|---|---|
| `x` | The left-hand side of the `+` operator. |
| `y` | The right-hand side of the `+` operator. |
| `name` | an optional name for the operation. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| The result of the elementwise `+` operation. ||

<br />

### `__rand__`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/math_ops.py#L1495-L1501)

    __rand__(
        x
    )

### `__rdiv__`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/math_ops.py#L1495-L1501)

    __rdiv__(
        x
    )

Divides x / y elementwise (using Python 2 division operator semantics). (deprecated)

<br />

#### Migrate to TF2

<br />

> [!CAUTION]
> **Caution:** This API was designed for TensorFlow v1. Continue reading for details on how to migrate from this API to a native TensorFlow v2 equivalent. See the [TensorFlow v1 to TensorFlow v2 migration guide](https://www.tensorflow.org/guide/migrate) for instructions on how to migrate the rest of your code.

This function is deprecated in TF2. Prefer using the Tensor division operator,
[`tf.divide`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/math/divide), or [`tf.math.divide`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/math/divide), which obey the Python 3 division operator
semantics.

<br />

<br />

#### Description

> [!WARNING]
> **Deprecated:** THIS FUNCTION IS DEPRECATED. It will be removed in a future version. Instructions for updating: Deprecated in favor of operator or tf.math.divide.

This function divides `x` and `y`, forcing Python 2 semantics. That is, if `x`
and `y` are both integers then the result will be an integer. This is in
contrast to Python 3, where division with `/` is always a float while division
with `//` is always an integer.

<br />

<br />

<br />

| Args ||
|---|---|
| `x` | `Tensor` numerator of real numeric type. |
| `y` | `Tensor` denominator of real numeric type. |
| `name` | A name for the operation (optional). |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| `x / y` returns the quotient of x and y. ||

<br />

### `__rfloordiv__`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/math_ops.py#L1495-L1501)

    __rfloordiv__(
        x
    )

Divides `x / y` elementwise, rounding toward the most negative integer.

Mathematically, this is equivalent to floor(x / y). For example:
floor(8.4 / 4.0) = floor(2.1) = 2.0
floor(-8.4 / 4.0) = floor(-2.1) = -3.0
This is equivalent to the '//' operator in Python 3.0 and above.

> [!NOTE]
> **Note:** `x` and `y` must have the same type, and the result will have the same type as well.

<br />

<br />

<br />

| Args ||
|---|---|
| `x` | `Tensor` numerator of real numeric type. |
| `y` | `Tensor` denominator of real numeric type. |
| `name` | A name for the operation (optional). |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| `x / y` rounded toward -infinity. ||

<br />

<br />

<br />

<br />

| Raises ||
|---|---|
| `TypeError` | If the inputs are complex. |

<br />

### `__rmatmul__`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/math_ops.py#L1495-L1501)

    __rmatmul__(
        x
    )

Multiplies matrix `a` by matrix `b`, producing `a` \* `b`.

The inputs must, following any transpositions, be tensors of rank \>= 2
where the inner 2 dimensions specify valid matrix multiplication dimensions,
and any further outer dimensions specify matching batch size.

Both matrices must be of the same type. The supported types are:
`bfloat16`, `float16`, `float32`, `float64`, `int32`, `int64`,
`complex64`, `complex128`.

Either matrix can be transposed or adjointed (conjugated and transposed) on
the fly by setting one of the corresponding flag to `True`. These are `False`
by default.

If one or both of the matrices contain a lot of zeros, a more efficient
multiplication algorithm can be used by setting the corresponding
`a_is_sparse` or `b_is_sparse` flag to `True`. These are `False` by default.
This optimization is only available for plain matrices (rank-2 tensors) with
datatypes `bfloat16` or `float32`.

