tf.Tensor

See Stable See Nightly

TensorFlow 1 version

View source on GitHub

A tensor represents a rectangular array of data.

tf.Tensor(
    op, value_index, dtype
)

When writing a TensorFlow program, the main object you manipulate and pass around is the tf.Tensor. A tf.Tensor object represents a rectangular array of arbitrary dimension, filled with data of a specific data type.

A tf.Tensor has the following properties:

• a data type (float32, int32, or string, for example)
• a shape

Each element in the Tensor has the same data type, and the data type is always known.

In eager execution, which is the default mode in TensorFlow, results are calculated immediately.

# Compute some values using a Tensor
c = tf.constant([[1.0, 2.0], [3.0, 4.0]])
d = tf.constant([[1.0, 1.0], [0.0, 1.0]])
e = tf.matmul(c, d)
print(e)
tf.Tensor(
[[1. 3.]
 [3. 7.]], shape=(2, 2), dtype=float32)

Note that during eager execution, you may discover your Tensors are actually of type EagerTensor. This is an internal detail, but it does give you access to a useful function, numpy:

type(e)
<class '...ops.EagerTensor'>
print(e.numpy())
  [[1. 3.]
   [3. 7.]]

TensorFlow can define computations without immediately executing them, most commonly inside tf.functions, as well as in (legacy) Graph mode. In those cases, the shape (that is, the rank of the Tensor and the size of each dimension) might be only partially known.

Most operations produce tensors of fully-known shapes if the shapes of their inputs are also fully known, but in some cases it's only possible to find the shape of a tensor at execution time.

There are specialized tensors; for these, see tf.Variable, tf.constant, tf.placeholder, tf.SparseTensor, and tf.RaggedTensor.

For more on Tensors, see the guide.

c = tf.constant([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0]])
print(c.shape) # will be TensorShape([2, 3])
(2, 3)

# Raises a ValueError, because `c` and `d` do not have compatible
# inner dimensions.
>>> e = tf.matmul(c, d)
Traceback (most recent call last):
...
tensorflow.python.framework.errors_impl.InvalidArgumentError: Matrix
size-incompatible: In[0]: [2,3], In[1]: [4,2] [Op:MatMul] name: MatMul/

# This works because we have compatible shapes.
>>> f = tf.matmul(c, d, transpose_a=True, transpose_b=True)
>>> print(f.shape)
(3, 4)

Methods

consumers

View source

consumers()

Returns a list of Operations that consume this tensor.

eval

View source

eval(
    feed_dict=None, session=None
)

Evaluates this tensor in a Session.

Calling this method will execute all preceding operations that produce the inputs needed for the operation that produces this tensor.

experimental_ref

View source

experimental_ref()

DEPRECATED FUNCTION

get_shape

View source

get_shape()

Alias of tf.Tensor.shape.

ref

View source

ref()

Returns a hashable reference object to this Tensor.

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

The following will raise an exception starting 2.0

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

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

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

Instead, we can use tensor.ref().

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

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

x = tf.constant(5)
x.ref().deref()
<tf.Tensor: shape=(), dtype=int32, numpy=5>

set_shape

View source

set_shape(
    shape
)

Updates the shape of this tensor.

This method can be called multiple times, and will merge the given shape with the current shape of this tensor. It can be used to provide additional information about the shape of this tensor that cannot be inferred from the graph alone. For example, this can be used to provide additional information about the shapes of images:

_, image_data = tf.compat.v1.TFRecordReader(...).read(...)
image = tf.image.decode_png(image_data, channels=3)

# The height and width dimensions of `image` are data dependent, and
# cannot be computed without executing the op.
print(image.shape)
==> TensorShape([Dimension(None), Dimension(None), Dimension(3)])

# We know that each image in this dataset is 28 x 28 pixels.
image.set_shape([28, 28, 3])
print(image.shape)
==> TensorShape([Dimension(28), Dimension(28), Dimension(3)])

__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. For a complex number \(a + bj\), its 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)
<tf.Tensor: shape=(2, 1), dtype=float64, numpy=
array([[5.25594901],
       [6.60492241]])>

__add__

View source

__add__(
    x, y
)

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

__and__

View source

__and__(
    x, y
)

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

__bool__

View source

__bool__()

Dummy method to prevent a tensor from being used as a Python bool.

This overload raises a TypeError when the user inadvertently treats a Tensor as a boolean (most commonly in an if or while statement), in code that was not converted by AutoGraph. For example:

if tf.constant(True):  # Will raise.
  # ...

if tf.constant(5) < tf.constant(7):  # Will raise.
  # ...

__div__

View source

__div__(
    x, y
)

Divide two values using Python 2 semantics.

Used for Tensor.div.

__eq__

View source

__eq__(
    other
)

Compares two tensors element-wise for equality.

__floordiv__

View source

__floordiv__(
    x, y
)

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.

__ge__

__ge__(
    x, y, name=None
)

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]

__getitem__

View source

__getitem__(
    tensor, slice_spec, var=None
)

Overload for Tensor.getitem.

This operation extracts the specified region from the tensor. The notation is similar to NumPy with the restriction that currently only support basic indexing. That means that using a non-scalar tensor as input is not currently allowed.

