tf.experimental.dtensor.DVariable

A replacement for tf.Variable which follows initial value placement.

Inherits From: Variable

tf.experimental.dtensor.DVariable(
    initial_value, *args, dtype=None, **kwargs
)

The class also handles restore/save operations in DTensor. Note that, DVariable may fall back to normal tf.Variable at this moment if initial_value is not a DTensor.

aggregation

constraint Returns the constraint function associated with this variable.
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.
save_as_bf16

shape The shape of this variable.
synchronization

trainable

Child Classes

class SaveSliceInfo

Methods

assign

View source

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

Assigns a new value to this variable.

Args
value A Tensor. The new value for this variable.
use_locking If True, use locking during the assignment.
name The name to use for the assignment.
read_value A bool. Whether to read and return the new value of the variable or not.

Returns
If read_value is True, this method will return the new value of the variable after the assignment has completed. Otherwise, when in graph mode it will return the Operation that does the assignment, and when in eager mode it will return None.

assign_add

View source

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

Adds a value to this variable.

Args
delta A Tensor. The value to add to this variable.
use_locking If True, use locking during the operation.
name The name to use for the operation.
read_value A bool. Whether to read and return the new value of the variable or not.

Returns
If read_value is True, this method will return the new value of the variable after the assignment has completed. Otherwise, when in graph mode it will return the Operation that does the assignment, and when in eager mode it will return None.

assign_sub

View source

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

Subtracts a value from this variable.

Args
delta A Tensor. The value to subtract from this variable.
use_locking If True, use locking during the operation.
name The name to use for the operation.
read_value A bool. Whether to read and return the new value of the variable or not.

Returns
If read_value is True, this method will return the new value of the variable after the assignment has completed. Otherwise, when in graph mode it will return the Operation that does the assignment, and when in eager mode it will return None.

batch_scatter_update

View source

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

Assigns 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.

Args
sparse_delta tf.IndexedSlices to be assigned to this variable.
use_locking If True, use locking during the operation.
name the name of the operation.

Returns
The updated variable.

Raises
TypeError if sparse_delta is not an IndexedSlices.

count_up_to

View source

count_up_to(
    limit
)

Increments this variable until it reaches limit. (deprecated)

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).

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

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.

eval

View source

eval(
    session=None
)

Evaluates and returns the value of this variable.

experimental_ref

View source

experimental_ref()

DEPRECATED FUNCTION

from_proto

View source

@staticmethod
from_proto(
    variable_def, import_scope=None
)

Returns a Variable object created from variable_def.

gather_nd

View source

gather_nd(
    indices, name=None
)

Reads the value of this variable sparsely, using gather_nd.

get_shape

View source

get_shape()

Alias of Variable.shape.

initialized_value

View source

initialized_value()

Returns the value of the initialized variable. (deprecated)

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)

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

is_initialized

View source

is_initialized(
    name=None
)

Checks whether a resource variable has been initialized.

Outputs boolean scalar indicating whether the tensor has been initialized.

Args
name A name for the operation (optional).

Returns
A Tensor of type bool.

load

View source

load(
    value, session=None
)

Load new value into this variable. (deprecated)

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 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]

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

Raises
ValueError Session is not passed and no default session

numpy

View source

numpy()

read_value

View source

read_value()

Constructs an op which reads the value of this variable.

Should be used when there are multiple reads, or when it is desirable to read the value only after some condition is true.

Returns
The value of the variable.

read_value_no_copy

View source

read_value_no_copy()

Constructs an op which reads the value of this variable without copy.

The variable is read without making a copy even when it has been sparsely accessed. Variables in copy-on-read mode will be converted to copy-on-write mode.

Returns
The value of the variable.

ref

View source

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

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

Adds tf.IndexedSlices to this variable.

Args
sparse_delta tf.IndexedSlices to be added to this variable.
use_locking If True, use locking during the operation.
name the name of the operation.

Returns
The updated variable.

Raises
TypeError if sparse_delta is not an IndexedSlices.

scatter_div

View source

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

Divide this variable by tf.IndexedSlices.

Args
sparse_delta tf.IndexedSlices to divide this variable by.
use_locking If True, use locking during the operation.
name the name of the operation.

Returns
The updated variable.

Raises
TypeError if sparse_delta is not an IndexedSlices.

scatter_max

View source

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

Updates this variable with the max of tf.IndexedSlices and itself.

Args
sparse_delta 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.

Returns
The updated variable.

Raises
TypeError if sparse_delta is not an IndexedSlices.

scatter_min

View source

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

Updates this variable with the min of tf.IndexedSlices and itself.

Args
sparse_delta 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.

Returns
The updated variable.

Raises
TypeError if sparse_delta is not an IndexedSlices.

scatter_mul

View source

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

Multiply this variable by tf.IndexedSlices.

Args
sparse_delta tf.IndexedSlices to multiply this variable by.
use_locking If True, use locking during the operation.
name the name of the operation.

Returns
The updated variable.

Raises
TypeError if sparse_delta is not an IndexedSlices.

scatter_nd_add

View source

scatter_nd_add(
    indices, updates, name=None
)

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

ref is a Tensor with rank P and indices is a Tensor of rank Q.

indices must be integer tensor, containing indices into ref. 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 Kth dimension of ref.

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

[d_0, ..., d_{Q-2}, ref.shape[K], ..., ref.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:

    ref = tf.Variable([1, 2, 3, 4, 5, 6, 7, 8])
    indices = tf.constant([[4], [3], [1] ,[7]])
    updates = tf.constant([9, 10, 11, 12])
    add = ref.scatter_nd_add(indices, updates)
    with tf.compat.v1.Session() as sess:
      print sess.run(add)

The resulting update to ref would look like this:

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

See tf.scatter_nd for more details about how to make updates to slices.

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.

Returns
The updated variable.

scatter_nd_max

View source

scatter_nd_max(
    indices, updates, name=None
)

Updates this variable with the max of tf.IndexedSlices and itself.

ref is a Tensor with rank P and indices is a Tensor of rank Q.

indices must be integer tensor, containing indices into ref. 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 Kth dimension of ref.

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

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

See tf.scatter_nd for more details about how to make updates to slices.

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.

Returns
The updated variable.

scatter_nd_min

View source

scatter_nd_min(
    indices, updates, name=None
)

Updates this variable with the min of tf.IndexedSlices and itself.

ref is a Tensor with rank P and indices is a Tensor of rank Q.

indices must be integer tensor, containing indices into ref. 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 Kth dimension of ref.

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

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

See tf.scatter_nd for more details about how to make updates to slices.

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.

Returns
The updated variable.

scatter_nd_sub

View source

scatter_nd_sub(
    indices, updates, name=None
)

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

ref is a Tensor with rank P and indices is a Tensor of rank Q.

indices must be integer tensor, containing indices into ref. 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 Kth dimension of ref.

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

[d_0, ..., d_{Q-2}, ref.shape[K], ..., ref.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:

    ref = tf.Variable([1, 2, 3, 4, 5, 6, 7, 8])
    indices = tf.constant([[4], [3], [1] ,[7]])
    updates = tf.constant([9, 10, 11, 12])
    op = ref.scatter_nd_sub(indices, updates)
    with tf.compat.v1.Session() as sess:
      print sess.run(op)

The resulting update to ref would look like this:

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

See tf.scatter_nd for more details about how to make updates to slices.

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.

Returns
The updated variable.

scatter_nd_update

View source

scatter_nd_update(
    indices, updates, name=None
)

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

ref is a Tensor with rank P and indices is a Tensor of rank Q.

indices must be integer tensor, containing indices into ref. 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 Kth dimension of ref.

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

[d_0, ..., d_{Q-2}, ref.shape[K], ..., ref.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:

    ref = tf.Variable([1, 2, 3, 4, 5, 6, 7, 8])
    indices = tf.constant([[4], [3], [1] ,[7]])
    updates = tf.constant([9, 10, 11, 12])
    op = ref.scatter_nd_update(indices, updates)
    with tf.compat.v1.Session() as sess:
      print sess.run(op)

The resulting update to ref would look like this:

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

See tf.scatter_nd for more details about how to make updates to slices.

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.

Returns
The updated variable.

scatter_sub

View source

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

Subtracts tf.IndexedSlices from this variable.

Args
sparse_delta tf.IndexedSlices to be subtracted from this variable.
use_locking If True, use locking during the operation.
name the name of the operation.

Returns
The updated variable.

Raises
TypeError if sparse_delta is not an IndexedSlices.

scatter_update

View source

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

Assigns tf.IndexedSlices to this variable.

Args
sparse_delta tf.IndexedSlices to be assigned to this variable.
use_locking If True, use locking during the operation.
name the name of the operation.

Returns
The updated variable.

Raises
TypeError if sparse_delta is not an IndexedSlices.

set_shape

View source

set_shape(
    shape
)

Overrides the shape for this variable.

Args
shape the TensorShape representing the overridden shape.

sparse_read

View source

sparse_read(
    indices, name=None
)

Reads the value of this variable sparsely, using gather.

to_proto

View source

to_proto(
    export_scope=None
)

Converts a ResourceVariable to a VariableDef protocol buffer.

Args
export_scope Optional string. Name scope to remove.

Raises
RuntimeError If run in EAGER mode.

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

value

View source

value()

A cached operation which reads the value of this variable.

__abs__

View source

__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]])>

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 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.

__add__

View source

__add__(
    y
)

The operation invoked by the Tensor.add operator.

Purpose in the API
This method is exposed in TensorFlow's API so that library developers can register dispatching for Tensor.add to allow it to handle custom composite tensors & other custom objects.

The API symbol is not intended to be called by users directly and does appear in TensorFlow's generated documentation.

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

Returns
The result of the elementwise + operation.

__and__

View source

__and__(
    y
)

__array__

View source

__array__(
    dtype=None
)

Allows direct conversion to a numpy array.

np.array(tf.Variable([1.0]))
array([1.], dtype=float32)

Returns
The variable value as a numpy array.

__bool__

View source

__bool__()

__div__

View source

__div__(
    y
)

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

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.

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.

Migrate to TF2

This function is deprecated in TF2. Prefer using the Tensor division operator, tf.divide, or tf.math.divide, which obey the Python 3 division operator semantics.

__eq__

View source

__eq__(
    other
)

Compares two variables element-wise for equality.

__floordiv__

View source

__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.

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 toward -infinity.

Raises
TypeError If the inputs are complex.

__ge__

__ge__(
    y: _atypes.TensorFuzzingAnnotation[TV_GreaterEqual_T], name=None
) -> _atypes.TensorFuzzingAnnotation[_atypes.Bool]

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

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]

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__(
    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() 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.

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__

__gt__(
    y: _atypes.TensorFuzzingAnnotation[TV_Greater_T], name=None
) -> _atypes.TensorFuzzingAnnotation[_atypes.Bool]

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

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]

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__(
    name=None
)

__iter__

View source

__iter__()

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

__le__

__le__(
    y: _atypes.TensorFuzzingAnnotation[TV_LessEqual_T], name=None
) -> _atypes.TensorFuzzingAnnotation[_atypes.Bool]

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

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]

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__

__lt__(
    y: _atypes.TensorFuzzingAnnotation[TV_Less_T], name=None
) -> _atypes.TensorFuzzingAnnotation[_atypes.Bool]

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

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]

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__(
    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). 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 tf.Tensor of type float16, float32, float64, int32, complex64, complex128 and rank > 1.
b 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, it just makes optimizations that assume most values in a are zero. See tf.sparse.sparse_dense_matmul for some support for tf.sparse.SparseTensor multiplication.
b_is_sparse If True, b is treated as a sparse matrix. Notice, this does not support tf.sparse.SparseTensor, it just makes optimizations that assume most values in b are zero. See tf.sparse.sparse_dense_matmul for some support for 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).

Returns
A 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:

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.
TypeError If output_type is specified but the types of a, b and output_type is not (u)int8, (u)int8 and int32.

__mod__

View source

__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.

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).

Returns
A Tensor. Has the same type as x.

__mul__

View source

__mul__(
    y
)

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

__ne__

View source

__ne__(
    other
)

Compares two variables element-wise for equality.

__neg__

__neg__(
    name=None
) -> _atypes.TensorFuzzingAnnotation[TV_Neg_T]

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, int8, int16, 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__(
    y
)

__pow__

View source

__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]]

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__(
    x
)

The operation invoked by the Tensor.add operator.

Purpose in the API
This method is exposed in TensorFlow's API so that library developers can register dispatching for Tensor.add to allow it to handle custom composite tensors & other custom objects.

The API symbol is not intended to be called by users directly and does appear in TensorFlow's generated documentation.

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

Returns
The result of the elementwise + operation.

__rand__

View source

__rand__(
    x
)

__rdiv__

View source

__rdiv__(
    x
)

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

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.

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.

Migrate to TF2

This function is deprecated in TF2. Prefer using the Tensor division operator, tf.divide, or tf.math.divide, which obey the Python 3 division operator semantics.

__rfloordiv__

View source

__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.

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 toward -infinity.

Raises
TypeError If the inputs are complex.

__rmatmul__

View source

__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). 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 tf.Tensor of type float16, float32, float64, int32, complex64, complex128 and rank > 1.
b 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, it just makes optimizations that assume most values in a are zero. See tf.sparse.sparse_dense_matmul for some support for tf.sparse.SparseTensor multiplication.
b_is_sparse If True, b is treated as a sparse matrix. Notice, this does not support tf.sparse.SparseTensor, it just makes optimizations that assume most values in b are zero. See tf.sparse.sparse_dense_matmul for some support for 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).

Returns
A 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:

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.
TypeError If output_type is specified but the types of a, b and output_type is not (u)int8, (u)int8 and int32.

__rmod__

View source

__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.

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).

Returns
A Tensor. Has the same type as x.

__rmul__

View source

__rmul__(
    x
)

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

__ror__

View source

__ror__(
    x
)

__rpow__

View source

__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]]

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__(
    x
)

Returns x - y element-wise.

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)>

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 follows the 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.]]])>

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).

Returns
A Tensor. Has the same type as x.

__rtruediv__

View source

__rtruediv__(
    x
)

Divides x / y elementwise (using Python 3 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).

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

Returns
x / y evaluated in floating point.

Raises
TypeError If x and y have different dtypes.

__rxor__

View source

__rxor__(
    x
)

__sub__

View source

__sub__(
    y
)

Returns x - y element-wise.

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)>

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 follows the 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.]]])>

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).

Returns
A Tensor. Has the same type as x.

__truediv__

View source

__truediv__(
    y
)

Divides x / y elementwise (using Python 3 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).

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

Returns
x / y evaluated in floating point.

Raises
TypeError If x and y have different dtypes.

__xor__

View source

__xor__(
    y
)