A simple 2-D tensor matrix multiplication:

    a = tf.constant([1, 2, 3, 4, 5, 6], shape=[2, 3])
    a  # 2-D tensor
    <tf.Tensor: shape=(2, 3), dtype=int32, numpy=
    array([[1, 2, 3],
           [4, 5, 6]], dtype=int32)>
    b = tf.constant([7, 8, 9, 10, 11, 12], shape=[3, 2])
    b  # 2-D tensor
    <tf.Tensor: shape=(3, 2), dtype=int32, numpy=
    array([[ 7,  8],
           [ 9, 10],
           [11, 12]], dtype=int32)>
    c = tf.matmul(a, b)
    c  # `a` * `b`
    <tf.Tensor: shape=(2, 2), dtype=int32, numpy=
    array([[ 58,  64],
           [139, 154]], dtype=int32)>

A batch matrix multiplication with batch shape \[2\]:

    a = tf.constant(np.arange(1, 13, dtype=np.int32), shape=[2, 2, 3])
    a  # 3-D tensor
    <tf.Tensor: shape=(2, 2, 3), dtype=int32, numpy=
    array([[[ 1,  2,  3],
            [ 4,  5,  6]],
           [[ 7,  8,  9],
            [10, 11, 12]]], dtype=int32)>
    b = tf.constant(np.arange(13, 25, dtype=np.int32), shape=[2, 3, 2])
    b  # 3-D tensor
    <tf.Tensor: shape=(2, 3, 2), dtype=int32, numpy=
    array([[[13, 14],
            [15, 16],
            [17, 18]],
           [[19, 20],
            [21, 22],
            [23, 24]]], dtype=int32)>
    c = tf.matmul(a, b)
    c  # `a` * `b`
    <tf.Tensor: shape=(2, 2, 2), dtype=int32, numpy=
    array([[[ 94, 100],
            [229, 244]],
           [[508, 532],
            [697, 730]]], dtype=int32)>

Since python \>= 3.5 the @ operator is supported
(see [PEP 465](https://www.python.org/dev/peps/pep-0465/)). In TensorFlow,
it simply calls the [`tf.matmul()`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/linalg/matmul) function, so the following lines are
equivalent:

    d = a @ b @ [[10], [11]]
    d = tf.matmul(tf.matmul(a, b), [[10], [11]])

<br />

<br />

<br />

| Args ||
|---|---|
| `a` | [`tf.Tensor`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/Tensor) of type `float16`, `float32`, `float64`, `int32`, `complex64`, `complex128` and rank \> 1. |
| `b` | [`tf.Tensor`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/Tensor) with same type and rank as `a`. |
| `transpose_a` | If `True`, `a` is transposed before multiplication. |
| `transpose_b` | If `True`, `b` is transposed before multiplication. |
| `adjoint_a` | If `True`, `a` is conjugated and transposed before multiplication. |
| `adjoint_b` | If `True`, `b` is conjugated and transposed before multiplication. |
| `a_is_sparse` | If `True`, `a` is treated as a sparse matrix. Notice, this **does not support [`tf.sparse.SparseTensor`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/sparse/SparseTensor)** , it just makes optimizations that assume most values in `a` are zero. See [`tf.sparse.sparse_dense_matmul`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/sparse/sparse_dense_matmul) for some support for [`tf.sparse.SparseTensor`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/sparse/SparseTensor) multiplication. |
| `b_is_sparse` | If `True`, `b` is treated as a sparse matrix. Notice, this **does not support [`tf.sparse.SparseTensor`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/sparse/SparseTensor)** , it just makes optimizations that assume most values in `b` are zero. See [`tf.sparse.sparse_dense_matmul`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/sparse/sparse_dense_matmul) for some support for [`tf.sparse.SparseTensor`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/sparse/SparseTensor) multiplication. |
| `output_type` | The output datatype if needed. Defaults to None in which case the output_type is the same as input type. Currently only works when input tensors are type (u)int8 and output_type can be int32. |
| `name` | Name for the operation (optional). |

<br />

<br />

| Returns ||
|---|---|
| A [`tf.Tensor`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/Tensor) of the same type as `a` and `b` where each inner-most matrix is the product of the corresponding matrices in `a` and `b`, e.g. if all transpose or adjoint attributes are `False`: <br /> `output[..., i, j] = sum_k (a[..., i, k] * b[..., k, j])`, for all indices `i`, `j`. ||
| `Note` | This is matrix product, not element-wise product. |

<br />

<br />

<br />

<br />

| Raises ||
|---|---|
| `ValueError` | If `transpose_a` and `adjoint_a`, or `transpose_b` and `adjoint_b` are both set to `True`. |
| `TypeError` | If output_type is specified but the types of `a`, `b` and `output_type` is not (u)int8, (u)int8 and int32. |

<br />

### `__rmod__`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/math_ops.py#L1495-L1501)

    __rmod__(
        x
    )

Returns element-wise remainder of division.

