<br />

Half-precision floating-point number type.

Inherits From: [`inexact`](https://www.tensorflow.org/api_docs/python/tf/experimental/numpy/inexact)

    tf.experimental.numpy.float16(
        *args, **kwargs
    )

:Character code: `'e'`
:Canonical name: `numpy.half`
:Alias on this platform (Linux x86_64): `numpy.float16`: 16-bit-precision floating-point number type: sign bit, 5 bits exponent, 10 bits mantissa.

<br />

<br />

<br />

| ## Attributes ||
|---|---|
| `T` | Scalar attribute identical to `ndarray.T`. |
| `base` | Scalar attribute identical to `ndarray.base`. |
| `data` | Pointer to start of data. |
| `device` | <br /> <br /> |
| `dtype` | Get array data-descriptor. |
| `flags` | The integer value of flags. |
| `flat` | A 1-D view of the scalar. |
| `imag` | The imaginary part of the scalar. |
| `itemsize` | The length of one element in bytes. |
| `nbytes` | <br /> <br /> |
| `ndim` | The number of array dimensions. |
| `real` | The real part of the scalar. |
| `shape` | Tuple of array dimensions. |
| `size` | The number of elements in the gentype. |
| `strides` | Tuple of bytes steps in each dimension. |

<br />

## Methods

### `all`

    all(
        axis=None, out=None, keepdims=False, *, where=True
    )

Scalar method identical to `ndarray.all`.

### `any`

    any(
        axis=None, out=None, keepdims=False, *, where=True
    )

Scalar method identical to `ndarray.any`.

### `argmax`

    argmax(
        axis=None, out=None, *, keepdims=False
    )

Scalar method identical to `ndarray.argmax`.

### `argmin`

    argmin(
        axis=None, out=None, *, keepdims=False
    )

Scalar method identical to `ndarray.argmin`.

### `argsort`

    argsort(
        axis=-1, kind=None, order=None, *, stable=None
    )

Scalar method identical to `ndarray.argsort`.

### `as_integer_ratio`

    as_integer_ratio()

half.as_integer_ratio() -\> (int, int)

Return a pair of integers, whose ratio is exactly equal to the original
floating point number, and with a positive denominator.
Raise `OverflowError` on infinities and a `ValueError` on NaNs.

    np.half(10.0).as_integer_ratio()
    (10, 1)
    np.half(0.0).as_integer_ratio()
    (0, 1)
    np.half(-.25).as_integer_ratio()
    (-1, 4)

### `astype`

    astype(
        dtype,
        order='K',
        casting='unsafe',
        subok=True,
        copy=True
    )

Scalar method identical to `ndarray.astype`.

### `byteswap`

    byteswap(
        inplace=False
    )

Scalar method identical to `ndarray.byteswap`.

### `choose`

    choose(
        choices, out=None, mode='raise'
    )

Scalar method identical to `ndarray.choose`.

### `clip`

    clip(
        min=None, max=None, out=None, **kwargs
    )

Scalar method identical to `ndarray.clip`.

### `compress`

    compress(
        condition, axis=None, out=None
    )

Scalar method identical to `ndarray.compress`.

### `conj`

    conj()

Scalar method identical to `ndarray.conj`.

### `conjugate`

    conjugate()

Scalar method identical to `ndarray.conjugate`.

### `copy`

    copy(
        order='C'
    )

Scalar method identical to `ndarray.copy`.

### `cumprod`

    cumprod(
        axis=None, dtype=None, out=None
    )

Scalar method identical to `ndarray.cumprod`.

### `cumsum`

    cumsum(
        axis=None, dtype=None, out=None
    )

Scalar method identical to `ndarray.cumsum`.

### `diagonal`

    diagonal(
        offset=0, axis1=0, axis2=1
    )

Scalar method identical to `ndarray.diagonal`.

### `dump`

    dump(
        file
    )

Scalar method identical to `ndarray.dump`.

### `dumps`

    dumps()

Scalar method identical to `ndarray.dumps`.

### `fill`

    fill(
        value
    )

Scalar method identical to `ndarray.fill`.

### `flatten`

    flatten(
        order='C'
    )

Scalar method identical to `ndarray.flatten`.

### `getfield`

    getfield(
        dtype, offset=0
    )

Scalar method identical to `ndarray.getfield`.

### `is_integer`

    is_integer()

half.is_integer() -\> bool

Return `True` if the floating point number is finite with integral
value, and `False` otherwise.

.. versionadded:: 1.22

## Examples

    >>> np.half(-2.0).is_integer()
    True
    >>> np.half(3.2).is_integer()
    False

### `item`

    item(
        *args
    )

Scalar method identical to `ndarray.item`.

### `max`

    max(
        axis=None, out=None, **kwargs
    )

Scalar method identical to `ndarray.max`.

### `mean`

    mean(
        axis=None, dtype=None, out=None, **kwargs
    )

Scalar method identical to `ndarray.mean`.

### `min`

    min(
        axis=None, out=None, **kwargs
    )

Scalar method identical to `ndarray.min`.

### `nonzero`

    nonzero()

Scalar method identical to `ndarray.nonzero`.

### `prod`

    prod(
        axis=None, dtype=None, out=None, **kwargs
    )

Scalar method identical to `ndarray.prod`.

### `put`

    put(
        indices, values, /, mode='raise'
    )

Scalar method identical to `ndarray.put`.

### `ravel`

    ravel(
        order='C'
    )

Scalar method identical to `ndarray.ravel`.

### `repeat`

    repeat(
        repeats, /, axis=None
    )

Scalar method identical to `ndarray.repeat`.

### `reshape`

    reshape(
        *shape, order='C', copy=None
    )

Scalar method identical to `ndarray.reshape`.

### `resize`

    resize(
        *new_shape, refcheck=True
    )

Scalar method identical to `ndarray.resize`.

### `round`

    round(
        decimals=0, out=None
    )

Scalar method identical to `ndarray.round`.

### `searchsorted`

    searchsorted(
        v, /, side='left', sorter=None
    )

Scalar method identical to `ndarray.searchsorted`.

### `setfield`

    setfield(
        val, /, dtype, offset=0
    )

Scalar method identical to `ndarray.setfield`.

### `setflags`

    setflags(
        *, write=None, align=None, uic=None
    )

Scalar method identical to `ndarray.setflags`.

### `sort`

    sort(
        axis=-1, kind=None, order=None, *, stable=None
    )

Scalar method identical to `ndarray.sort`.

### `squeeze`

    squeeze(
        axis=None
    )

Scalar method identical to `ndarray.squeeze`.

### `std`

    std(
        axis=None, dtype=None, out=None, ddof=0, **kwargs
    )

Scalar method identical to `ndarray.std`.

### `sum`

    sum(
        axis=None, dtype=None, out=None, **kwargs
    )

Scalar method identical to `ndarray.sum`.

### `swapaxes`

    swapaxes(
        axis1, axis2, /
    )

Scalar method identical to `ndarray.swapaxes`.

### `take`

    take(
        indices, /, axis=None, out=None, mode='raise'
    )

Scalar method identical to `ndarray.take`.

### `to_device`

    to_device(
        device, /, *, stream=None
    )

Scalar method identical to `ndarray.to_device`.

### `tobytes`

    tobytes(
        order='C'
    )

Scalar method identical to `ndarray.tobytes`.

### `tofile`

    tofile(
        fid, /, sep='', format='%s'
    )

Scalar method identical to `ndarray.tofile`.

### `tolist`

    tolist()

Scalar method identical to `ndarray.tolist`.

### `trace`

    trace(
        offset=0, axis1=0, axis2=1, dtype=None, out=None
    )

Scalar method identical to `ndarray.trace`.

### `transpose`

    transpose(
        *axes
    )

Scalar method identical to `ndarray.transpose`.

### `var`

    var(
        axis=None, dtype=None, out=None, ddof=0, **kwargs
    )

Scalar method identical to `ndarray.var`.

### `view`

    view(
        *args, **kwargs
    )

Scalar method identical to `ndarray.view`.

### `__abs__`

    __abs__()

abs(self)

### `__add__`

    __add__(
        value, /
    )

Return self+value.

### `__and__`

    __and__(
        value, /
    )

Return self\&value.

### `__array__`

    __array__()

sc.**array**(dtype) return 0-dim array from scalar with specified dtype

### `__bool__`

    __bool__()

True if self else False

### `__eq__`

    __eq__(
        value, /
    )

Return self==value.

### `__floordiv__`

    __floordiv__(
        value, /
    )

Return self//value.

### `__ge__`

    __ge__(
        value, /
    )

Return self\>=value.

### `__getitem__`

    __getitem__(
        key, /
    )

Return self\[key\].

### `__gt__`

    __gt__(
        value, /
    )

Return self\>value.

### `__invert__`

    __invert__()

\~self

### `__le__`

    __le__(
        value, /
    )

Return self\<=value.

### `__lshift__`

    __lshift__(
        value, /
    )

Return self\<\<value.

### `__lt__`

    __lt__(
        value, /
    )

Return self\<value.

### `__mod__`

    __mod__(
        value, /
    )

Return self%value.

### `__mul__`

    __mul__(
        value, /
    )

Return self\*value.

### `__ne__`

    __ne__(
        value, /
    )

Return self!=value.

### `__neg__`

    __neg__()

-self

### `__or__`

    __or__(
        value, /
    )

Return self\|value.

### `__pos__`

    __pos__()

+self

### `__pow__`

    __pow__(
        value, mod, /
    )

Return pow(self, value, mod).

### `__radd__`

    __radd__(
        value, /
    )

Return value+self.

### `__rand__`

    __rand__(
        value, /
    )

Return value\&self.

### `__rfloordiv__`

    __rfloordiv__(
        value, /
    )

Return value//self.

### `__rlshift__`

    __rlshift__(
        value, /
    )

Return value\<\<self.

### `__rmod__`

    __rmod__(
        value, /
    )

Return value%self.

### `__rmul__`

    __rmul__(
        value, /
    )

Return value\*self.

### `__ror__`

    __ror__(
        value, /
    )

Return value\|self.

### `__rpow__`

    __rpow__(
        value, mod, /
    )

Return pow(value, self, mod).

### `__rrshift__`

    __rrshift__(
        value, /
    )

Return value\>\>self.

### `__rshift__`

    __rshift__(
        value, /
    )

Return self\>\>value.

### `__rsub__`

    __rsub__(
        value, /
    )

Return value-self.

### `__rtruediv__`

    __rtruediv__(
        value, /
    )

Return value/self.

### `__rxor__`

    __rxor__(
        value, /
    )

Return value\^self.

### `__sub__`

    __sub__(
        value, /
    )

Return self-value.

### `__truediv__`

    __truediv__(
        value, /
    )

Return self/value.

### `__xor__`

    __xor__(
        value, /
    )

Return self\^value.