Module: tf

TensorFlow

pip install tensorflow

Modules

audio module: Public API for tf._api.v2.audio namespace

autodiff module: Public API for tf._api.v2.autodiff namespace

autograph module: Public API for tf._api.v2.autograph namespace

bitwise module: Public API for tf._api.v2.bitwise namespace

compat module: Public API for tf._api.v2.compat namespace

config module: Public API for tf._api.v2.config namespace

data module: Public API for tf._api.v2.data namespace

debugging module: Public API for tf._api.v2.debugging namespace

distribute module: Public API for tf._api.v2.distribute namespace

dtypes module: Public API for tf._api.v2.dtypes namespace

errors module: Public API for tf._api.v2.errors namespace

estimator module: Public API for tf_estimator.python.estimator.api._v2.estimator namespace

experimental module: Public API for tf._api.v2.experimental namespace

feature_column module: Public API for tf._api.v2.feature_column namespace

graph_util module: Public API for tf._api.v2.graph_util namespace

image module: Public API for tf._api.v2.image namespace

io module: Public API for tf._api.v2.io namespace

keras module

linalg module: Public API for tf._api.v2.linalg namespace

lite module: Public API for tf._api.v2.lite namespace

lookup module: Public API for tf._api.v2.lookup namespace

math module: Public API for tf._api.v2.math namespace

mlir module: Public API for tf._api.v2.mlir namespace

nest module: Public API for tf._api.v2.nest namespace

nn module: Public API for tf._api.v2.nn namespace

profiler module: Public API for tf._api.v2.profiler namespace

quantization module: Public API for tf._api.v2.quantization namespace

queue module: Public API for tf._api.v2.queue namespace

ragged module: Public API for tf._api.v2.ragged namespace

random module: Public API for tf._api.v2.random namespace

raw_ops module: Public API for tf._api.v2.raw_ops namespace

saved_model module: Public API for tf._api.v2.saved_model namespace

sets module: Public API for tf._api.v2.sets namespace

signal module: Public API for tf._api.v2.signal namespace

sparse module: Public API for tf._api.v2.sparse namespace

strings module: Public API for tf._api.v2.strings namespace

summary module: Operations for writing summary data, for use in analysis and visualization.

sysconfig module: Public API for tf._api.v2.sysconfig namespace

test module: Public API for tf._api.v2.test namespace

tpu module: Public API for tf._api.v2.tpu namespace

train module: Public API for tf._api.v2.train namespace

types module: Public API for tf._api.v2.types namespace

version module: Public API for tf._api.v2.version namespace

xla module: Public API for tf._api.v2.xla 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: Type specification for tf.experimental.Optional.

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.sparse.SparseTensor.

class Tensor: A tf.Tensor represents a multidimensional array of elements.

class TensorArray: Class wrapping dynamic-sized, per-time-step, Tensor arrays.

class TensorArraySpec: Type specification for a tf.TensorArray.

class TensorShape: Represents the shape of a Tensor.

class TensorSpec: Describes the type of 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 variable 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(...): Returns the element-wise sum of a list of tensors.

approx_top_k(...): Returns min/max k values and their indices of the input operand in an approximate manner.

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 tf.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 from a tensor-like object.

control_dependencies(...): Wrapper for Graph.control_dependencies() using the default graph.

conv(...): Computes a N-D convolution given (N+1+batch_dims)-D input and (N+2)-D filter tensors.

conv2d_backprop_filter_v2(...): Computes the gradients of convolution with respect to the filter.

conv2d_backprop_input_v2(...): Computes the gradients of convolution with respect to the input.

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.

eig(...): Computes the eigen decomposition of a batch of matrices.

eigvals(...): Computes the eigenvalues of one or more matrices.

einsum(...): Tensor contraction over specified indices and outer product.

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(...): Checks whether the current thread has eager execution enabled.

exp(...): Computes exponential of x element-wise. \(y = e^x\).

expand_dims(...): Returns a tensor with a length 1 axis inserted at index axis.

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.

fftnd(...): ND fast Fourier transform.

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. (deprecated argument values)

foldr(...): foldr on the list of tensors unpacked from elems on dimension 0. (deprecated argument values)

function(...): Compiles a function into a callable TensorFlow graph. (deprecated arguments) (deprecated arguments) (deprecated arguments)

gather(...): Gather slices from params axis axis according to indices. (deprecated arguments)

gather_nd(...): Gather slices from params into a Tensor with shape specified by indices.

get_current_name_scope(...): Returns current full name scope specified by tf.name_scope(...)s.

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(...): Promise to the TF runtime that the input tensor is a constant. (deprecated)

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

ifftnd(...): ND inverse fast Fourier transform.

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.

inside_function(...): Indicates whether the caller code is executing inside a tf.function.

irfftnd(...): ND inverse real fast Fourier transform.

is_symbolic_tensor(...): Test if tensor is a symbolic Tensor.

is_tensor(...): Checks whether x is a TF-native type that can be passed to many TF ops.

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

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

linspace(...): Generates evenly-spaced values in an interval along a given axis.

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(...): Transforms elems by applying fn to each element unstacked on axis 0. (deprecated arguments)

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 an element-wise x * y.

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 one (1).

ones_like(...): Creates a tensor of all ones that has the same shape as the input.

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.

ragged_fill_empty_rows(...)

ragged_fill_empty_rows_grad(...)

random_index_shuffle(...): Outputs the position of value in a permutation of [0, ..., max_index].

range(...): Creates a sequence of numbers.

rank(...): Returns the rank of a tensor.

realdiv(...): Returns x / y element-wise for real types.

recompute_grad(...): Defines a function as a recompute-checkpoint for the tape auto-diff.

reduce_all(...): Computes tf.math.logical_and of elements across dimensions of a tensor.

reduce_any(...): Computes tf.math.logical_or of elements across dimensions of a tensor.

reduce_logsumexp(...): Computes log(sum(exp(elements across dimensions of a tensor))).

reduce_max(...): Computes tf.math.maximum of elements across dimensions of a tensor.

reduce_mean(...): Computes the mean of elements across dimensions of a tensor.

reduce_min(...): Computes the tf.math.minimum of elements across dimensions of a tensor.

reduce_prod(...): Computes tf.math.multiply 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.

repeat(...): Repeat elements of input.

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.

rfftnd(...): ND fast real Fourier transform.

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. (deprecated argument values)

scatter_nd(...): Scatters updates into a tensor of shape shape according to indices.

searchsorted(...): Searches for where a value would go in a sorted sequence.

sequence_mask(...): Returns a mask tensor representing the first N positions of each cell.

shape(...): Returns a tensor containing the shape of the input tensor.

shape_n(...): Returns shape of a list 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.

size(...): Returns the size of a tensor.

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 value into a list of sub tensors.

sqrt(...): Computes element-wise square root of the input tensor.

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.

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_max(...): Apply a sparse update to a tensor taking the element-wise maximum.

tensor_scatter_nd_min(...)

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 and outer product.

tile(...): Constructs a tensor by tiling a given tensor.

timestamp(...): Provides the time since epoch in seconds.

transpose(...): Transposes a, where a is a Tensor.

truediv(...): Divides x / y elementwise (using Python 3 division operator semantics).

truncatediv(...): Returns x / y element-wise, rounded towards zero.

truncatemod(...): Returns element-wise remainder of division.

tuple(...): Groups tensors together.

type_spec_from_value(...): Returns a tf.TypeSpec that represents the given value.

unique(...): Finds unique elements in a 1-D tensor.

unique_with_counts(...): Finds unique elements in a 1-D tensor.

unravel_index(...): Converts an array of flat indices into a tuple of coordinate arrays.

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(...): Returns the indices of non-zero elements, or multiplexes x and y.

while_loop(...): Repeat body while the condition cond is true. (deprecated argument values)

zeros(...): Creates a tensor with all elements set to zero.

zeros_like(...): Creates a tensor with all elements set to zero.