TensorFlow
Install Learn
  • Introduction
    New to TensorFlow?
  • TensorFlow
    The core open source ML library
  • For JavaScript
    TensorFlow.js for ML using JavaScript
  • For Mobile & Edge
    TensorFlow Lite for mobile and edge devices
  • For Production
    TensorFlow Extended for end-to-end ML components
API
  • TensorFlow (v2.12.0)
  • Versions…
  • TensorFlow.js
  • TensorFlow Lite
  • TFX
Resources
  • Models & datasets
    Pre-trained models and datasets built by Google and the community
  • Tools
    Ecosystem of tools to help you use TensorFlow
  • Libraries & extensions
    Libraries and extensions built on TensorFlow
  • TensorFlow Certificate program
    Differentiate yourself by demonstrating your ML proficiency
  • Learn ML
    Educational resources to learn the fundamentals of ML with TensorFlow
  • Responsible AI
    Resources and tools to integrate Responsible AI practices into your ML workflow
Community
  • Join
    Explore ways to get involved
  • Blog
    Stay up to date with all things TensorFlow
  • Forum ↗
    Discussion platform for the TensorFlow community
  • Groups
    User groups, interest groups and mailing lists
  • Contribute
    Guide for contributing to code and documentation
Why TensorFlow
  • About
  • Case studies
  • English
  • 中文 – 简体
GitHub Sign in
  • TensorFlow v1.15.0
Overview Python C++ Java
TensorFlow
  • Install
  • Learn
    • More
  • API
    • More
    • Overview
    • Python
    • C++
    • Java
  • Resources
    • More
  • Community
    • More
  • Why TensorFlow
    • More
  • GitHub
  • Overview
  • All Symbols
  • Python v1.15.0
  • tf
    • Overview
    • add_check_numerics_ops
    • add_to_collection
    • add_to_collections
    • AggregationMethod
    • all_variables
    • argsort
    • arg_max
    • arg_min
    • assert_variables_initialized
    • assign
    • assign_add
    • assign_sub
    • AttrValue
    • AttrValue.ListValue
    • batch_gather
    • batch_scatter_update
    • batch_to_space
    • batch_to_space_nd
    • bitcast
    • boolean_mask
    • broadcast_dynamic_shape
    • broadcast_static_shape
    • broadcast_to
    • case
    • cast
    • clip_by_average_norm
    • clip_by_global_norm
    • clip_by_norm
    • clip_by_value
    • colocate_with
    • concat
    • cond
    • ConditionalAccumulator
    • ConditionalAccumulatorBase
    • ConfigProto
    • ConfigProto.DeviceCountEntry
    • ConfigProto.Experimental
    • constant
    • container
    • control_dependencies
    • control_flow_v2_enabled
    • convert_to_tensor
    • convert_to_tensor_or_indexed_slices
    • convert_to_tensor_or_sparse_tensor
    • count_up_to
    • create_partitioned_variables
    • CriticalSection
    • custom_gradient
    • decode_raw
    • delete_session_tensor
    • device
    • DeviceSpec
    • Dimension
    • disable_control_flow_v2
    • disable_eager_execution
    • disable_resource_variables
    • disable_tensor_equality
    • disable_v2_behavior
    • disable_v2_tensorshape
    • div
    • dynamic_partition
    • dynamic_stitch
    • edit_distance
    • einsum
    • enable_control_flow_v2
    • enable_eager_execution
    • enable_resource_variables
    • enable_tensor_equality
    • enable_v2_behavior
    • enable_v2_tensorshape
    • ensure_shape
    • Event
    • executing_eagerly
    • expand_dims
    • extract_volume_patches
    • eye
    • fill
    • fingerprint
    • FixedLengthRecordReader
    • fixed_size_partitioner
    • floor_div
    • foldl
    • foldr
    • function
    • gather
    • gather_nd
    • get_collection
    • get_collection_ref
    • get_default_graph
    • get_default_session
    • get_local_variable
    • get_logger
    • get_session_handle
    • get_session_tensor
    • get_static_value
    • get_variable
    • get_variable_scope
    • global_variables
    • glorot_normal_initializer
    • glorot_uniform_initializer
    • GPUOptions
    • GPUOptions.Experimental
    • GPUOptions.Experimental.VirtualDevices
    • gradients
    • GradientTape
    • grad_pass_through
    • Graph
    • GraphDef
    • GraphKeys
    • GraphOptions
    • group
    • guarantee_const
    • hessians
    • HistogramProto
    • histogram_fixed_width
    • histogram_fixed_width_bins
    • identity
    • IdentityReader
    • identity_n
    • IndexedSlices
    • IndexedSlicesSpec
    • initialize_all_tables
    • initialize_all_variables
    • initialize_local_variables
    • initialize_variables
    • init_scope
    • InteractiveSession
    • is_tensor
    • is_variable_initialized
    • linspace
    • LMDBReader
    • load_file_system_library
    • load_library
    • load_op_library
    • local_variables
    • LogMessage
    • make_ndarray
    • make_template
    • make_tensor_proto
    • map_fn
    • meshgrid
    • MetaGraphDef
    • MetaGraphDef.CollectionDefEntry
    • MetaGraphDef.MetaInfoDef
    • MetaGraphDef.SignatureDefEntry
    • min_max_variable_partitioner
    • model_variables
    • Module
    • moving_average_variables
    • NameAttrList
    • NameAttrList.AttrEntry
    • name_scope
    • NodeDef
    • NodeDef.AttrEntry
    • NodeDef.ExperimentalDebugInfo
    • nondifferentiable_batch_function
    • norm
    • no_gradient
    • no_op
    • no_regularizer
    • numpy_function
    • ones
    • ones_like
    • one_hot
    • Operation
    • OptimizerOptions
    • OptionalSpec
    • op_scope
    • pad
    • parallel_stack
    • placeholder
    • placeholder_with_default
    • Print
    • print
    • py_func
    • py_function
    • quantize_v2
    • RaggedTensor
    • RaggedTensorSpec
    • random_normal_initializer
    • random_uniform_initializer
    • range
    • rank
    • ReaderBase
    • realdiv
    • recompute_grad
    • RegisterGradient
    • register_tensor_conversion_function