This follows Python semantics in that the
result here is consistent with a flooring divide. E.g.
`floor(x / y) * y + floormod(x, y) = x`, regardless of the signs of x and y.

> [!NOTE]
> **Note:** [`math.floormod`](https://www.tensorflow.org/api_docs/python/tf/math/floormod) supports broadcasting. More about broadcasting [here](http://docs.scipy.org/doc/numpy/user/basics.broadcasting.html)

<br />

<br />

<br />

| Args ||
|---|---|
| `x` | A `Tensor`. Must be one of the following types: `int8`, `int16`, `int32`, `int64`, `uint8`, `uint16`, `uint32`, `uint64`, `bfloat16`, `half`, `float32`, `float64`. |
| `y` | A `Tensor`. Must have the same type as `x`. |
| `name` | A name for the operation (optional). |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| A `Tensor`. Has the same type as `x`. ||

<br />

### `__rmul__`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/math_ops.py#L1495-L1501)

    __rmul__(
        x
    )

Dispatches cwise mul for "Dense*Dense" and "Dense*Sparse".

### `__ror__`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/math_ops.py#L1495-L1501)

    __ror__(
        x
    )

### `__rpow__`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/math_ops.py#L1495-L1501)

    __rpow__(
        x
    )

Computes the power of one value to another.

Given a tensor `x` and a tensor `y`, this operation computes \\(x\^y\\) for
corresponding elements in `x` and `y`. For example:

    x = tf.constant([[2, 2], [3, 3]])
    y = tf.constant([[8, 16], [2, 3]])
    tf.pow(x, y)  # [[256, 65536], [9, 27]]

<br />

<br />

<br />

| Args ||
|---|---|
| `x` | A `Tensor` of type `float16`, `float32`, `float64`, `int32`, `int64`, `complex64`, or `complex128`. |
| `y` | A `Tensor` of type `float16`, `float32`, `float64`, `int32`, `int64`, `complex64`, or `complex128`. |
| `name` | A name for the operation (optional). |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| A `Tensor`. ||

<br />

### `__rsub__`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/math_ops.py#L1495-L1501)

    __rsub__(
        x
    )

Returns x - y element-wise.

> [!NOTE]
> **Note:** [`tf.subtract`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/math/subtract) supports broadcasting. More about broadcasting [here](http://docs.scipy.org/doc/numpy/user/basics.broadcasting.html)

Both input and output have a range `(-inf, inf)`.

Example usages below.

Subtract operation between an array and a scalar:

    x = [1, 2, 3, 4, 5]
    y = 1
    tf.subtract(x, y)
    <tf.Tensor: shape=(5,), dtype=int32, numpy=array([0, 1, 2, 3, 4], dtype=int32)>
    tf.subtract(y, x)
    <tf.Tensor: shape=(5,), dtype=int32,
    numpy=array([ 0, -1, -2, -3, -4], dtype=int32)>

Note that binary `-` operator can be used instead:

    x = tf.convert_to_tensor([1, 2, 3, 4, 5])
    y = tf.convert_to_tensor(1)
    x - y
    <tf.Tensor: shape=(5,), dtype=int32, numpy=array([0, 1, 2, 3, 4], dtype=int32)>

Subtract operation between an array and a tensor of same shape:

    x = [1, 2, 3, 4, 5]
    y = tf.constant([5, 4, 3, 2, 1])
    tf.subtract(y, x)
    <tf.Tensor: shape=(5,), dtype=int32,
    numpy=array([ 4,  2,  0, -2, -4], dtype=int32)>

> [!WARNING]
> **Warning:** If one of the inputs (`x` or `y`) is a tensor and the other is a non-tensor, the non-tensor input will adopt (or get casted to) the data type of the tensor input. This can potentially cause unwanted overflow or underflow conversion.

