TensorFlow Python reference documentation

• Building Graphs:

  • add_to_collection
  • as_dtype
  • bytes
  • container
  • control_dependencies
  • convert_to_tensor
  • convert_to_tensor_or_indexed_slices
  • device
  • DeviceSpec
  • Dimension
  • DType
  • get_collection
  • get_collection_ref
  • get_default_graph
  • get_seed
  • Graph
  • GraphKeys
  • import_graph_def
  • load_file_system_library
  • load_op_library
  • name_scope
  • NoGradient
  • op_scope
  • Operation
  • register_tensor_conversion_function
  • RegisterGradient
  • RegisterShape
  • reset_default_graph
  • Tensor
  • TensorShape

• Asserts and boolean checks.:

  • assert_equal
  • assert_integer
  • assert_less
  • assert_less_equal
  • assert_negative
  • assert_non_negative
  • assert_non_positive
  • assert_positive
  • assert_proper_iterable
  • assert_rank
  • assert_rank_at_least
  • assert_type
  • is_non_decreasing
  • is_numeric_tensor
  • is_strictly_increasing

• Constants, Sequences, and Random Values:

  • constant
  • fill
  • linspace
  • multinomial
  • ones
  • ones_like
  • ops
  • random_crop
  • random_gamma
  • random_normal
  • random_shuffle
  • random_uniform
  • range
  • set_random_seed
  • truncated_normal
  • zeros
  • zeros_like

• Variables:

  • all_variables
  • assert_variables_initialized
  • assign
  • assign_add
  • assign_sub
  • constant_initializer
  • count_up_to
  • device
  • export_meta_graph
  • get_checkpoint_state
  • get_variable
  • get_variable_scope
  • import_meta_graph
  • IndexedSlices
  • initialize_all_variables
  • initialize_local_variables
  • initialize_variables
  • is_variable_initialized
  • latest_checkpoint
  • local_variables
  • make_template
  • min_max_variable_partitioner
  • moving_average_variables
  • no_regularizer
  • ones_initializer
  • random_normal_initializer
  • random_uniform_initializer
  • report_uninitialized_variables
  • Saver
  • scatter_add
  • scatter_sub
  • scatter_update
  • sparse_mask
  • trainable_variables
  • truncated_normal_initializer
  • uniform_unit_scaling_initializer
  • update_checkpoint_state
  • Variable
  • variable_axis_size_partitioner
  • variable_op_scope
  • variable_scope
  • VariableScope
  • zeros_initializer

• Tensor Transformations:

  • batch_to_space
  • bitcast
  • boolean_mask
  • cast
  • concat
  • copy
  • depth_to_space
  • dynamic_partition
  • dynamic_stitch
  • expand_dims
  • extract_image_patches
  • gather
  • gather_nd
  • meshgrid
  • one_hot
  • pack
  • pad
  • rank
  • reshape
  • reverse
  • reverse_sequence
  • saturate_cast
  • shape
  • shape_n
  • size
  • slice
  • space_to_batch
  • space_to_depth
  • split
  • squeeze
  • strided_slice
  • string_to_number
  • tile
  • to_bfloat16
  • to_double
  • to_float
  • to_int32
  • to_int64
  • transpose
  • unique_with_counts
  • unpack

• Math:

  • abs
  • accumulate_n
  • acos
  • add
  • add_n
  • argmax
  • argmin
  • asin
  • atan
  • batch_cholesky
  • batch_cholesky_solve
  • batch_fft
  • batch_fft2d
  • batch_fft3d
  • batch_ifft
  • batch_ifft2d
  • batch_ifft3d
  • batch_matmul
  • batch_matrix_band_part
  • batch_matrix_determinant
  • batch_matrix_diag
  • batch_matrix_diag_part
  • batch_matrix_inverse
  • batch_matrix_set_diag
  • batch_matrix_solve
  • batch_matrix_solve_ls
  • batch_matrix_transpose
  • batch_matrix_triangular_solve
  • batch_self_adjoint_eig
  • batch_self_adjoint_eigvals
  • batch_svd
  • ceil
  • cholesky
  • cholesky_solve
  • complex
  • complex_abs
  • conj
  • cos
  • cross
  • cumprod
  • cumsum
  • diag
  • diag_part
  • digamma
  • div
  • edit_distance
  • erf
  • erfc
  • exp
  • fft
  • fft2d
  • fft3d
  • floor
  • floordiv
  • ifft
  • ifft2d
  • ifft3d
  • igamma
  • igammac
  • imag
  • inv
  • invert_permutation
  • lbeta
  • lgamma
  • listdiff
  • log
  • matmul
  • matrix_determinant
  • matrix_inverse
  • matrix_solve
  • matrix_solve_ls
  • matrix_triangular_solve
  • maximum
  • minimum
  • mod
  • mul
  • neg
  • polygamma
  • pow
  • real
  • reduce_all
  • reduce_any
  • reduce_max
  • reduce_mean
  • reduce_min
  • reduce_prod
  • reduce_sum
  • round
  • rsqrt
  • scalar_mul
  • segment_max
  • segment_mean
  • segment_min
  • segment_prod
  • segment_sum
  • self_adjoint_eig
  • self_adjoint_eigvals
  • sign
  • sin
  • sparse_segment_mean
  • sparse_segment_sqrt_n
  • sparse_segment_sqrt_n_grad
  • sparse_segment_sum
  • sqrt
  • square
  • squared_difference
  • sub
  • svd
  • tan
  • trace
  • transpose
  • truediv
  • unique
  • unsorted_segment_sum
  • where
  • zeta