    • repeat
    • report_uninitialized_variables
    • required_space_to_batch_paddings
    • reset_default_graph
    • reshape
    • resource_variables_enabled
    • reverse
    • reverse_sequence
    • roll
    • RunMetadata
    • RunMetadata.FunctionGraphs
    • RunOptions
    • RunOptions.Experimental
    • scan
    • scatter_add
    • scatter_div
    • scatter_max
    • scatter_min
    • scatter_mul
    • scatter_nd
    • scatter_nd_add
    • scatter_nd_sub
    • scatter_nd_update
    • scatter_sub
    • scatter_update
    • searchsorted
    • sequence_mask
    • Session
    • SessionLog
    • setdiff1d
    • shape
    • shape_n
    • size
    • slice
    • sort
    • space_to_batch_nd
    • SparseTensorSpec
    • SparseTensorValue
    • sparse_matmul
    • sparse_to_dense
    • split
    • squeeze
    • stack
    • stop_gradient
    • strided_slice
    • string_split
    • substr
    • Summary
    • SummaryMetadata
    • SummaryMetadata.PluginData
    • switch_case
    • Tensor
    • TensorArray
    • TensorArraySpec
    • tensordot
    • TensorInfo
    • TensorInfo.CompositeTensor
    • TensorInfo.CooSparse
    • TensorShape
    • TensorSpec
    • tensor_scatter_nd_add
    • tensor_scatter_nd_sub
    • tensor_scatter_nd_update
    • TextLineReader
    • TFRecordReader
    • tile
    • timestamp
    • to_bfloat16
    • to_complex128
    • to_complex64
    • to_double
    • to_float
    • to_int32
    • to_int64
    • trainable_variables
    • transpose
    • truncatediv
    • truncatemod
    • tuple
    • TypeSpec
    • UnconnectedGradients
    • unique
    • unique_with_counts
    • unravel_index
    • unstack
    • Variable
    • Variable.SaveSliceInfo
    • VariableAggregation
    • VariableScope
    • VariableSynchronization
    • variable_axis_size_partitioner
    • variable_creator_scope
    • variable_op_scope
    • variable_scope
    • vectorized_map
    • where
    • where_v2
    • while_loop
    • WholeFileReader
    • wrap_function
    • zeros
    • zeros_initializer
    • zeros_like
  • tf.app
    • Overview
    • run
  • tf.audio
    • Overview
    • decode_wav
    • encode_wav
  • tf.autograph
    • Overview
    • set_verbosity
    • to_code
    • to_graph
    • trace
    • experimental
      • Overview
      • do_not_convert
      • Feature
  • tf.bitwise
    • Overview
    • bitwise_and
    • bitwise_or
    • bitwise_xor
    • invert
    • left_shift
    • right_shift
  • tf.compat
    • Overview
    • as_bytes
    • as_str_any
    • as_text
    • dimension_at_index
    • dimension_value
    • forward_compatibility_horizon
    • forward_compatible
    • path_to_str
    • v1
      • Overview
      • app
        • Overview
      • audio
        • Overview
      • autograph
        • Overview
        • experimental
          • Overview
      • bitwise
        • Overview
      • compat
        • Overview
      • config
        • Overview
        • experimental
          • Overview
        • optimizer
          • Overview
        • threading
          • Overview
      • data
        • Overview
        • experimental
          • Overview
      • debugging
        • Overview
      • distribute
        • Overview
        • cluster_resolver
          • Overview
        • experimental
          • Overview
      • distributions
        • Overview
      • dtypes
        • Overview
      • errors
        • Overview
      • experimental
        • Overview
      • feature_column
        • Overview
      • gfile
        • Overview
      • graph_util
        • Overview
      • image
        • Overview
      • initializers
        • Overview
      • io
        • Overview
        • gfile
          • Overview
      • layers
        • Overview
        • experimental
          • Overview
      • linalg
        • Overview
      • lite
        • Overview
        • constants
          • Overview
        • experimental
          • Overview
          • nn
            • Overview
      • logging
        • Overview
      • lookup
        • Overview
        • experimental
          • Overview
      • losses
        • Overview
      • manip
        • Overview
      • math
        • Overview
      • metrics
        • Overview
      • nest
        • Overview
      • nn
        • Overview
        • rnn_cell
          • Overview
      • profiler
        • Overview
      • python_io
        • Overview
      • quantization
        • Overview
      • queue
        • Overview
      • ragged
        • Overview
      • random
        • Overview
        • experimental
          • Overview
      • raw_ops
        • Overview
      • resource_loader
        • Overview
      • saved_model
        • Overview
        • builder
          • Overview
        • constants
          • Overview
        • experimental
          • Overview
        • loader
          • Overview
        • main_op
          • Overview
        • signature_constants
          • Overview
        • signature_def_utils
          • Overview
        • tag_constants
          • Overview
        • utils
          • Overview
      • sets
        • Overview
      • signal
        • Overview
      • sparse
        • Overview
      • spectral
        • Overview
      • strings
        • Overview
      • summary
        • Overview
      • sysconfig
        • Overview
      • test
        • Overview
      • tpu
        • Overview
        • experimental
          • Overview
      • train
        • Overview
        • experimental
          • Overview
        • queue_runner
          • Overview
      • user_ops
        • Overview
      • version
        • Overview
      • xla
        • Overview
        • experimental
          • Overview
    • v2
      • Overview
      • argmax
      • argmin
      • assert_equal