For example,

    x = tf.constant([1, 2], dtype=tf.int8)
    y = [2**8 + 1, 2**8 + 2]
    tf.subtract(x, y)
    <tf.Tensor: shape=(2,), dtype=int8, numpy=array([0, 0], dtype=int8)>

When subtracting two input values of different shapes, [`tf.subtract`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/math/subtract) follows the
[general broadcasting rules](https://numpy.org/doc/stable/user/basics.broadcasting.html#general-broadcasting-rules)
. The two input array shapes are compared element-wise. Starting with the
trailing dimensions, the two dimensions either have to be equal or one of them
needs to be `1`.

For example,

    x = np.ones(6).reshape(2, 3, 1)
    y = np.ones(6).reshape(2, 1, 3)
    tf.subtract(x, y)
    <tf.Tensor: shape=(2, 3, 3), dtype=float64, numpy=
    array([[[0., 0., 0.],
            [0., 0., 0.],
            [0., 0., 0.]],
           [[0., 0., 0.],
            [0., 0., 0.],
            [0., 0., 0.]]])>

Example with inputs of different dimensions:

    x = np.ones(6).reshape(2, 3, 1)
    y = np.ones(6).reshape(1, 6)
    tf.subtract(x, y)
    <tf.Tensor: shape=(2, 3, 6), dtype=float64, numpy=
    array([[[0., 0., 0., 0., 0., 0.],
            [0., 0., 0., 0., 0., 0.],
            [0., 0., 0., 0., 0., 0.]],
           [[0., 0., 0., 0., 0., 0.],
            [0., 0., 0., 0., 0., 0.],
            [0., 0., 0., 0., 0., 0.]]])>

<br />

<br />

<br />

| Args ||
|---|---|
| `x` | A `Tensor`. Must be one of the following types: `bfloat16`, `half`, `float32`, `float64`, `uint8`, `int8`, `uint16`, `int16`, `int32`, `int64`, `complex64`, `complex128`, `uint32`, `uint64`. |
| `y` | A `Tensor`. Must have the same type as `x`. |
| `name` | A name for the operation (optional). |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| A `Tensor`. Has the same type as `x`. ||

<br />

### `__rtruediv__`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/math_ops.py#L1495-L1501)

    __rtruediv__(
        x
    )

Divides x / y elementwise (using Python 3 division operator semantics).

> [!NOTE]
> **Note:** Prefer using the Tensor operator or tf.divide which obey Python division operator semantics.

This function forces Python 3 division operator semantics where all integer
arguments are cast to floating types first. This op is generated by normal
`x / y` division in Python 3 and in Python 2.7 with
`from __future__ import division`. If you want integer division that rounds
down, use `x // y` or `tf.math.floordiv`.

`x` and `y` must have the same numeric type. If the inputs are floating
point, the output will have the same type. If the inputs are integral, the
inputs are cast to `float32` for `int8` and `int16` and `float64` for `int32`
and `int64` (matching the behavior of Numpy).

<br />

<br />

<br />

| Args ||
|---|---|
| `x` | `Tensor` numerator of numeric type. |
| `y` | `Tensor` denominator of numeric type. |
| `name` | A name for the operation (optional). |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| `x / y` evaluated in floating point. ||

<br />

<br />

<br />

<br />

| Raises ||
|---|---|
| `TypeError` | If `x` and `y` have different dtypes. |

<br />

### `__rxor__`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/math_ops.py#L1495-L1501)

    __rxor__(
        x
    )

### `__sub__`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/math_ops.py#L1458-L1484)

    __sub__(
        y
    )

Returns x - y element-wise.

> [!NOTE]
> **Note:** [`tf.subtract`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/math/subtract) supports broadcasting. More about broadcasting [here](http://docs.scipy.org/doc/numpy/user/basics.broadcasting.html)

Both input and output have a range `(-inf, inf)`.

Example usages below.

