Constants, Sequences, and Random Values
Note: Functions taking Tensor
arguments can also take anything accepted bytf.convert_to_tensor
.
Contents
Constants, Sequences, and Random Values
- Constant Value Tensors
- Sequences
- Random Tensors
- Examples:
tf.random_normal(shape, mean=0.0, stddev=1.0, dtype=tf.float32, seed=None, name=None)
tf.truncated_normal(shape, mean=0.0, stddev=1.0, dtype=tf.float32, seed=None, name=None)
tf.random_uniform(shape, minval=0.0, maxval=1.0, dtype=tf.float32, seed=None, name=None)
tf.random_shuffle(value, seed=None, name=None)
tf.set_random_seed(seed)
Constant Value Tensors
TensorFlow provides several operations that you can use to generate constants.
tf.zeros(shape, dtype=tf.float32, name=None)
Creates a tensor with all elements set to zero.
This operation returns a tensor of type dtype
with shape shape
andall elements set to zero.
For example:
tf.zeros([3, 4], int32) ==> [[0, 0, 0, 0], [0, 0, 0, 0], [0, 0, 0, 0]]
Args:
shape
: Either a list of integers, or a 1-DTensor
of typeint32
.dtype
: The type of an element in the resultingTensor
.name
: A name for the operation (optional).
Returns:
A Tensor
with all elements set to zero.
tf.zeros_like(tensor, dtype=None, name=None)
Creates a tensor with all elements set to zero.
Given a single tensor (tensor
), this operation returns a tensor of thesame type and shape as tensor
with all elements set to zero. Optionally,you can use dtype
to specify a new type for the returned tensor.
For example:
# 'tensor' is [[1, 2, 3], [4, 5, 6]]
tf.zeros_like(tensor) ==> [[0, 0, 0], [0, 0, 0]]
Args:
tensor
: ATensor
.-
dtype
: A type for the returnedTensor
. Must befloat32
,float64
,int8
,int16
,int32
,int64
,uint8
, orcomplex64
. -
name
: A name for the operation (optional).
Returns:
A Tensor
with all elements set to zero.
tf.ones(shape, dtype=tf.float32, name=None)
Creates a tensor with all elements set to 1.
This operation returns a tensor of type dtype
with shape shape
and allelements set to 1.
For example:
tf.ones([2, 3], int32) ==> [[1, 1, 1], [1, 1, 1]]
Args:
shape
: Either a list of integers, or a 1-DTensor
of typeint32
.dtype
: The type of an element in the resultingTensor
.name
: A name for the operation (optional).
Returns:
A Tensor
with all elements set to 1.
tf.ones_like(tensor, dtype=None, name=None)
Creates a tensor with all elements set to 1.
Given a single tensor (tensor
), this operation returns a tensor of the sametype and shape as tensor
with all elements set to 1. Optionally, you canspecify a new type (dtype
) for the returned tensor.
For example:
# 'tensor' is [[1, 2, 3], [4, 5, 6]]
tf.ones_like(tensor) ==> [[1, 1, 1], [1, 1, 1]]
Args:
tensor
: ATensor
.-
dtype
: A type for the returnedTensor
. Must befloat32
,float64
,int8
,int16
,int32
,int64
,uint8
, orcomplex64
. -
name
: A name for the operation (optional).
Returns:
A Tensor
with all elements set to 1.
tf.fill(dims, value, name=None)
Creates a tensor filled with a scalar value.
This operation creates a tensor of shape dims
and fills it with value
.
For example:
# output tensor shape needs to be [2, 3]
# so 'dims' is [2, 3]
fill(dims, 9) ==> [[9, 9, 9]
[9, 9, 9]]
Args:
dims
: ATensor
of typeint32
. 1-D. Represents the shape of the output tensor.value
: ATensor
. 0-D (scalar). Value to fill the returned tensor.name
: A name for the operation (optional).
Returns:
A Tensor
. Has the same type as value
.
tf.constant(value, dtype=None, shape=None, name='Const')
Creates a constant tensor.
The resulting tensor is populated with values of type dtype
, as specified by arguments value
and (optionally) shape
(see examples below).
The argument value
can be a constant value, or a list of values of type dtype
. If value
is a list, then the length of the list must be less than or equal to the number of elements implied by the shape
argument (if specified). In the case where the list length is less than the number of elements specified by shape
, the last element in the list will be used to fill the remaining entries.
The argument shape
is optional. If present, it specifies the dimensions of the resulting tensor. If not present, then the tensor is a scalar (0-D) if value
is a scalar, or 1-D otherwise.
If the argument dtype
is not specified, then the type is inferred from the type of value
.
For example:
# Constant 1-D Tensor populated with value list.
tensor = tf.constant([1, 2, 3, 4, 5, 6, 7]) => [1 2 3 4 5 6 7]
# Constant 2-D tensor populated with scalar value -1.
tensor = tf.constant(-1.0, shape=[2, 3]) => [[-1. -1. -1.]
[-1. -1. -1.]]
Args:
value
: A constant value (or list) of output typedtype
.
dtype
: The type of the elements of the resulting tensor.
shape
: Optional dimensions of resulting tensor.
name
: Optional name for the tensor.
Returns:
A Constant Tensor.
Sequences
tf.linspace(start, stop, num, name=None)
Generates values in an interval.
A sequence of num
evenly-spaced values are generated beginning at start
.If num > 1
, the values in the sequence increase by stop - start / num - 1
,so that the last one is exactly stop
.
For example:
tf.linspace(10.0, 12.0, 3, name="linspace") => [ 10.0 11.0 12.0]
Args:
start
: ATensor
. Must be one of the following types:float32
,float64
. First entry in the range.stop
: ATensor
. Must have the same type asstart
. Last entry in the range.num
: ATensor
of typeint32
. Number of values to generate.name
: A name for the operation (optional).
Returns:
A Tensor
. Has the same type as start
. 1-D. The generated values.
tf.range(start, limit, delta=1, name='range')
Creates a sequence of integers.
This operation creates a sequence of integers that begins at start
andextends by increments of delta
up to but not including limit
.
For example:
# 'start' is 3
# 'limit' is 18
# 'delta' is 3
tf.range(start, limit, delta) ==> [3, 6, 9, 12, 15]
Args:
start
: A 0-D (scalar) of typeint32
. First entry in sequence.limit
: A 0-D (scalar) of typeint32
. Upper limit of sequence, exclusive.delta
: A 0-DTensor
(scalar) of typeint32
. Optional. Default is 1. Number that incrementsstart
.name
: A name for the operation (optional).
Returns:
An 1-D int32
Tensor
.
Random Tensors
TensorFlow has several ops that create random tensors with differentdistributions. The random ops are stateful, and create new random values eachtime they are evaluated.
The seed
keyword argument in these functions acts in conjunction withthe graph-level random seed. Changing either the graph-level seed usingset_random_seed
or theop-level seed will change the underlying seed of these operations. Settingneither graph-level nor op-level seed, results in a random seed for alloperations.See set_random_seed
for details on the interaction between operation-level and graph-level randomseeds.
Examples:
# Create a tensor of shape [2, 3] consisting of random normal values, with mean
# -1 and standard deviation 4.
norm = tf.random_normal([2, 3], mean=-1, stddev=4)
# Shuffle the first dimension of a tensor
c = tf.constant([[1, 2], [3, 4], [5, 6]])
shuff = tf.random_shuffle(c)
# Each time we run these ops, different results are generated
sess = tf.Session()
print sess.run(norm)
print sess.run(norm)
# Set an op-level seed to generate repeatable sequences across sessions.
c = tf.constant([[1, 2], [3, 4], [5, 6]])
sess = tf.Session()
norm = tf.random_normal(c, seed=1234)
print sess.run(norm)
print sess.run(norm)
Another common use of random values is the intialization of variables. Also seethe Variables How To.
# Use random uniform values in [0, 1) as the initializer for a variable of shape
# [2, 3]. The default type is float32.
var = tf.Variable(tf.random_uniform([2, 3]), name="var")
init = tf.initialize_all_variables()
sess = tf.Session()
sess.run(init)
print sess.run(var)
tf.random_normal(shape, mean=0.0, stddev=1.0, dtype=tf.float32, seed=None, name=None)
Outputs random values from a normal distribution.
Args:
shape
: A 1-D integer Tensor or Python array. The shape of the output tensor.mean
: A 0-D Tensor or Python value of typedtype
. The mean of the normal distribution.stddev
: A 0-D Tensor or Python value of typedtype
. The standard deviation of the normal distribution.dtype
: The type of the output.seed
: A Python integer. Used to create a random seed for the distribution. Seeset_random_seed
for behavior.name
: A name for the operation (optional).
Returns:
A tensor of the specified shape filled with random normal values.
tf.truncated_normal(shape, mean=0.0, stddev=1.0, dtype=tf.float32, seed=None, name=None)
Outputs random values from a truncated normal distribution.
The generated values follow a normal distribution with specified mean andstandard deviation, except that values whose magnitude is more than 2 standarddeviations from the mean are dropped and re-picked.
Args:
shape
: A 1-D integer Tensor or Python array. The shape of the output tensor.mean
: A 0-D Tensor or Python value of typedtype
. The mean of the truncated normal distribution.stddev
: A 0-D Tensor or Python value of typedtype
. The standard deviation of the truncated normal distribution.dtype
: The type of the output.seed
: A Python integer. Used to create a random seed for the distribution. Seeset_random_seed
for behavior.name
: A name for the operation (optional).
Returns:
A tensor of the specified shape filled with random truncated normal values.
tf.random_uniform(shape, minval=0.0, maxval=1.0, dtype=tf.float32, seed=None, name=None)
Outputs random values from a uniform distribution.
The generated values follow a uniform distribution in the range[minval, maxval)
. The lower bound minval
is included in the range, whilethe upper bound maxval
is excluded.
Args:
shape
: A 1-D integer Tensor or Python array. The shape of the output tensor.minval
: A 0-D Tensor or Python value of typedtype
. The lower bound on the range of random values to generate.maxval
: A 0-D Tensor or Python value of typedtype
. The upper bound on the range of random values to generate.dtype
: The type of the output.seed
: A Python integer. Used to create a random seed for the distribution. Seeset_random_seed
for behavior.name
: A name for the operation (optional).
Returns:
A tensor of the specified shape filled with random uniform values.
tf.random_shuffle(value, seed=None, name=None)
Randomly shuffles a tensor along its first dimension.
The tensor is shuffled along dimension 0, such that each value[j]
is mappedto one and only one output[i]
. For example, a mapping that might occur for a3x2 tensor is:
[[1, 2], [[5, 6],
[3, 4], ==> [1, 2],
[5, 6]] [3, 4]]
Args:
value
: A Tensor to be shuffled.seed
: A Python integer. Used to create a random seed for the distribution. Seeset_random_seed
for behavior.name
: A name for the operation (optional).
Returns:
A tensor of same shape and type as value
, shuffled along its first dimension.
tf.set_random_seed(seed)
Sets the graph-level random seed.
Operations that rely on a random seed actually derive it from two seeds:the graph-level and operation-level seeds. This sets the graph-level seed.
Its interactions with operation-level seeds is as follows:
- If neither the graph-level nor the operation seed is set:A random seed is used for this op.
- If the graph-level seed is set, but the operation seed is not:The system deterministically picks an operation seed in conjunctionwith the graph-level seed so that it gets a unique random sequence.
- If the graph-level seed is not set, but the operation seed is set:A default graph-level seed and the specified operation seed are used todetermine the random sequence.
- If both the graph-level and the operation seed are set:Both seeds are used in conjunction to determine the random sequence.
To illustrate the user-visible effects, consider these examples:
To generate different sequences across sessions, set neithergraph-level nor op-level seeds:
a = tf.random_uniform([1])
b = tf.random_normal([1])
print "Session 1"
with tf.Session() as sess1:
print sess1.run(a) # generates 'A1'
print sess1.run(a) # generates 'A2'
print sess1.run(b) # generates 'B1'
print sess1.run(b) # generates 'B2'
print "Session 2"
with tf.Session() as sess2:
print sess2.run(a) # generates 'A3'
print sess2.run(a) # generates 'A4'
print sess2.run(b) # generates 'B3'
print sess2.run(b) # generates 'B4'
To generate the same repeatable sequence for an op across sessions, set theseed for the op:
a = tf.random_uniform([1], seed=1)
b = tf.random_normal([1])
# Repeatedly running this block with the same graph will generate the same
# sequence of values for 'a', but different sequences of values for 'b'.
print "Session 1"
with tf.Session() as sess1:
print sess1.run(a) # generates 'A1'
print sess1.run(a) # generates 'A2'
print sess1.run(b) # generates 'B1'
print sess1.run(b) # generates 'B2'
print "Session 2"
with tf.Session() as sess2:
print sess2.run(a) # generates 'A1'
print sess2.run(a) # generates 'A2'
print sess2.run(b) # generates 'B3'
print sess2.run(b) # generates 'B4'
To make the random sequences generated by all ops be repeatable acrosssessions, set a graph-level seed:
tf.set_random_seed(1234)
a = tf.random_uniform([1])
b = tf.random_normal([1])
# Repeatedly running this block with the same graph will generate different
# sequences of 'a' and 'b'.
print "Session 1"
with tf.Session() as sess1:
print sess1.run(a) # generates 'A1'
print sess1.run(a) # generates 'A2'
print sess1.run(b) # generates 'B1'
print sess1.run(b) # generates 'B2'
print "Session 2"
with tf.Session() as sess2:
print sess2.run(a) # generates 'A1'
print sess2.run(a) # generates 'A2'
print sess2.run(b) # generates 'B1'
print sess2.run(b) # generates 'B2'
Args:
seed
: integer.