      • assert_greater
      • assert_less
      • assert_rank
      • batch_to_space
      • boolean_mask
      • case
      • cond
      • constant
      • convert_to_tensor
      • device
      • DeviceSpec
      • expand_dims
      • gather
      • gather_nd
      • gradients
      • hessians
      • name_scope
      • norm
      • ones_like
      • pad
      • reduce_all
      • reduce_any
      • reduce_logsumexp
      • reduce_max
      • reduce_mean
      • reduce_min
      • reduce_prod
      • reduce_sum
      • reverse_sequence
      • scalar_mul
      • shape
      • size
      • space_to_batch
      • squeeze
      • transpose
      • tuple
      • Variable
      • VariableAggregation
      • variable_creator_scope
      • while_loop
      • zeros_like
      • audio
        • Overview
      • autograph
        • Overview
        • to_code
        • to_graph
        • experimental
          • Overview
      • bitwise
        • Overview
      • compat
        • Overview
      • config
        • Overview
        • experimental
          • Overview
        • optimizer
          • Overview
        • threading
          • Overview
      • data
        • Overview
        • Dataset
        • FixedLengthRecordDataset
        • TextLineDataset
        • TFRecordDataset
        • experimental
          • Overview
          • choose_from_datasets
          • Counter
          • CsvDataset
          • make_batched_features_dataset
          • make_csv_dataset
          • RandomDataset
          • sample_from_datasets
          • SqlDataset
          • StatsAggregator
      • debugging
        • Overview
        • assert_all_finite
        • assert_greater_equal
        • assert_integer
        • assert_less_equal
        • assert_near
        • assert_negative
        • assert_none_equal
        • assert_non_negative
        • assert_non_positive
        • assert_positive
        • assert_rank_at_least
        • assert_rank_in
        • assert_scalar
        • assert_shapes
        • assert_type
      • distribute
        • Overview
        • MirroredStrategy
        • OneDeviceStrategy
        • Strategy
        • StrategyExtended
        • cluster_resolver
          • Overview
        • experimental
          • Overview
          • CentralStorageStrategy
          • MultiWorkerMirroredStrategy
          • ParameterServerStrategy
          • TPUStrategy
      • dtypes
        • Overview
      • errors
        • Overview
      • estimator
        • Overview
        • BaselineClassifier
        • BaselineEstimator
        • BaselineRegressor
        • classifier_parse_example_spec
        • DNNClassifier
        • DNNEstimator
        • DNNLinearCombinedClassifier
        • DNNLinearCombinedEstimator
        • DNNLinearCombinedRegressor
        • DNNRegressor
        • Estimator
        • LinearClassifier
        • LinearEstimator
        • LinearRegressor
        • regressor_parse_example_spec
        • experimental
          • Overview
          • RNNClassifier
          • RNNEstimator
        • export
          • Overview
      • experimental
        • Overview
      • feature_column
        • Overview
        • categorical_column_with_vocabulary_file
        • make_parse_example_spec
        • shared_embeddings
      • graph_util
        • Overview
      • image
        • Overview
        • crop_and_resize
        • draw_bounding_boxes
        • extract_glimpse
        • resize
        • ResizeMethod
        • resize_with_pad
        • sample_distorted_bounding_box
      • io
        • Overview
        • decode_csv
        • decode_raw
        • parse_example
        • parse_single_example
        • serialize_many_sparse
        • serialize_sparse
        • gfile
          • Overview
      • keras
        • Overview
        • activations
          • Overview
        • applications
          • Overview
          • densenet
            • Overview
          • imagenet_utils
            • Overview
          • inception_resnet_v2
            • Overview
          • inception_v3
            • Overview
          • mobilenet
            • Overview
          • mobilenet_v2
            • Overview
          • nasnet
            • Overview
          • resnet
            • Overview
          • resnet50
            • Overview
          • resnet_v2
            • Overview
          • vgg16
            • Overview
          • vgg19
            • Overview
          • xception
            • Overview
        • backend
          • Overview
          • name_scope
        • callbacks
          • Overview
          • TensorBoard
        • constraints
          • Overview
        • datasets
          • Overview
          • boston_housing
            • Overview
          • cifar10
            • Overview
          • cifar100
            • Overview
          • fashion_mnist
            • Overview
          • imdb
            • Overview
          • mnist
            • Overview
          • reuters
            • Overview
        • estimator
          • Overview
          • model_to_estimator
        • experimental
          • Overview
        • initializers
          • Overview
          • Constant
          • GlorotNormal
          • GlorotUniform
          • he_normal
          • he_uniform
          • Identity
          • Initializer
          • lecun_normal
          • lecun_uniform
          • Ones
          • Orthogonal
          • RandomNormal
          • RandomUniform
          • TruncatedNormal
          • VarianceScaling
          • Zeros
        • layers
          • Overview
          • BatchNormalization
          • DenseFeatures
          • GRU
          • GRUCell
          • LSTM
          • LSTMCell
        • losses
          • Overview
          • Reduction
        • metrics
