tf.contrib.eager.Variable

View source on GitHub

Class Variable

Variable based on resource handles.

See the Variables How To for a high level overview.

A ResourceVariable allows you to maintain state across subsequent calls to session.run.

The ResourceVariable 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.

Just like any Tensor, variables created with tf.Variable(use_resource=True) 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.

Unlike ref-based variable, a ResourceVariable has well-defined semantics. Each usage of a ResourceVariable in a TensorFlow graph adds a read_value operation to the graph. The Tensors returned by a read_value operation are guaranteed to see all modifications to the value of the variable which happen in any operation on which the read_value depends on (either directly, indirectly, or via a control dependency) and guaranteed to not see any modification to the value of the variable from operations that depend on the read_value operation. Updates from operations that have no dependency relationship to the read_value operation might or might not be visible to read_value.

For example, if there is more than one assignment to a ResourceVariable in a single session.run call there is a well-defined value for each operation which uses the variable's value if the assignments and the read are connected by edges in the graph. Consider the following example, in which two writes can cause tf.Variable and tf.ResourceVariable to behave differently:

a = tf.Variable(1.0, use_resource=True)
a.initializer.run()

assign = a.assign(2.0)
with tf.control_dependencies([assign]):
  b = a.read_value()
with tf.control_dependencies([b]):
  other_assign = a.assign(3.0)
with tf.control_dependencies([other_assign]):
  # Will print 2.0 because the value was read before other_assign ran. If
  # `a` was a tf.Variable instead, 2.0 or 3.0 could be printed.
  tf.compat.v1.Print(b, [b]).eval()

__init__

View source

__init__(
    initial_value=None,
    trainable=None,
    collections=None,
    validate_shape=True,
    caching_device=None,
    name=None,
    dtype=None,
    variable_def=None,
    import_scope=None,
    constraint=None,
    distribute_strategy=None,
    synchronization=None,
    aggregation=None,
    shape=None
)

Creates a variable.

Args:

  • initial_value: A Tensor, or Python object convertible to a Tensor, which is the initial value for the Variable. Can also be a callable with no argument that returns the initial value when called. (Note that initializer functions from init_ops.py must first be bound to a shape before being used here.)
  • trainable: If True, the default, 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: Ignored. Provided for compatibility with tf.Variable.
  • caching_device: Optional device string or function 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.
  • 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 float32 will be used (if it is a Python object convertible to a Tensor).
  • variable_def: VariableDef protocol buffer. If not None, recreates the ResourceVariable object with its contents. variable_def and other arguments (except for import_scope) are mutually exclusive.
  • import_scope: Optional string. Name scope to add to the ResourceVariable. Only used when variable_def is provided.
  • 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.
  • distribute_strategy: The tf.distribute.Strategy this variable is being created inside of.
  • synchronization: Indicates when a distributed a variable will be aggregated. Accepted values are constants defined in the class 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.
  • 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) (representing an unspecified shape), the variable can be assigned with values of different shapes.

Raises:

  • ValueError: If the initial value is not specified, or does not have a shape and validate_shape is True.

Eager Compatibility

When Eager Execution is enabled, the default for the collections argument is None, which signifies that this Variable will not be added to any collections.

Child Classes

class SaveSliceInfo

Properties

aggregation

constraint

Returns the constraint function associated with this variable.

Returns:

The constraint function that was passed to the variable constructor. Can be None if no constraint was passed.

create

The op responsible for initializing this variable.

device

The device this variable is on.

dtype

The dtype of this variable.

graph

The Graph of this variable.

handle

The handle by which this variable can be accessed.

initial_value

Returns the Tensor used as the initial value for the variable.

initializer

The op responsible for initializing this variable.

name

The name of the handle for this variable.

op

The op for this variable.

shape

The shape of this variable.

synchronization

trainable

Methods

__abs__

View source

__abs__(
    x,
    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. All elements in x must be complex numbers of the form \(a + bj\). The absolute value is computed as \( \sqrt{a^2 + b^2}\). For example:

x = tf.constant([[-2.25 + 4.75j], [-3.25 + 5.75j]])
tf.abs(x)  # [5.25594902, 6.60492229]

Args:

  • x: A Tensor or SparseTensor of type float16, float32, float64, int32, int64, complex64 or complex128.
  • name: A name for the operation (optional).

Returns:

A Tensor or SparseTensor 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.

__add__

View source

__add__(
    a,
    *args,
    **kwargs
)

Dispatches to add for strings and add_v2 for all other types.