Some useful examples:

# Strip leading and trailing 2 elements
foo = tf.constant([1,2,3,4,5,6])
print(foo[2:-2].eval())  # => [3,4]

# Skip every other row and reverse the order of the columns
foo = tf.constant([[1,2,3], [4,5,6], [7,8,9]])
print(foo[::2,::-1].eval())  # => [[3,2,1], [9,8,7]]

# Use scalar tensors as indices on both dimensions
print(foo[tf.constant(0), tf.constant(2)].eval())  # => 3

# Insert another dimension
foo = tf.constant([[1,2,3], [4,5,6], [7,8,9]])
print(foo[tf.newaxis, :, :].eval()) # => [[[1,2,3], [4,5,6], [7,8,9]]]
print(foo[:, tf.newaxis, :].eval()) # => [[[1,2,3]], [[4,5,6]], [[7,8,9]]]
print(foo[:, :, tf.newaxis].eval()) # => [[[1],[2],[3]], [[4],[5],[6]],
[[7],[8],[9]]]

# Ellipses (3 equivalent operations)
foo = tf.constant([[1,2,3], [4,5,6], [7,8,9]])
print(foo[tf.newaxis, :, :].eval())  # => [[[1,2,3], [4,5,6], [7,8,9]]]
print(foo[tf.newaxis, ...].eval())  # => [[[1,2,3], [4,5,6], [7,8,9]]]
print(foo[tf.newaxis].eval())  # => [[[1,2,3], [4,5,6], [7,8,9]]]

# Masks
foo = tf.constant([[1,2,3], [4,5,6], [7,8,9]])
print(foo[foo > 2].eval())  # => [3, 4, 5, 6, 7, 8, 9]

Notes:

• tf.newaxis is None as in NumPy.
• An implicit ellipsis is placed at the end of the slice_spec
• NumPy advanced indexing is currently not supported.

__gt__

__gt__(
    x, y, name=None
)

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]

__invert__

__invert__(
    x, name=None
)

Returns the truth value of NOT x element-wise.

Example:

tf.math.logical_not(tf.constant([True, False]))
<tf.Tensor: shape=(2,), dtype=bool, numpy=array([False,  True])>

__iter__

View source

__iter__()

__le__

__le__(
    x, y, name=None
)

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]

__len__

View source

__len__()

__lt__

__lt__(
    x, y, name=None
)

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]

__matmul__

View source

__matmul__(
    x, 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: 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.

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]])

__mod__

View source

__mod__(
    x, y
)

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.

__mul__

View source

__mul__(
    x, y
)

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

__ne__

View source

__ne__(
    other
)

Compares two tensors element-wise for equality.

__neg__

__neg__(
    x, name=None
)

Computes numerical negative value element-wise.

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

__nonzero__

View source

__nonzero__()

Dummy method to prevent a tensor from being used as a Python bool.

This is the Python 2.x counterpart to __bool__() above.

__or__

View source

__or__(
    x, y
)

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

__pow__

View source

__pow__(
    x, 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]]

__radd__

View source

__radd__(
    y, x
)

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

__rand__

View source

__rand__(
    y, x
)

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

__rdiv__

View source

__rdiv__(
    y, x
)

Divide two values using Python 2 semantics.

Used for Tensor.div.

__rfloordiv__

View source

__rfloordiv__(
    y, x
)

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.

__rmatmul__

View source

__rmatmul__(
    y, 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: 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.

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]])

__rmod__

View source

__rmod__(
    y, x
)

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.

__rmul__

View source

__rmul__(
    y, x
)

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

__ror__

View source

__ror__(
    y, x
)

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

__rpow__

View source

__rpow__(
    y, 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]]

__rsub__

View source

__rsub__(
    y, x
)

Returns x - y element-wise.

__rtruediv__

View source

__rtruediv__(
    y, x
)

__rxor__

View source

__rxor__(
    y, x
)

Logical XOR function.

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

The operation works for the following input types:

• Two single elements of type bool
• One tf.Tensor of type bool and one single bool, where the result will be calculated by applying logical XOR with the single element to each element in the larger Tensor.
• Two tf.Tensor objects of type bool of the same shape. In this case, the result will be the element-wise logical XOR of the two input tensors.

Usage:

a = tf.constant([True])
b = tf.constant([False])
tf.math.logical_xor(a, b)
<tf.Tensor: shape=(1,), dtype=bool, numpy=array([ True])>

c = tf.constant([True])
x = tf.constant([False, True, True, False])
tf.math.logical_xor(c, x)
<tf.Tensor: shape=(4,), dtype=bool, numpy=array([ True, False, False,  True])>

y = tf.constant([False, False, True, True])
z = tf.constant([False, True, False, True])
tf.math.logical_xor(y, z)
<tf.Tensor: shape=(4,), dtype=bool, numpy=array([False,  True,  True, False])>

__sub__

View source

__sub__(
    x, y
)

Returns x - y element-wise.

__truediv__

View source

__truediv__(
    x, y
)

__xor__

View source

__xor__(
    x, y
)

Logical XOR function.

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

The operation works for the following input types:

• Two single elements of type bool
• One tf.Tensor of type bool and one single bool, where the result will be calculated by applying logical XOR with the single element to each element in the larger Tensor.
• Two tf.Tensor objects of type bool of the same shape. In this case, the result will be the element-wise logical XOR of the two input tensors.

Usage:

a = tf.constant([True])
b = tf.constant([False])
tf.math.logical_xor(a, b)
<tf.Tensor: shape=(1,), dtype=bool, numpy=array([ True])>

c = tf.constant([True])
x = tf.constant([False, True, True, False])
tf.math.logical_xor(c, x)
<tf.Tensor: shape=(4,), dtype=bool, numpy=array([ True, False, False,  True])>

y = tf.constant([False, False, True, True])
z = tf.constant([False, True, False, True])
tf.math.logical_xor(y, z)
<tf.Tensor: shape=(4,), dtype=bool, numpy=array([False,  True,  True, False])>

Class Variables

• OVERLOADABLE_OPERATORS