          • Overview
        • mixed_precision
          • Overview
          • experimental
            • Overview
        • models
          • Overview
        • optimizers
          • Overview
          • schedules
            • Overview
        • preprocessing
          • Overview
          • image
            • Overview
          • sequence
            • Overview
          • text
            • Overview
        • regularizers
          • Overview
        • utils
          • Overview
        • wrappers
          • Overview
          • scikit_learn
            • Overview
      • linalg
        • Overview
        • l2_normalize
      • lite
        • Overview
        • TFLiteConverter
        • experimental
          • Overview
      • lookup
        • Overview
        • StaticHashTable
        • StaticVocabularyTable
        • experimental
          • Overview
      • math
        • Overview
        • bincount
        • confusion_matrix
        • count_nonzero
        • in_top_k
        • log_softmax
        • softmax
      • nest
        • Overview
      • nn
        • Overview
        • avg_pool2d
        • batch_norm_with_global_normalization
        • conv1d
        • conv2d
        • conv2d_transpose
        • conv3d
        • conv3d_transpose
        • convolution
        • crelu
        • depthwise_conv2d
        • depth_to_space
        • dilation2d
        • dropout
        • embedding_lookup
        • embedding_lookup_sparse
        • erosion2d
        • fractional_avg_pool
        • fractional_max_pool
        • max_pool_with_argmax
        • moments
        • nce_loss
        • pool
        • RNNCellDeviceWrapper
        • RNNCellDropoutWrapper
        • RNNCellResidualWrapper
        • safe_embedding_lookup_sparse
        • sampled_softmax_loss
        • separable_conv2d
        • sigmoid_cross_entropy_with_logits
        • softmax_cross_entropy_with_logits
        • space_to_depth
        • sparse_softmax_cross_entropy_with_logits
        • sufficient_statistics
        • weighted_cross_entropy_with_logits
        • weighted_moments
      • quantization
        • Overview
      • queue
        • Overview
      • ragged
        • Overview
      • random
        • Overview
        • poisson
        • set_seed
        • experimental
          • Overview
      • raw_ops
        • Overview
      • saved_model
        • Overview
        • contains_saved_model
      • sets
        • Overview
      • signal
        • Overview
      • sparse
        • Overview
        • add
        • concat
        • reduce_max
        • reduce_sum
        • segment_mean
        • segment_sqrt_n
        • segment_sum
        • split
      • strings
        • Overview
        • length
        • reduce_join
        • split
        • substr
        • to_hash_bucket
        • to_number
      • summary
        • Overview
        • audio
        • create_file_writer
        • create_noop_writer
        • flush
        • histogram
        • image
        • record_if
        • scalar
        • SummaryWriter
        • text
        • trace_export
        • trace_off
        • trace_on
        • write
        • experimental
          • Overview
          • get_step
          • set_step
          • summary_scope
          • write_raw_pb
      • sysconfig
        • Overview
      • test
        • Overview
        • assert_equal_graph_def
        • compute_gradient
      • tpu
        • Overview
        • experimental
          • Overview
      • train
        • Overview
        • Checkpoint
        • experimental
          • Overview
          • disable_mixed_precision_graph_rewrite
          • enable_mixed_precision_graph_rewrite
      • version
        • Overview
      • xla
        • Overview
        • experimental
          • Overview
  • tf.config
    • Overview
    • experimental_connect_to_cluster
    • experimental_connect_to_host
    • experimental_list_devices
    • experimental_run_functions_eagerly
    • get_soft_device_placement
    • set_soft_device_placement
    • experimental
      • Overview
      • get_device_policy
      • get_memory_growth
      • get_synchronous_execution
      • get_virtual_device_configuration
      • get_visible_devices
      • list_logical_devices
      • list_physical_devices
      • set_device_policy
      • set_memory_growth
      • set_synchronous_execution
      • set_virtual_device_configuration
      • set_visible_devices
      • VirtualDeviceConfiguration
    • optimizer
      • Overview
      • get_experimental_options
      • get_jit
      • set_experimental_options
      • set_jit
    • threading
      • Overview
      • get_inter_op_parallelism_threads
      • get_intra_op_parallelism_threads
      • set_inter_op_parallelism_threads
      • set_intra_op_parallelism_threads
  • tf.contrib
    • Overview
    • autograph
      • Overview
      • AutoGraphError
      • ConversionOptions
      • convert
      • converted_call
      • set_element_type
      • stack
      • StackTraceMapper
    • batching
      • Overview
    • bayesflow
      • Overview
      • monte_carlo
        • Overview
        • expectation
        • expectation_importance_sampler
        • expectation_importance_sampler_logspace
    • checkpoint
      • Overview
      • capture_dependencies
      • Checkpointable
      • CheckpointableBase
      • CheckpointableObjectGraph
      • CheckpointableObjectGraph.TrackableObject
      • CheckpointableObjectGraph.TrackableObject.ObjectReference
      • CheckpointableObjectGraph.TrackableObject.SerializedTensor
      • CheckpointableObjectGraph.TrackableObject.SlotVariableReference
      • dot_graph_from_checkpoint
      • List
      • list_objects
      • Mapping
      • NoDependency
      • NumpyState