__and__

View source

__and__(
    a,
    *args,
    **kwargs
)

Returns the truth value of x AND y element-wise.

NOTE: math.logical_and supports broadcasting. More about broadcasting here

Args:

  • x: A Tensor of type bool.
  • y: A Tensor of type bool.
  • name: A name for the operation (optional).

Returns:

A Tensor of type bool.

__bool__

View source

__bool__()

__div__

View source

__div__(
    a,
    *args,
    **kwargs
)

Divide two values using Python 2 semantics.

Used for Tensor.div.

Args:

  • x: Tensor numerator of real numeric type.
  • y: Tensor denominator of real numeric type.
  • name: A name for the operation (optional).

Returns:

x / y returns the quotient of x and y.

__eq__

View source

__eq__(other)

Compares two variables element-wise for equality.

__floordiv__

View source

__floordiv__(
    a,
    *args,
    **kwargs
)

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

The same as tf.compat.v1.div(x,y) for integers, but uses tf.floor(tf.compat.v1.div(x,y)) for floating point arguments so that the result is always an integer (though possibly an integer represented as floating point). This op is generated by x // y floor division in Python 3 and in Python 2.7 with from __future__ import division.

x and y must have the same type, and the result will have the same type as well.

Args:

  • x: Tensor numerator of real numeric type.
  • y: Tensor denominator of real numeric type.
  • name: A name for the operation (optional).

Returns:

x / y rounded down.

Raises:

  • TypeError: If the inputs are complex.

__ge__

View source

__ge__(
    a,
    *args,
    **kwargs
)

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

NOTE: math.greater_equal supports broadcasting. More about broadcasting here

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).

Returns:

A Tensor of type bool.

__getitem__

View source

__getitem__(
    var,
    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 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(). For example,

import tensorflow as tf
A = tf.Variable([[1,2,3], [4,5,6], [7,8,9]], dtype=tf.float32)
with tf.compat.v1.Session() as sess:
  sess.run(tf.compat.v1.global_variables_initializer())
  print(sess.run(A[:2, :2]))  # => [[1,2], [4,5]]

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

Note that assignments currently do not support NumPy broadcasting semantics.

Args:

  • var: An ops.Variable object.
  • slice_spec: The arguments to Tensor.getitem.

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.

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.

__gt__

View source

__gt__(
    a,
    *args,
    **kwargs
)

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

NOTE: math.greater supports broadcasting. More about broadcasting here

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).

Returns:

A Tensor of type bool.

__invert__

View source

__invert__(
    a,
    *args,
    **kwargs
)

Returns the truth value of NOT x element-wise.

Args:

  • x: A Tensor of type bool.
  • name: A name for the operation (optional).

Returns:

A Tensor of type bool.

__iter__

View source

__iter__()

Dummy method to prevent iteration.

Do not call.

NOTE(mrry): If we register getitem as an overloaded operator, Python will valiantly attempt to iterate over the variable's Tensor from 0 to infinity. Declaring this method prevents this unintended behavior.

Raises:

  • TypeError: when invoked.

__le__

View source

__le__(
    a,
    *args,
    **kwargs
)

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

NOTE: math.less_equal supports broadcasting. More about broadcasting here

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).

Returns:

A Tensor of type bool.

__lt__

View source

__lt__(
    a,
    *args,
    **kwargs
)

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

NOTE: math.less supports broadcasting. More about broadcasting here

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).

Returns:

A Tensor of type bool.

__matmul__

View source

__matmul__(
    a,
    *args,
    **kwargs
)

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 arguments, and any further outer dimensions match.

Both matrices must be of the same type. The supported types are: float16, float32, float64, int32, 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.

For example:

# 2-D tensor `a`
# [[1, 2, 3],
#  [4, 5, 6]]
a = tf.constant([1, 2, 3, 4, 5, 6], shape=[2, 3])

# 2-D tensor `b`
# [[ 7,  8],
#  [ 9, 10],
#  [11, 12]]
b = tf.constant([7, 8, 9, 10, 11, 12], shape=[3, 2])

# `a` * `b`
# [[ 58,  64],
#  [139, 154]]
c = tf.matmul(a, b)


# 3-D tensor `a`
# [[[ 1,  2,  3],
#   [ 4,  5,  6]],
#  [[ 7,  8,  9],
#   [10, 11, 12]]]
a = tf.constant(np.arange(1, 13, dtype=np.int32),
                shape=[2, 2, 3])