• Strings:

  • as_string
  • reduce_join
  • string_join
  • string_to_hash_bucket
  • string_to_hash_bucket_fast
  • string_to_hash_bucket_strong

• Histograms:

  • histogram_fixed_width

• Control Flow:

  • add_check_numerics_ops
  • Assert
  • case
  • check_numerics
  • cond
  • count_up_to
  • equal
  • greater
  • greater_equal
  • group
  • identity
  • is_finite
  • is_inf
  • is_nan
  • less
  • less_equal
  • logical_and
  • logical_not
  • logical_or
  • logical_xor
  • no_op
  • not_equal
  • Print
  • select
  • tuple
  • verify_tensor_all_finite
  • where
  • while_loop

• Higher Order Functions:

  • foldl
  • foldr
  • map_fn
  • scan

• TensorArray Operations:

  • concat
  • pack
  • split
  • TensorArray
  • unpack

• Tensor Handle Operations:

  • delete_session_tensor
  • get_session_handle
  • get_session_tensor

• Images:

  • adjust_brightness
  • adjust_contrast
  • adjust_hue
  • adjust_saturation
  • central_crop
  • convert_image_dtype
  • crop_and_resize
  • crop_to_bounding_box
  • decode_jpeg
  • decode_png
  • draw_bounding_boxes
  • encode_jpeg
  • encode_png
  • extract_glimpse
  • flip_left_right
  • flip_up_down
  • grayscale_to_rgb
  • hsv_to_rgb
  • non_max_suppression
  • pad_to_bounding_box
  • per_image_whitening
  • random_brightness
  • random_contrast
  • random_flip_left_right
  • random_flip_up_down
  • random_hue
  • random_saturation
  • resize_area
  • resize_bicubic
  • resize_bilinear
  • resize_image_with_crop_or_pad
  • resize_images
  • resize_nearest_neighbor
  • rgb_to_grayscale
  • rgb_to_hsv
  • rot90
  • sample_distorted_bounding_box
  • transpose_image

• Sparse Tensors:

  • shape
  • sparse_add
  • sparse_concat
  • sparse_fill_empty_rows
  • sparse_maximum
  • sparse_merge
  • sparse_minimum
  • sparse_reduce_sum
  • sparse_reorder
  • sparse_reset_shape
  • sparse_reshape
  • sparse_retain
  • sparse_softmax
  • sparse_split
  • sparse_tensor_dense_matmul
  • sparse_tensor_to_dense
  • sparse_to_dense
  • sparse_to_indicator
  • SparseTensor
  • SparseTensorValue

• Inputs and Readers:

  • batch
  • batch_join
  • decode_csv
  • decode_json_example
  • decode_raw
  • FIFOQueue
  • FixedLenFeature
  • FixedLengthRecordReader
  • FixedLenSequenceFeature
  • IdentityReader
  • input_producer
  • limit_epochs
  • match_filenames_once
  • matching_files
  • PaddingFIFOQueue
  • parse_example
  • parse_single_example
  • placeholder
  • placeholder_with_default
  • QueueBase
  • RandomShuffleQueue
  • range_input_producer
  • read_file
  • ReaderBase
  • shuffle_batch
  • shuffle_batch_join
  • size
  • slice_input_producer
  • sparse_placeholder
  • string_input_producer
  • TextLineReader
  • TFRecordReader
  • VarLenFeature
  • WholeFileReader

• Data IO (Python functions):

  • tf_record_iterator
  • TFRecordWriter

• Neural Network:

  • atrous_conv2d
  • avg_pool
  • avg_pool3d
  • batch_normalization
  • bias_add
  • bidirectional_rnn
  • compute_accidental_hits
  • conv2d
  • conv2d_transpose
  • conv3d
  • ctc_beam_search_decoder
  • ctc_greedy_decoder
  • ctc_loss
  • depthwise_conv2d
  • depthwise_conv2d_native
  • dilation2d
  • dropout
  • dynamic_rnn
  • elu
  • embedding_lookup
  • embedding_lookup_sparse
  • erosion2d
  • fixed_unigram_candidate_sampler
  • in_top_k
  • l2_loss
  • l2_normalize
  • learned_unigram_candidate_sampler
  • local_response_normalization
  • log_poisson_loss
  • log_softmax
  • log_uniform_candidate_sampler
  • max_pool
  • max_pool3d
  • max_pool_with_argmax
  • moments
  • nce_loss
  • normalize_moments
  • relu
  • relu6
  • rnn
  • sampled_softmax_loss
  • separable_conv2d
  • sigmoid
  • sigmoid_cross_entropy_with_logits
  • softmax
  • softmax_cross_entropy_with_logits
  • softplus
  • softsign
  • sparse_softmax_cross_entropy_with_logits
  • state_saving_rnn
  • sufficient_statistics
  • tanh
  • top_k
  • uniform_candidate_sampler
  • weighted_cross_entropy_with_logits

• Neural Network RNN Cells:

  • BasicLSTMCell
  • BasicRNNCell
  • DropoutWrapper
  • EmbeddingWrapper
  • GRUCell
  • InputProjectionWrapper
  • LSTMCell
  • LSTMStateTuple
  • MultiRNNCell
  • OutputProjectionWrapper
  • RNNCell

• Running Graphs:

  • AbortedError
  • AlreadyExistsError
  • CancelledError
  • DataLossError
  • DeadlineExceededError
  • FailedPreconditionError
  • get_default_session
  • InteractiveSession
  • InternalError
  • InvalidArgumentError
  • NotFoundError
  • OpError
  • OutOfRangeError
  • PermissionDeniedError
  • ResourceExhaustedError
  • Session
  • UnauthenticatedError
  • UnavailableError
  • UnimplementedError
  • UnknownError

• Training:

  • AdadeltaOptimizer
  • AdagradOptimizer
  • AdamOptimizer
  • add_queue_runner
  • AggregationMethod
  • audio_summary
  • clip_by_average_norm
  • clip_by_global_norm
  • clip_by_norm
  • clip_by_value
  • ClusterSpec
  • Coordinator
  • do_quantize_training_on_graphdef
  • exponential_decay
  • ExponentialMovingAverage
  • FtrlOptimizer
  • generate_checkpoint_state_proto
  • global_norm
  • global_step
  • GradientDescentOptimizer
  • gradients
  • histogram_summary
  • image_summary
  • LooperThread
  • merge_all_summaries
  • merge_summary
  • MomentumOptimizer
  • Optimizer
  • QueueRunner
  • replica_device_setter
  • RMSPropOptimizer
  • scalar_summary
  • Server
  • SessionManager
  • start_queue_runners
  • stop_gradient
  • summary_iterator
  • SummaryWriter
  • Supervisor
  • write_graph
  • zero_fraction

• Wraps python functions:

  • py_func

• Summary Operations:

  • tensor_summary

• Testing:

  • assert_equal_graph_def
  • compute_gradient
  • compute_gradient_error
  • get_temp_dir
  • is_built_with_cuda
  • main

• BayesFlow Stochastic Graph (contrib):

  • DistributionTensor
  • get_current_value_type
  • get_score_function_with_baseline
  • MeanValue
  • NoValueTypeSetError
  • SampleAndReshapeValue
  • SampleValue
  • score_function
  • StochasticTensor
  • surrogate_loss
  • value_type

• Statistical distributions (contrib):

  • BaseDistribution
  • batch_matrix_diag_transform
  • Bernoulli
  • Beta
  • Binomial
  • Categorical
  • Chi2
  • Dirichlet
  • DirichletMultinomial
  • Distribution
  • Exponential
  • Gamma
  • InverseGamma
  • kl
  • Laplace
  • Multinomial
  • MultivariateNormalCholesky
  • MultivariateNormalDiag
  • MultivariateNormalDiagPlusVDVT
  • MultivariateNormalFull
  • Normal
  • normal_congugates_known_sigma_predictive
  • normal_conjugates_known_sigma_posterior
  • RegisterKL
  • StudentT
  • TransformedDistribution
  • Uniform

• FFmpeg (contrib):

  • decode_audio
  • encode_audio

• Framework (contrib):

  • add_arg_scope
  • add_model_variable
  • arg_scope
  • arg_scoped_arguments
  • assert_global_step
  • assert_or_get_global_step
  • assert_same_float_dtype
  • assert_scalar_int
  • convert_to_tensor_or_sparse_tensor
  • create_global_step
  • deprecated
  • deprecated_arg_values
  • get_global_step
  • get_graph_from_inputs
  • get_local_variables
  • get_model_variables
  • get_or_create_global_step
  • get_unique_variable
  • get_variables
  • get_variables_by_name
  • get_variables_by_suffix
  • get_variables_to_restore
  • has_arg_scope
  • is_non_decreasing
  • is_numeric_tensor
  • is_strictly_increasing
  • is_tensor
  • local_variable
  • model_variable
  • reduce_sum_n
  • safe_embedding_lookup_sparse
  • variable
  • VariableDeviceChooser
  • with_same_shape
  • with_shape

• Graph Editor (contrib):

  • bypass
  • connect
  • detach
  • detach_inputs
  • detach_outputs
  • matcher
  • ph
  • reroute_a2b
  • reroute_a2b_inputs
  • reroute_a2b_outputs
  • reroute_b2a
  • reroute_b2a_inputs
  • reroute_b2a_outputs
  • select_ops
  • select_ts
  • sgv
  • sgv_scope
  • SubGraphView
  • swap
  • swap_inputs
  • swap_outputs
  • Transformer
  • ts

• Layers (contrib):

  • apply_regularization
  • avg_pool2d
  • batch_norm
  • convolution2d
  • convolution2d_in_plane
  • convolution2d_transpose
  • flatten
  • fully_connected
  • l1_regularizer
  • l2_regularizer
  • max_pool2d
  • one_hot_encoding
  • optimize_loss
  • repeat
  • separable_convolution2d
  • stack
  • sum_regularizer
  • summarize_activation
  • summarize_activations
  • summarize_collection
  • summarize_tensor
  • summarize_tensors
  • unit_norm
  • variance_scaling_initializer
  • xavier_initializer
  • xavier_initializer_conv2d

• Learn (contrib):

  • BaseEstimator
  • DNNClassifier
  • DNNRegressor
  • Estimator
  • evaluate
  • extract_dask_data
  • extract_dask_labels
  • extract_pandas_data
  • extract_pandas_labels
  • extract_pandas_matrix
  • infer
  • LinearClassifier
  • LinearRegressor
  • ModeKeys
  • NanLossDuringTrainingError
  • read_batch_examples
  • read_batch_features
  • read_batch_record_features
  • run_feeds
  • run_n
  • RunConfig
  • TensorFlowClassifier
  • TensorFlowDNNClassifier
  • TensorFlowDNNRegressor
  • TensorFlowEstimator
  • TensorFlowLinearClassifier
  • TensorFlowLinearRegressor
  • TensorFlowRegressor
  • TensorFlowRNNClassifier
  • TensorFlowRNNRegressor
  • train

• Monitors (contrib):

  • BaseMonitor
  • CaptureVariable
  • CheckpointSaver
  • EveryN
  • ExportMonitor
  • get_default_monitors
  • GraphDump
  • LoggingTrainable
  • NanLoss
  • PrintTensor
  • StepCounter
  • StopAtStep
  • SummarySaver
  • SummaryWriterCache
  • ValidationMonitor

• Losses (contrib):

  • absolute_difference
  • add_loss
  • cosine_distance
  • get_losses
  • get_regularization_losses
  • get_total_loss
  • hinge_loss
  • log_loss
  • sigmoid_cross_entropy
  • softmax_cross_entropy
  • sum_of_pairwise_squares
  • sum_of_squares

• RNN (contrib):

  • AttentionCellWrapper
  • CoupledInputForgetGateLSTMCell
  • GridLSTMCell
  • LSTMFusedCell
  • TimeFreqLSTMCell

• Metrics (contrib):

  • accuracy
  • aggregate_metric_map
  • aggregate_metrics
  • auc_using_histogram
  • confusion_matrix
  • set_difference
  • set_intersection
  • set_size
  • set_union
  • streaming_accuracy
  • streaming_auc
  • streaming_mean
  • streaming_mean_absolute_error
  • streaming_mean_cosine_distance
  • streaming_mean_iou
  • streaming_mean_relative_error
  • streaming_mean_squared_error
  • streaming_percentage_less
  • streaming_precision
  • streaming_recall
  • streaming_recall_at_k
  • streaming_root_mean_squared_error
  • streaming_sparse_precision_at_k
  • streaming_sparse_recall_at_k

• Utilities (contrib):

  • constant_value
  • make_ndarray
  • make_tensor_proto
  • ops_used_by_graph_def
  • stripped_op_list_for_graph

• Copying Graph Elements (contrib):

  • copy_op_to_graph
  • copy_variable_to_graph
  • get_copied_op