      • object_metadata
      • split_dependency
      • UniqueNameTracker
    • cloud
      • Overview
      • BigQueryReader
      • BigtableClient
      • BigtableTable
      • BlockCacheParams
      • ConfigureGcsHook
      • configure_colab_session
      • configure_gcs
    • cluster_resolver
      • Overview
    • compiler
      • Overview
    • constrained_optimization
      • Overview
      • AdditiveExternalRegretOptimizer
      • AdditiveSwapRegretOptimizer
      • ConstrainedMinimizationProblem
      • ConstrainedOptimizer
      • find_best_candidate_distribution
      • find_best_candidate_index
      • MultiplicativeSwapRegretOptimizer
    • copy_graph
      • Overview
      • copy_op_to_graph
      • copy_variable_to_graph
      • get_copied_op
    • crf
      • Overview
      • CrfDecodeBackwardRnnCell
      • CrfDecodeForwardRnnCell
      • CrfForwardRnnCell
      • crf_binary_score
      • crf_decode
      • crf_log_likelihood
      • crf_log_norm
      • crf_multitag_sequence_score
      • crf_sequence_score
      • crf_unary_score
      • viterbi_decode
    • cudnn_rnn
      • Overview
      • CudnnCompatibleGRUCell
      • CudnnCompatibleLSTMCell
      • CudnnGRU
      • CudnnGRUSaveable
      • CudnnLSTM
      • CudnnLSTMSaveable
      • CudnnParamsFormatConverterGRU
      • CudnnParamsFormatConverterLSTM
      • CudnnParamsFormatConverterRelu
      • CudnnParamsFormatConverterTanh
      • CudnnRNNRelu
      • CudnnRNNReluSaveable
      • CudnnRNNTanh
      • CudnnRNNTanhSaveable
    • data
      • Overview
      • assert_element_shape
      • batch_and_drop_remainder
      • bucket_by_sequence_length
      • CheckpointInputPipelineHook
      • choose_from_datasets
      • copy_to_device
      • Counter
      • CsvDataset
      • dense_to_sparse_batch
      • enumerate_dataset
      • get_single_element
      • group_by_reducer
      • group_by_window
      • ignore_errors
      • LMDBDataset
      • make_batched_features_dataset
      • make_csv_dataset
      • make_saveable_from_iterator
      • map_and_batch
      • padded_batch_and_drop_remainder
      • parallel_interleave
      • parse_example_dataset
      • prefetch_to_device
      • RandomDataset
      • read_batch_features
      • Reducer
      • reduce_dataset
      • rejection_resample
      • sample_from_datasets
      • scan
      • shuffle_and_repeat
      • sliding_window_batch
      • sloppy_interleave
      • SqlDataset
      • TFRecordWriter
      • unbatch
      • unique
    • deprecated
      • Overview
      • audio_summary
      • histogram_summary
      • image_summary
      • merge_all_summaries
      • merge_summary
      • scalar_summary
    • distribute
      • Overview
      • AllReduceCrossDeviceOps
      • CollectiveAllReduceStrategy
      • DistributeConfig
      • get_cross_replica_context
      • MirroredStrategy
      • Monitor
      • MultiWorkerAllReduce
      • ParameterServerStrategy
      • require_replica_context
      • run_standard_tensorflow_server
      • StandardInputStep
      • StandardSingleLossStep
      • Step
      • UpdateContext
    • distributions
      • Overview
      • assign_log_moving_mean_exp
      • assign_moving_mean_variance
      • Autoregressive
      • auto_correlation
      • BatchReshape
      • BetaWithSoftplusConcentration
      • Binomial
      • Cauchy
      • Chi2
      • Chi2WithAbsDf
      • ConditionalDistribution
      • ConditionalTransformedDistribution
      • Deterministic
      • estimator_head_distribution_regression
      • ExponentialWithSoftplusRate
      • ExpRelaxedOneHotCategorical
      • fill_triangular
      • fill_triangular_inverse
      • GammaWithSoftplusConcentrationRate
      • Geometric
      • HalfNormal
      • Independent
      • InverseGamma
      • InverseGammaWithSoftplusConcentrationRate
      • Kumaraswamy
      • LaplaceWithSoftplusScale
      • Logistic
      • matrix_diag_transform
      • Mixture
      • MixtureSameFamily
      • moving_mean_variance
      • MultivariateNormalDiag
      • MultivariateNormalDiagPlusLowRank
      • MultivariateNormalDiagWithSoftplusScale
      • MultivariateNormalFullCovariance
      • MultivariateNormalTriL
      • NegativeBinomial
      • NormalWithSoftplusScale
      • normal_conjugates_known_scale_posterior
      • normal_conjugates_known_scale_predictive
      • OneHotCategorical
      • percentile
      • Poisson
      • PoissonLogNormalQuadratureCompound
      • quadrature_scheme_lognormal_gauss_hermite
      • quadrature_scheme_lognormal_quantiles
      • quadrature_scheme_softmaxnormal_gauss_hermite
      • quadrature_scheme_softmaxnormal_quantiles
      • QuantizedDistribution
      • reduce_weighted_logsumexp
      • RelaxedBernoulli
      • RelaxedOneHotCategorical
      • SeedStream
      • SinhArcsinh
      • softplus_inverse
      • StudentTWithAbsDfSoftplusScale
      • TransformedDistribution
      • tridiag
      • VectorDeterministic
      • VectorDiffeomixture
      • VectorExponentialDiag
      • VectorLaplaceDiag
      • VectorSinhArcsinhDiag
      • WishartCholesky
      • WishartFull
      • bijectors
        • Overview
        • AbsoluteValue
        • Affine
        • AffineLinearOperator
        • AffineScalar
        • BatchNormalization
        • Bijector
        • Chain
        • CholeskyOuterProduct
        • ConditionalBijector
        • Exp
        • FillTriangular
        • Gumbel
        • Identity
        • Inline
        • Invert
        • Kumaraswamy
        • MaskedAutoregressiveFlow
        • masked_autoregressive_default_template
        • masked_dense
        • MatrixInverseTriL
        • Ordered
        • Permute
        • PowerTransform
        • RealNVP
        • real_nvp_default_template
        • Reshape