# 3-D tensor `b`
# [[[13, 14],
#   [15, 16],
#   [17, 18]],
#  [[19, 20],
#   [21, 22],
#   [23, 24]]]
b = tf.constant(np.arange(13, 25, dtype=np.int32),
                shape=[2, 3, 2])

# `a` * `b`
# [[[ 94, 100],
#   [229, 244]],
#  [[508, 532],
#   [697, 730]]]
c = tf.matmul(a, b)

# Since python >= 3.5 the @ operator is supported (see PEP 465).
# In TensorFlow, it simply calls the `tf.matmul()` function, so the
# following lines are equivalent:
d = a @ b @ [[10.], [11.]]
d = tf.matmul(tf.matmul(a, b), [[10.], [11.]])

Args:

  • a: Tensor of type float16, float32, float64, int32, complex64, complex128 and rank > 1.
  • b: 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.
  • b_is_sparse: If True, b is treated as a sparse matrix.
  • name: Name for the operation (optional).

Returns:

A 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:

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.

Raises:

  • ValueError: If transpose_a and adjoint_a, or transpose_b and adjoint_b are both set to True.

__mod__

View source

__mod__(
    a,
    *args,
    **kwargs
)

Returns element-wise remainder of division. When x < 0 xor y < 0 is

true, this follows Python semantics in that the result here is consistent with a flooring divide. E.g. floor(x / y) * y + mod(x, y) = x.

NOTE: math.floormod supports broadcasting. More about broadcasting here

Args:

  • x: A Tensor. Must be one of the following types: int32, int64, bfloat16, half, float32, float64.
  • y: A Tensor. Must have the same type as x.
  • name: A name for the operation (optional).

Returns:

A Tensor. Has the same type as x.

__mul__

View source

__mul__(
    a,
    *args,
    **kwargs
)

Dispatches cwise mul for "DenseDense" and "DenseSparse".

__ne__

View source

__ne__(other)

Compares two variables element-wise for equality.

__neg__

View source

__neg__(
    a,
    *args,
    **kwargs
)

Computes numerical negative value element-wise.

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

Args:

  • x: A Tensor. Must be one of the following types: bfloat16, half, float32, float64, int32, int64, complex64, complex128.
  • name: A name for the operation (optional).

Returns:

A Tensor. Has the same type as x.

__nonzero__

View source

__nonzero__()

__or__

View source

__or__(
    a,
    *args,
    **kwargs
)

Returns the truth value of x OR y element-wise.

NOTE: math.logical_or supports broadcasting. More about broadcasting here

Args:

  • x: A Tensor of type bool.
  • y: A Tensor of type bool.
  • name: A name for the operation (optional).

Returns:

A Tensor of type bool.

__pow__

View source

__pow__(
    a,
    *args,
    **kwargs
)

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]]

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).

Returns:

A Tensor.

__radd__

View source

__radd__(
    a,
    *args,
    **kwargs
)

Dispatches to add for strings and add_v2 for all other types.

__rand__

View source

__rand__(
    a,
    *args,
    **kwargs
)

Returns the truth value of x AND y element-wise.

NOTE: math.logical_and supports broadcasting. More about broadcasting here

Args:

  • x: A Tensor of type bool.
  • y: A Tensor of type bool.
  • name: A name for the operation (optional).

Returns:

A Tensor of type bool.

__rdiv__

View source

__rdiv__(
    a,
    *args,
    **kwargs
)

Divide two values using Python 2 semantics.

Used for Tensor.div.

Args:

  • x: Tensor numerator of real numeric type.
  • y: Tensor denominator of real numeric type.
  • name: A name for the operation (optional).

Returns:

x / y returns the quotient of x and y.

__rfloordiv__

View source

__rfloordiv__(
    a,
    *args,
    **kwargs
)

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

The same as tf.compat.v1.div(x,y) for integers, but uses tf.floor(tf.compat.v1.div(x,y)) for floating point arguments so that the result is always an integer (though possibly an integer represented as floating point). This op is generated by x // y floor division in Python 3 and in Python 2.7 with from __future__ import division.

x and y must have the same type, and the result will have the same type as well.

Args:

  • x: Tensor numerator of real numeric type.
  • y: Tensor denominator of real numeric type.
  • name: A name for the operation (optional).

Returns:

x / y rounded down.

Raises:

  • TypeError: If the inputs are complex.

__rmatmul__

View source

__rmatmul__(
    a,
    *args,
    **kwargs
)

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 arguments, and any further outer dimensions match.