Subtract operation between an array and a scalar:

    x = [1, 2, 3, 4, 5]
    y = 1
    tf.subtract(x, y)
    <tf.Tensor: shape=(5,), dtype=int32, numpy=array([0, 1, 2, 3, 4], dtype=int32)>
    tf.subtract(y, x)
    <tf.Tensor: shape=(5,), dtype=int32,
    numpy=array([ 0, -1, -2, -3, -4], dtype=int32)>

Note that binary `-` operator can be used instead:

    x = tf.convert_to_tensor([1, 2, 3, 4, 5])
    y = tf.convert_to_tensor(1)
    x - y
    <tf.Tensor: shape=(5,), dtype=int32, numpy=array([0, 1, 2, 3, 4], dtype=int32)>

Subtract operation between an array and a tensor of same shape:

    x = [1, 2, 3, 4, 5]
    y = tf.constant([5, 4, 3, 2, 1])
    tf.subtract(y, x)
    <tf.Tensor: shape=(5,), dtype=int32,
    numpy=array([ 4,  2,  0, -2, -4], dtype=int32)>

> [!WARNING]
> **Warning:** If one of the inputs (`x` or `y`) is a tensor and the other is a non-tensor, the non-tensor input will adopt (or get casted to) the data type of the tensor input. This can potentially cause unwanted overflow or underflow conversion.

For example,

    x = tf.constant([1, 2], dtype=tf.int8)
    y = [2**8 + 1, 2**8 + 2]
    tf.subtract(x, y)
    <tf.Tensor: shape=(2,), dtype=int8, numpy=array([0, 0], dtype=int8)>

When subtracting two input values of different shapes, [`tf.subtract`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/math/subtract) follows the
[general broadcasting rules](https://numpy.org/doc/stable/user/basics.broadcasting.html#general-broadcasting-rules)
. The two input array shapes are compared element-wise. Starting with the
trailing dimensions, the two dimensions either have to be equal or one of them
needs to be `1`.

For example,

    x = np.ones(6).reshape(2, 3, 1)
    y = np.ones(6).reshape(2, 1, 3)
    tf.subtract(x, y)
    <tf.Tensor: shape=(2, 3, 3), dtype=float64, numpy=
    array([[[0., 0., 0.],
            [0., 0., 0.],
            [0., 0., 0.]],
           [[0., 0., 0.],
            [0., 0., 0.],
            [0., 0., 0.]]])>

Example with inputs of different dimensions:

    x = np.ones(6).reshape(2, 3, 1)
    y = np.ones(6).reshape(1, 6)
    tf.subtract(x, y)
    <tf.Tensor: shape=(2, 3, 6), dtype=float64, numpy=
    array([[[0., 0., 0., 0., 0., 0.],
            [0., 0., 0., 0., 0., 0.],
            [0., 0., 0., 0., 0., 0.]],
           [[0., 0., 0., 0., 0., 0.],
            [0., 0., 0., 0., 0., 0.],
            [0., 0., 0., 0., 0., 0.]]])>

<br />

<br />

<br />

| Args ||
|---|---|
| `x` | A `Tensor`. Must be one of the following types: `bfloat16`, `half`, `float32`, `float64`, `uint8`, `int8`, `uint16`, `int16`, `int32`, `int64`, `complex64`, `complex128`, `uint32`, `uint64`. |
| `y` | A `Tensor`. Must have the same type as `x`. |
| `name` | A name for the operation (optional). |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| A `Tensor`. Has the same type as `x`. ||

<br />

### `__truediv__`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/math_ops.py#L1458-L1484)

    __truediv__(
        y
    )

Divides x / y elementwise (using Python 3 division operator semantics).

> [!NOTE]
> **Note:** Prefer using the Tensor operator or tf.divide which obey Python division operator semantics.

This function forces Python 3 division operator semantics where all integer
arguments are cast to floating types first. This op is generated by normal
`x / y` division in Python 3 and in Python 2.7 with
`from __future__ import division`. If you want integer division that rounds
down, use `x // y` or `tf.math.floordiv`.

`x` and `y` must have the same numeric type. If the inputs are floating
point, the output will have the same type. If the inputs are integral, the
inputs are cast to `float32` for `int8` and `int16` and `float64` for `int32`
and `int64` (matching the behavior of Numpy).

<br />

<br />

<br />

| Args ||
|---|---|
| `x` | `Tensor` numerator of numeric type. |
| `y` | `Tensor` denominator of numeric type. |
| `name` | A name for the operation (optional). |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| `x / y` evaluated in floating point. ||

<br />

<br />

<br />

<br />

| Raises ||
|---|---|
| `TypeError` | If `x` and `y` have different dtypes. |

<br />

### `__xor__`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.13.1/tensorflow/python/ops/math_ops.py#L1458-L1484)

    __xor__(
        y
    )