        • ScaleTriL
        • Sigmoid
        • SinhArcsinh
        • SoftmaxCentered
        • Softplus
        • Softsign
        • Square
        • TransformDiagonal
    • eager
      • Overview
      • add_execution_callback
      • async_clear_error
      • async_wait
      • clear_execution_callbacks
      • defun
      • EagerVariableStore
      • enable_remote_eager_execution
      • errstate
      • ExecutionCallback
      • execution_mode
      • get_optimizer_variables
      • gradients_function
      • implicit_gradients
      • implicit_value_and_gradients
      • inf_callback
      • inf_nan_callback
      • Iterator
      • make_template
      • nan_callback
      • Network
      • num_gpus
      • restore_network_checkpoint
      • restore_variables_on_create
      • run
      • run_all_tests_in_graph_and_eager_modes
      • run_test_in_graph_and_eager_modes
      • Saver
      • save_network_checkpoint
      • Sequential
      • seterr
      • set_execution_mode
      • set_server_def
      • value_and_gradients_function
      • Variable
      • metrics
        • Overview
        • Accuracy
        • BinaryAccuracy
        • CategoricalAccuracy
        • Mean
        • Metric
        • SparseAccuracy
    • estimator
      • Overview
      • add_metrics
      • binary_classification_head
      • boosted_trees_classifier_train_in_memory
      • boosted_trees_regressor_train_in_memory
      • build_raw_supervised_input_receiver_fn
      • build_supervised_input_receiver_fn_from_input_fn
      • call_logit_fn
      • clip_gradients_by_norm
      • DNNClassifierWithLayerAnnotations
      • DNNRegressorWithLayerAnnotations
      • dnn_logit_fn_builder
      • export_all_saved_models
      • export_saved_model_for_mode
      • forward_features
      • linear_logit_fn_builder
      • logistic_regression_head
      • multi_class_head
      • multi_head
      • multi_label_head
      • poisson_regression_head
      • regression_head
      • replicate_model_fn
      • RNNClassifier
      • RNNEstimator
      • SavedModelEstimator
      • TowerOptimizer
    • factorization
      • Overview
      • GMM
      • gmm
      • GmmAlgorithm
      • KMeans
      • KMeansClustering
      • WALSMatrixFactorization
      • WALSModel
    • feature_column
      • Overview
      • sequence_categorical_column_with_hash_bucket
      • sequence_categorical_column_with_identity
      • sequence_categorical_column_with_vocabulary_file
      • sequence_categorical_column_with_vocabulary_list
      • sequence_input_layer
      • sequence_numeric_column
    • ffmpeg
      • Overview
      • decode_audio
      • decode_video
      • encode_audio
    • framework
      • Overview
      • add_arg_scope
      • add_model_variable
      • arg_scope
      • arg_scoped_arguments
      • assert_global_step
      • assert_or_get_global_step
      • assert_scalar_int
      • assign_from_checkpoint
      • assign_from_checkpoint_fn
      • assign_from_values
      • assign_from_values_fn
      • BoundedTensorSpec
      • convolutional_delta_orthogonal
      • convolutional_orthogonal_1d
      • convolutional_orthogonal_2d
      • convolutional_orthogonal_3d
      • create_global_step
      • current_arg_scope
      • deprecated
      • deprecated_args
      • deprecated_arg_values
      • filter_variables
      • fuse_op
      • get_global_step
      • get_graph_from_inputs
      • get_local_variables
      • get_model_variables
      • get_name_scope
      • get_or_create_global_step
      • get_placeholders
      • get_trainable_variables
      • get_unique_variable
      • get_variables
      • get_variables_by_name
      • get_variables_by_suffix
      • get_variables_to_restore
      • get_variable_full_name
      • global_variable
      • has_arg_scope
      • init_from_checkpoint
      • list_variables
      • load_and_remap_matrix_initializer
      • load_checkpoint
      • load_embedding_initializer
      • load_linear_multiclass_bias_initializer
      • load_variable
      • load_variable_slot_initializer
      • local_variable
      • model_variable
      • prepend_name_scope
      • py_func
      • RecordInput
      • reduce_sum_n
      • remove_squeezable_dimensions
      • smart_case
      • smart_cond
      • smart_constant_value
      • strip_name_scope
      • variable
      • VariableDeviceChooser
      • with_same_shape
      • with_shape
      • zero_initializer
      • nest
        • Overview
        • assert_shallow_structure
        • flatten_dict_items
        • flatten_up_to
        • flatten_with_joined_string_paths
        • flatten_with_tuple_paths
        • flatten_with_tuple_paths_up_to
        • get_traverse_shallow_structure
        • is_sequence
        • is_sequence_or_composite
        • map_structure_up_to
        • map_structure_with_paths
        • map_structure_with_tuple_paths
        • map_structure_with_tuple_paths_up_to
        • yield_flat_paths
    • graph_editor
      • Overview
      • add_control_inputs
      • assign_renamed_collections_handler
      • bypass
      • can_be_regex
      • check_cios
      • compute_boundary_ts
      • connect
      • ControlOutputs
      • copy
      • copy_op_handler
      • copy_with_input_replacements
      • detach
      • detach_control_inputs
      • detach_control_outputs
      • detach_inputs
      • detach_outputs
      • filter_ops
      • filter_ops_from_regex
      • filter_ts
      • filter_ts_from_regex
      • get_backward_walk_ops
      • get_consuming_ops
      • get_forward_walk_ops
      • get_generating_ops
      • get_name_scope_ops
      • get_ops_ios
      • get_tensors
      • get_walks_intersection_ops
      • get_walks_union_ops
      • get_within_boundary_ops
      • graph_replace
      • keep_t_if_possible_handler
      • make_list_of_op
      • make_list_of_t
      • make_placeholder_from_dtype_and_shape
      • make_placeholder_from_tensor
      • make_regex
      • make_view
      • make_view_from_scope
      • placeholder_name
      • remove_control_inputs
      • replace_t_with_placeholder_handler
      • reroute_inputs
      • reroute_ios
      • reroute_outputs
      • reroute_ts
      • select_ops
      • select_ops_and_ts
      • select_ts
      • SubGraphView
      • swap_inputs
      • swap_ios
      • swap_outputs
      • swap_ts
      • Transformer
      • TransformerInfo
      • transform_op_if_inside_handler
      • edit
        • Overview
      • reroute
        • Overview
      • select
        • Overview
      • subgraph
        • Overview
      • transform
        • Overview
      • util
        • Overview
    • grid_rnn
      • Overview
    • image
      • Overview
      • angles_to_projective_transforms
      • bipartite_match
      • compose_transforms
      • connected_components
      • dense_image_warp
      • flat_transforms_to_matrices
      • interpolate_spline
      • matrices_to_flat_transforms
      • rotate
      • single_image_random_dot_stereograms
      • sparse_image_warp
      • transform
      • translate
      • translations_to_projective_transforms
    • input_pipeline
      • Overview
      • obtain_next
    • integrate
      • Overview
      • odeint
      • odeint_fixed
    • keras
      • Overview
    • kernel_methods
      • Overview
      • KernelLinearClassifier
      • RandomFourierFeatureMapper
      • sparse_multiclass_hinge_loss
    • labeled_tensor
      • Overview
    • layers
      • Overview
      • apply_regularization
      • avg_pool2d
      • avg_pool3d
      • batch_norm
      • bias_add
      • bow_encoder
      • bucketized_column
      • check_feature_columns
      • conv1d
      • conv2d
      • conv2d_in_plane
      • conv2d_transpose
      • conv3d
      • conv3d_transpose
      • convolution
      • create_feature_spec_for_parsing
      • crossed_column
      • dense_to_sparse
      • dropout
      • elu
      • embedding_column
      • embedding_lookup_unique
      • embed_sequence
      • flatten
      • fully_connected
      • GDN
      • gdn
      • group_norm
      • images_to_sequence
      • infer_real_valued_columns
      • input_from_feature_columns
      • instance_norm
      • joint_weighted_sum_from_feature_columns
      • l1_l2_regularizer
      • l1_regularizer
      • l2_regularizer
      • layer_norm
      • legacy_fully_connected
      • legacy_linear
      • legacy_relu
      • linear
      • make_place_holder_tensors_for_base_features
      • maxout
      • max_pool2d
      • max_pool3d
      • multi_class_target
      • one_hot_column
      • one_hot_encoding
      • optimize_loss
      • parse_feature_columns_from_examples
      • parse_feature_columns_from_sequence_examples
      • real_valued_column
      • recompute_grad
      • regression_target
      • relu
      • relu6
      • repeat
      • RevBlock
      • rev_block
      • safe_embedding_lookup_sparse
      • scale_gradient
      • scattered_embedding_column
      • separable_conv2d
      • sequence_input_from_feature_columns
      • sequence_to_images
      • shared_embedding_columns
      • softmax
      • sparse_column_with_hash_bucket
      • sparse_column_with_integerized_feature
      • sparse_column_with_keys
      • sparse_column_with_vocabulary_file
      • spatial_softmax
      • stack
      • summarize_activation
      • summarize_activations
      • summarize_collection
      • summarize_tensor
      • summarize_tensors
      • sum_regularizer
      • transform_features
      • unit_norm
      • variance_scaling_initializer
      • weighted_sparse_column
      • weighted_sum_from_feature_columns
      • xavier_initializer
      • feature_column
        • Overview
      • summaries
        • Overview
    • learn
      • Overview
      • BaseEstimator
      • binary_svm_head
      • build_parsing_serving_input_fn
      • DNNClassifier
      • DNNEstimator
      • DNNLinearCombinedClassifier
      • DNNLinearCombinedEstimator
      • DNNLinearCombinedRegressor
      • DNNRegressor
      • DynamicRnnEstimator
      • Estimator
      • Evaluable
      • evaluate
      • Experiment
      • ExportStrategy
      • extract_dask_data
      • extract_dask_labels
      • extract_pandas_data
      • extract_pandas_labels
      • extract_pandas_matrix
      • Head
      • infer
      • infer_real_valued_columns_from_input
      • infer_real_valued_columns_from_input_fn
      • InputFnOps
      • KMeansClustering
      • LinearClassifier
      • LinearEstimator
      • LinearRegressor
      • LogisticRegressor
      • make_export_strategy
      • MetricSpec
      • ModeKeys
      • ModelFnOps
      • multi_class_head
      • multi_head
      • multi_label_head
      • NanLossDuringTrainingError
      • NotFittedError
      • no_op_train_fn
      • poisson_regression_head
      • PredictionKey
      • ProblemType
      • read_batch_examples
      • read_batch_features
      • read_batch_record_features
      • read_keyed_batch_examples
      • read_keyed_batch_examples_shared_queue
      • read_keyed_batch_features
      • read_keyed_batch_features_shared_queue
      • regression_head
      • RunConfig
      • run_feeds
      • run_n
      • SKCompat
      • SVM
      • TaskType
      • train
      • Trainable
      • datasets
        • Overview
      • graph_actions
        • Overview
      • head
        • Overview
      • io
        • Overview
      • learn_runner
        • Overview
        • run
        • tune
      • models
        • Overview
      • monitors
        • Overview