Both matrices must be of the same type. The supported types are: float16, float32, float64, int32, 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.

For example:

# 2-D tensor `a`
# [[1, 2, 3],
#  [4, 5, 6]]
a = tf.constant([1, 2, 3, 4, 5, 6], shape=[2, 3])

# 2-D tensor `b`
# [[ 7,  8],
#  [ 9, 10],
#  [11, 12]]
b = tf.constant([7, 8, 9, 10, 11, 12], shape=[3, 2])

# `a` * `b`
# [[ 58,  64],
#  [139, 154]]
c = tf.matmul(a, b)


# 3-D tensor `a`
# [[[ 1,  2,  3],
#   [ 4,  5,  6]],
#  [[ 7,  8,  9],
#   [10, 11, 12]]]
a = tf.constant(np.arange(1, 13, dtype=np.int32),
                shape=[2, 2, 3])

# 3-D tensor `b`
# [[[13, 14],
#   [15, 16],
#   [17, 18]],
#  [[19, 20],
#   [21, 22],
#   [23, 24]]]
b = tf.constant(np.arange(13, 25, dtype=np.int32),
                shape=[2, 3, 2])

# `a` * `b`
# [[[ 94, 100],
#   [229, 244]],
#  [[508, 532],
#   [697, 730]]]
c = tf.matmul(a, b)

# Since python >= 3.5 the @ operator is supported (see PEP 465).
# In TensorFlow, it simply calls the `tf.matmul()` function, so the
# following lines are equivalent:
d = a @ b @ [[10.], [11.]]
d = tf.matmul(tf.matmul(a, b), [[10.], [11.]])

Args:

  • a: Tensor of type float16, float32, float64, int32, complex64, complex128 and rank > 1.
  • b: 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.
  • b_is_sparse: If True, b is treated as a sparse matrix.
  • name: Name for the operation (optional).

Returns:

A 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:

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.

Raises:

  • ValueError: If transpose_a and adjoint_a, or transpose_b and adjoint_b are both set to True.

__rmod__

View source

__rmod__(
    a,
    *args,
    **kwargs
)

Returns element-wise remainder of division. When x < 0 xor y < 0 is

true, this follows Python semantics in that the result here is consistent with a flooring divide. E.g. floor(x / y) * y + mod(x, y) = x.

NOTE: math.floormod supports broadcasting. More about broadcasting here

Args:

  • x: A Tensor. Must be one of the following types: int32, int64, bfloat16, half, float32, float64.
  • y: A Tensor. Must have the same type as x.
  • name: A name for the operation (optional).

Returns:

A Tensor. Has the same type as x.

__rmul__

View source

__rmul__(
    a,
    *args,
    **kwargs
)

Dispatches cwise mul for "DenseDense" and "DenseSparse".

__ror__

View source

__ror__(
    a,
    *args,
    **kwargs
)

Returns the truth value of x OR y element-wise.

NOTE: math.logical_or supports broadcasting. More about broadcasting here

Args:

  • x: A Tensor of type bool.
  • y: A Tensor of type bool.
  • name: A name for the operation (optional).

Returns:

A Tensor of type bool.

__rpow__

View source

__rpow__(
    a,
    *args,
    **kwargs
)

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]]

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).

Returns:

A Tensor.

__rsub__

View source

__rsub__(
    a,
    *args,
    **kwargs
)

Returns x - y element-wise.

NOTE: Subtract supports broadcasting. More about broadcasting here

Args:

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

Returns:

A Tensor. Has the same type as x.

__rtruediv__

View source

__rtruediv__(
    a,
    *args,
    **kwargs
)

__rxor__

View source

__rxor__(
    a,
    *args,
    **kwargs
)

Logical XOR function.

x ^ y = (x | y) & ~(x & y)

Inputs are tensor and if the tensors contains more than one element, an element-wise logical XOR is computed.

Usage:

x = tf.constant([False, False, True, True], dtype = tf.bool)
y = tf.constant([False, True, False, True], dtype = tf.bool)
z = tf.logical_xor(x, y, name="LogicalXor")
#  here z = [False  True  True False]

Args:

  • x: A Tensor type bool.
  • y: A Tensor of type bool.

Returns:

A Tensor of type bool with the same size as that of x or y.

__sub__

View source

__sub__(
    a,
    *args,
    **kwargs
)

Returns x - y element-wise.

NOTE: Subtract supports broadcasting. More about broadcasting here

Args: