TensorFlow
pip install tensorflow
Modules
audio module: Public API for tf. namespace.
autograph module: Conversion of plain Python into TensorFlow graph code.
bitwise module: Operations for manipulating the binary representations of integers.
compat module: Functions for Python 2 vs. 3 ibility.
config module: Public API for tf. namespace.
data module: tf..Dataset API for input pipelines.
debugging module: Public API for tf. namespace.
distribute module: Library for running a computation across multiple devices.
dtypes module: Public API for tf. namespace.
errors module: Exception types for TensorFlow .
estimator module: Estimator: High level tools for working with models.
experimental module: Public API for tf. namespace.
feature_column module: Public API for tf. namespace.
graph_util module: Helpers to manipulate a tensor graph in python.
image module: Image processing and decoding ops.
initializers module: Keras initializer serialization / deserialization.
io module: Public API for tf. namespace.
keras module: Implementation of the Keras API meant to be a high-level API for TensorFlow.
linalg module: Operations for linear algebra.
lite module: Public API for tf. namespace.
lookup module: Public API for tf. namespace.
losses module: Built-in loss functions.
math module: Math Operations.
metrics module: Built-in .
nest module: Public API for tf. namespace.
nn module: Wrappers for primitive Neural Net (NN) Operations.
optimizers module: Built-in optimizer classes.
quantization module: Public API for tf. namespace.
queue module: Public API for tf. namespace.
ragged module: Ragged Tensors.
random module: Public API for tf. namespace.
raw_ops module: Public API for tf. namespace.
saved_model module: Public API for tf. namespace.
sets module: Tensorflow set operations.
signal module: Signal processing operations.
sparse module: Sparse Tensor Representation.
strings module: Operations for working with string Tensors.
summary module: Operations for writing data, for use in analysis and visualization.
sysconfig module: System configuration library.
test module: Testing.
tpu module: Ops related to Tensor Processing Units.
train module: Support for ing models.
version module: Public API for tf. namespace.
xla module: Public API for tf. namespace.
Classes
class AggregationMethod: A class listing aggregation methods used to combine gradients.
class CriticalSection: Critical section.
class DType: Represents the type of the elements in a Tensor.
class DeviceSpec: Represents a (possibly partial) specification for a TensorFlow device.
class GradientTape: Record operations for automatic differentiation.
class Graph: A TensorFlow computation, represented as a dataflow graph.
class IndexedSlices: A sparse representation of a set of tensor slices at given indices.
class IndexedSlicesSpec: Type specification for a tf.IndexedSlices.
class Module: Base neural network module class.
class Operation: Represents a graph node that performs computation on tensors.
class OptionalSpec: Represents an optional potentially containing a structured value.
class RaggedTensor: Represents a ragged tensor.
class RaggedTensorSpec: Type specification for a tf.RaggedTensor.
class RegisterGradient: A decorator for registering the gradient function for an op type.
class SparseTensor: Represents a sparse tensor.
class SparseTensorSpec: Type specification for a tf.SparseTensor.
class Tensor: Represents one of the outputs of an Operation.
class TensorArray: Class wrapping dynamic-sized, per-time-step, write-once Tensor arrays.
class TensorArraySpec: Type specification for a tf.TensorArray.
class TensorShape: Represents the shape of a Tensor.
class TensorSpec: Describes a tf.Tensor.
class TypeSpec: Specifies a TensorFlow value type.
class UnconnectedGradients: Controls how gradient computation behaves when y does not depend on x.
class Variable: See the Variables Guide.
class VariableAggregation: Indicates how a distributed variable will be aggregated.
class VariableSynchronization: Indicates when a distributed variable will be synced.
class constant_initializer: Initializer that generates tensors with constant values.
class name_scope: A context manager for use when defining a Python op.
class ones_initializer: Initializer that generates tensors initialized to 1.
class random_normal_initializer: Initializer that generates tensors with a normal distribution.
class random_uniform_initializer: Initializer that generates tensors with a uniform distribution.
class zeros_initializer: Initializer that generates tensors initialized to 0.
Functions
Assert(...): Asserts that the given condition is true.
abs(...): Computes the absolute value of a tensor.
acos(...): Computes acos of x element-wise.
acosh(...): Computes inverse hyperbolic cosine of x element-wise.
add(...): Returns x + y element-wise.
add_n(...): Adds all input tensors element-wise.
argmax(...): Returns the index with the largest value across axes of a tensor.
argmin(...): Returns the index with the smallest value across axes of a tensor.
argsort(...): Returns the indices of a tensor that give its sorted order along an axis.
as_dtype(...): Converts the given type_value to a DType.
as_string(...): Converts each entry in the given tensor to strings.
asin(...): Computes the trignometric inverse sine of x element-wise.
asinh(...): Computes inverse hyperbolic sine of x element-wise.
assert_equal(...): Assert the condition x == y holds element-wise.
assert_greater(...): Assert the condition x > y holds element-wise.
assert_less(...): Assert the condition x < y holds element-wise.
assert_rank(...): Assert that x has rank equal to rank.
atan(...): Computes the trignometric inverse tangent of x element-wise.
atan2(...): Computes arctangent of y/x element-wise, respecting signs of the arguments.
atanh(...): Computes inverse hyperbolic tangent of x element-wise.
batch_to_space(...): BatchToSpace for N-D tensors of type T.
bitcast(...): Bitcasts a tensor from one type to another without copying data.
boolean_mask(...): Apply boolean mask to tensor.
broadcast_dynamic_shape(...): Computes the shape of a broadcast given symbolic shapes.
broadcast_static_shape(...): Computes the shape of a broadcast given known shapes.
broadcast_to(...): Broadcast an array for a compatible shape.
case(...): Create a case operation.
cast(...): Casts a tensor to a new type.
clip_by_global_norm(...): Clips values of multiple tensors by the ratio of the sum of their norms.
clip_by_norm(...): Clips tensor values to a maximum L2-norm.
clip_by_value(...): Clips tensor values to a specified min and max.
complex(...): Converts two real numbers to a complex number.
concat(...): Concatenates tensors along one dimension.
cond(...): Return true_fn() if the predicate pred is true else false_fn().
constant(...): Creates a constant tensor.
control_dependencies(...): Wrapper for Graph.control_dependencies() using the default graph.
convert_to_tensor(...): Converts the given value to a Tensor.
cos(...): Computes cos of x element-wise.
cosh(...): Computes hyperbolic cosine of x element-wise.
cumsum(...): Compute the cumulative sum of the tensor x along axis.
custom_gradient(...): Decorator to define a function with a custom gradient.
device(...): Specifies the device for ops created/executed in this context.
divide(...): Computes Python style division of x by y.
dynamic_partition(...): Partitions data into num_partitions tensors using indices from partitions.
dynamic_stitch(...): Interleave the values from the data tensors into a single tensor.
edit_distance(...): Computes the Levenshtein distance between sequences.
einsum(...): A generalized contraction between tensors of arbitrary dimension.
ensure_shape(...): Updates the shape of a tensor and checks at runtime that the shape holds.
equal(...): Returns the truth value of (x == y) element-wise.
executing_eagerly(...): Returns True if the current thread has eager execution enabled.
exp(...): Computes exponential of x element-wise. .
expand_dims(...): Inserts a dimension of 1 into a tensor's shape.
extract_volume_patches(...): Extract patches from input and put them in the "depth" output dimension. 3D extension of extract_image_patches.
eye(...): Construct an identity matrix, or a batch of matrices.
fill(...): Creates a tensor filled with a scalar value.
fingerprint(...): Generates fingerprint values.
floor(...): Returns element-wise largest integer not greater than x.
foldl(...): foldl on the list of tensors unpacked from elems on dimension 0.
foldr(...): foldr on the list of tensors unpacked from elems on dimension 0.
function(...): Creates a callable TensorFlow graph from a Python function.
gather(...): Gather slices from params axis axis according to indices.
gather_nd(...): Gather slices from params into a Tensor with shape specified by indices.
get_logger(...): Return TF logger instance.
get_static_value(...): Returns the constant value of the given tensor, if efficiently calculable.
grad_pass_through(...): Creates a grad-pass-through op with the forward behavior provided in f.
gradients(...): Constructs symbolic derivatives of sum of ys w.r.t. x in xs.
greater(...): Returns the truth value of (x > y) element-wise.
greater_equal(...): Returns the truth value of (x >= y) element-wise.
group(...): Create an op that groups multiple operations.
guarantee_const(...): Gives a guarantee to the TF runtime that the input tensor is a constant.
hessians(...): Constructs the Hessian of sum of ys with respect to x in xs.
histogram_fixed_width(...): Return histogram of values.
histogram_fixed_width_bins(...): Bins the given values for use in a histogram.
identity(...): Return a tensor with the same shape and contents as input.
identity_n(...): Returns a list of tensors with the same shapes and contents as the input
import_graph_def(...): Imports the graph from graph_def into the current default Graph. (deprecated arguments)
init_scope(...): A context manager that lifts ops out of control-flow scopes and function-building graphs.
is_tensor(...): Checks whether x is a tensor or "tensor-like".
less(...): Returns the truth value of (x < y) element-wise.
less_equal(...): Returns the truth value of (x <= y) element-wise.
linspace(...): Generates values in an interval.
load_library(...): Loads a TensorFlow plugin.
load_op_library(...): Loads a TensorFlow plugin, containing custom ops and kernels.
logical_and(...): Returns the truth value of x AND y element-wise.
logical_not(...): Returns the truth value of NOT x element-wise.
logical_or(...): Returns the truth value of x OR y element-wise.
make_ndarray(...): Create a numpy ndarray from a tensor.
make_tensor_proto(...): Create a TensorProto.
map_fn(...): map on the list of tensors unpacked from elems on dimension 0.
matmul(...): Multiplies matrix a by matrix b, producing a * b.
matrix_square_root(...): Computes the matrix square root of one or more square matrices:
maximum(...): Returns the max of x and y (i.e. x > y ? x : y) element-wise.
meshgrid(...): Broadcasts parameters for evaluation on an N-D grid.
minimum(...): Returns the min of x and y (i.e. x < y ? x : y) element-wise.
multiply(...): Returns x * y element-wise.
negative(...): Computes numerical negative value element-wise.
no_gradient(...): Specifies that ops of type op_type is not differentiable.
no_op(...): Does nothing. Only useful as a placeholder for control edges.
nondifferentiable_batch_function(...): Batches the computation done by the decorated function.
norm(...): Computes the norm of vectors, matrices, and tensors.
not_equal(...): Returns the truth value of (x != y) element-wise.
numpy_function(...): Wraps a python function and uses it as a TensorFlow op.
one_hot(...): Returns a one-hot tensor.
ones(...): Creates a tensor with all elements set to 1.
ones_like(...): Creates a tensor with all elements set to one.
pad(...): Pads a tensor.
parallel_stack(...): Stacks a list of rank-R tensors into one rank-(R+1) tensor in parallel.
pow(...): Computes the power of one value to another.
print(...): Print the specified inputs.
py_function(...): Wraps a python function into a TensorFlow op that executes it eagerly.
range(...): Creates a sequence of numbers.
rank(...): Returns the rank of a tensor.
realdiv(...): Returns x / y element-wise for real types.
recompute_grad(...): An eager-compatible version of recompute_grad.
reduce_all(...): Computes the "logical and" of elements across dimensions of a tensor.
reduce_any(...): Computes the "logical or" of elements across dimensions of a tensor.
reduce_logsumexp(...): Computes log(sum(exp(elements across dimensions of a tensor))).
reduce_max(...): Computes the maximum of elements across dimensions of a tensor.
reduce_mean(...): Computes the mean of elements across dimensions of a tensor.
reduce_min(...): Computes the minimum of elements across dimensions of a tensor.
reduce_prod(...): Computes the product of elements across dimensions of a tensor.
reduce_sum(...): Computes the sum of elements across dimensions of a tensor.
register_tensor_conversion_function(...): Registers a function for converting objects of base_type to Tensor.
required_space_to_batch_paddings(...): Calculate padding required to make block_shape divide input_shape.
reshape(...): Reshapes a tensor.
reverse(...): Reverses specific dimensions of a tensor.
reverse_sequence(...): Reverses variable length slices.
roll(...): Rolls the elements of a tensor along an axis.
round(...): Rounds the values of a tensor to the nearest integer, element-wise.
saturate_cast(...): Performs a safe saturating cast of value to dtype.
scalar_mul(...): Multiplies a scalar times a Tensor or IndexedSlices object.
scan(...): scan on the list of tensors unpacked from elems on dimension 0.
scatter_nd(...): Scatter updates into a new tensor according to indices.
searchsorted(...): Searches input tensor for values on the innermost dimension.
sequence_mask(...): Returns a mask tensor representing the first N positions of each cell.
shape(...): Returns the shape of a tensor.
shape_n(...): Returns shape of tensors.
sigmoid(...): Computes sigmoid of x element-wise.
sign(...): Returns an element-wise indication of the sign of a number.
sin(...): Computes sine of x element-wise.
sinh(...): Computes hyperbolic sine of x element-wise.
slice(...): Extracts a slice from a tensor.
sort(...): Sorts a tensor.
space_to_batch(...): SpaceToBatch for N-D tensors of type T.
space_to_batch_nd(...): SpaceToBatch for N-D tensors of type T.
split(...): Splits a tensor into sub tensors.
sqrt(...): Computes square root of x element-wise.
square(...): Computes square of x element-wise.
squeeze(...): Removes dimensions of size 1 from the shape of a tensor.
stack(...): Stacks a list of rank-R tensors into one rank-(R+1) tensor.
stop_gradient(...): Stops gradient computation.
strided_slice(...): Extracts a strided slice of a tensor (generalized python array indexing).
subtract(...): Returns x - y element-wise.
switch_case(...): Create a switch/case operation, i.e. an integer-indexed conditional.
tan(...): Computes tan of x element-wise.
tanh(...): Computes hyperbolic tangent of x element-wise.
tensor_scatter_nd_add(...): Adds sparse updates to an existing tensor according to indices.
tensor_scatter_nd_sub(...): Subtracts sparse updates from an existing tensor according to indices.
tensor_scatter_nd_update(...): Scatter updates into an existing tensor according to indices.
tensordot(...): Tensor contraction of a and b along specified axes.
tile(...): Constructs a tensor by tiling a given tensor.
timestamp(...): Provides the time since epoch in seconds.
transpose(...): Transposes a.
truediv(...): Divides x / y elementwise (using Python 3 division operator semantics).
truncatediv(...): Returns x / y element-wise for integer types.
truncatemod(...): Returns element-wise remainder of division. This emulates C semantics in that
tuple(...): Group tensors together.
unique(...): Finds unique elements in a 1-D tensor.
unique_with_counts(...): Finds unique elements in a 1-D tensor.
unravel_index(...): Converts a flat index or array of flat indices into a tuple of
unstack(...): Unpacks the given dimension of a rank-R tensor into rank-(R-1) tensors.
variable_creator_scope(...): Scope which defines a variable creation function to be used by variable().
vectorized_map(...): Parallel map on the list of tensors unpacked from elems on dimension 0.
where(...): Return the elements, either from x or y, depending on the condition.
while_loop(...): Repeat body while the condition cond is true.
zeros(...): Creates a tensor with all elements set to zero.
zeros_like(...): Creates a tensor with all elements set to zero.
Other Members
__version__ = '2.0.0'bfloat16boolcomplex128complex64doublefloat16float32float64halfint16int32int64int8qint16qint32qint8quint16quint8resourcestringuint16uint32uint64uint8variant