      • ops
        • Overview
      • preprocessing
        • Overview
      • utils
        • Overview
    • legacy_seq2seq
      • Overview
      • attention_decoder
      • basic_rnn_seq2seq
      • embedding_attention_decoder
      • embedding_attention_seq2seq
      • embedding_rnn_decoder
      • embedding_rnn_seq2seq
      • embedding_tied_rnn_seq2seq
      • model_with_buckets
      • one2many_rnn_seq2seq
      • rnn_decoder
      • sequence_loss
      • sequence_loss_by_example
      • tied_rnn_seq2seq
    • linear_optimizer
      • Overview
      • SdcaModel
      • SDCAOptimizer
      • SparseFeatureColumn
    • lookup
      • Overview
      • HasherSpec
      • HashTable
      • IdTableWithHashBuckets
      • index_table_from_file
      • index_table_from_tensor
      • index_to_string
      • index_to_string_table_from_file
      • index_to_string_table_from_tensor
      • InitializableLookupTableBase
      • LookupInterface
      • MutableHashTable
      • string_to_index
      • string_to_index_table_from_file
      • string_to_index_table_from_tensor
      • StrongHashSpec
      • TableInitializerBase
      • TextFileIdTableInitializer
      • TextFileStringTableInitializer
    • losses
      • Overview
      • absolute_difference
      • add_loss
      • compute_weighted_loss
      • cosine_distance
      • get_losses
      • get_regularization_losses
      • get_total_loss
      • hinge_loss
      • log_loss
      • mean_pairwise_squared_error
      • mean_squared_error
      • sigmoid_cross_entropy
      • softmax_cross_entropy
      • sparse_softmax_cross_entropy
      • metric_learning
        • Overview
        • cluster_loss
        • contrastive_loss
        • lifted_struct_loss
        • npairs_loss
        • npairs_loss_multilabel
        • triplet_semihard_loss
    • memory_stats
      • Overview
      • BytesInUse
      • BytesLimit
      • MaxBytesInUse
    • metrics
      • Overview
      • accuracy
      • aggregate_metrics
      • aggregate_metric_map
      • auc_using_histogram
      • auc_with_confidence_intervals
      • cohen_kappa
      • confusion_matrix
      • count
      • f1_score
      • precision_at_recall
      • precision_recall_at_equal_thresholds
      • recall_at_precision
      • sparse_recall_at_top_k
      • streaming_accuracy
      • streaming_auc
      • streaming_concat
      • streaming_covariance
      • streaming_curve_points
      • streaming_dynamic_auc
      • streaming_false_negatives
      • streaming_false_negatives_at_thresholds
      • streaming_false_negative_rate
      • streaming_false_negative_rate_at_thresholds
      • streaming_false_positives
      • streaming_false_positives_at_thresholds
      • streaming_false_positive_rate
      • streaming_false_positive_rate_at_thresholds
      • streaming_mean
      • streaming_mean_absolute_error
      • streaming_mean_cosine_distance
      • streaming_mean_iou
      • streaming_mean_relative_error
      • streaming_mean_squared_error
      • streaming_mean_tensor
      • streaming_pearson_correlation
      • streaming_percentage_less
      • streaming_precision
      • streaming_precision_at_thresholds
      • streaming_recall
      • streaming_recall_at_k
      • streaming_recall_at_thresholds
      • streaming_root_mean_squared_error
      • streaming_sensitivity_at_specificity
      • streaming_sparse_average_precision_at_k
      • streaming_sparse_average_precision_at_top_k
      • streaming_sparse_precision_at_k
      • streaming_sparse_precision_at_top_k
      • streaming_sparse_recall_at_k
      • streaming_specificity_at_sensitivity
      • streaming_true_negatives
      • streaming_true_negatives_at_thresholds
      • streaming_true_positives
      • streaming_true_positives_at_thresholds
    • mixed_precision
      • Overview
      • ExponentialUpdateLossScaleManager
      • FixedLossScaleManager
      • LossScaleManager
      • LossScaleOptimizer
    • model_pruning
      • Overview
      • apply_mask
      • get_masked_weights
      • get_masks
      • get_pruning_hparams
      • get_thresholds
      • get_weights
      • get_weight_sparsity
      • graph_def_from_checkpoint
      • MaskedBasicLSTMCell
      • MaskedLSTMCell
      • masked_conv2d
      • masked_fully_connected
      • Pruning
      • strip_pruning_vars_fn
      • train
    • nn
      • Overview
      • alpha_dropout
      • deprecated_flipped_sigmoid_cross_entropy_with_logits
      • deprecated_flipped_softmax_cross_entropy_with_logits
      • deprecated_flipped_sparse_softmax_cross_entropy_with_logits
      • nth_element
      • rank_sampled_softmax_loss
      • sampled_sparse_softmax_loss
      • scaled_softplus
    • opt
      • Overview
      • AdaMaxOptimizer
      • AdamGSOptimizer
      • AdamWOptimizer
      • AddSignOptimizer
      • AGNCustomGetter
      • AGNOptimizer
      • clip_gradients_by_global_norm
      • DecoupledWeightDecayExtension
      • DropStaleGradientOptimizer
      • ElasticAverageCustomGetter
      • ElasticAverageOptimizer
      • extend_with_decoupled_weight_decay
      • ExternalOptimizerInterface
      • GGTOptimizer
      • LARSOptimizer
      • LazyAdamGSOptimizer
      • LazyAdamOptimizer
      • ModelAverageCustomGetter
      • ModelAverageOptimizer
      • MomentumWOptimizer
      • MovingAverageOptimizer
      • MultitaskOptimizerWrapper
      • NadamOptimizer
      • PowerSignOptimizer
      • RegAdagradOptimizer
      • ScipyOptimizerInterface
      • ShampooOptimizer
      • VariableClippingOptimizer
    • optimizer_v2
      • Overview
      • AdadeltaOptimizer
      • AdagradOptimizer
      • AdamOptimizer
      • GradientDescentOptimizer
      • MomentumOptimizer
      • OptimizerV2
      • RMSPropOptimizer