Package: tfaddons 0.10.3

Turgut Abdullayev

tfaddons: Interface to 'TensorFlow SIG Addons'

'TensorFlow SIG Addons' <https://www.tensorflow.org/addons> is a repository of community contributions that conform to well-established API patterns, but implement new functionality not available in core 'TensorFlow'. 'TensorFlow' natively supports a large number of operators, layers, metrics, losses, optimizers, and more. However, in a fast moving field like Machine Learning, there are many interesting new developments that cannot be integrated into core 'TensorFlow' (because their broad applicability is not yet clear, or it is mostly used by a smaller subset of the community).

Authors:Turgut Abdullayev [aut, cre]

tfaddons_0.10.3.tar.gz
tfaddons_0.10.3.zip(r-4.5)tfaddons_0.10.3.zip(r-4.4)tfaddons_0.10.3.zip(r-4.3)
tfaddons_0.10.3.tgz(r-4.4-any)tfaddons_0.10.3.tgz(r-4.3-any)
tfaddons_0.10.3.tar.gz(r-4.5-noble)tfaddons_0.10.3.tar.gz(r-4.4-noble)
tfaddons_0.10.3.tgz(r-4.4-emscripten)tfaddons_0.10.3.tgz(r-4.3-emscripten)
tfaddons.pdf |tfaddons.html✨
tfaddons/json (API)

# Install 'tfaddons' in R:
install.packages('tfaddons', repos = c('https://eagerai.r-universe.dev', 'https://cloud.r-project.org'))

Peer review:

Bug tracker:https://github.com/henry090/tfaddons/issues

On CRAN:

deep-learningkerasneural-networkstensorflowtensorflow-addonstfa

5.15 score 20 stars 14 scripts 138 downloads 137 exports 34 dependencies

Last updated 3 years agofrom:640e4c26aa. Checks:OK: 3 NOTE: 4. Indexed: yes.

TargetResultDate
Doc / VignettesOKNov 11 2024
R-4.5-winNOTENov 11 2024
R-4.5-linuxNOTENov 11 2024
R-4.4-winNOTENov 11 2024
R-4.4-macNOTENov 11 2024
R-4.3-winOKNov 11 2024
R-4.3-macOKNov 11 2024

Exports:activation_geluactivation_hardshrinkactivation_lishtactivation_mishactivation_rreluactivation_softshrinkactivation_sparsemaxactivation_tanhshrinkattention_bahdanauattention_bahdanau_monotonicattention_luongattention_luong_monotonicattention_monotonicattention_wrapperattention_wrapper_statecallback_average_model_checkpointcallback_time_stoppingcallback_tqdm_progress_barcrf_binary_scorecrf_decodecrf_decode_backwardcrf_decode_forwardcrf_forwardcrf_log_likelihoodcrf_log_normcrf_multitag_sequence_scorecrf_sequence_scorecrf_unary_scoredecode_dynamicdecoderdecoder_basedecoder_basicdecoder_basic_outputdecoder_beam_searchdecoder_beam_search_outputdecoder_beam_search_statedecoder_final_beam_search_outputextend_with_decoupled_weight_decaygather_treegather_tree_from_arrayhardmaximg_adjust_hsv_in_yiqimg_angles_to_projective_transformsimg_blendimg_compose_transformsimg_connected_componentsimg_cutoutimg_dense_image_warpimg_equalizeimg_euclidean_dist_transformimg_flat_transforms_to_matricesimg_from_4Dimg_get_ndimsimg_interpolate_bilinearimg_interpolate_splineimg_matrices_to_flat_transformsimg_mean_filter2dimg_median_filter2dimg_random_cutoutimg_random_hsv_in_yiqimg_resamplerimg_rotateimg_sharpnessimg_shear_ximg_shear_yimg_sparse_image_warpimg_to_4Dimg_transformimg_translateimg_translate_xyimg_translations_to_projective_transformsimg_unwrapimg_wrapinstall_tfaddonslayer_activation_gelulayer_correlation_costlayer_filter_response_normalizationlayer_group_normalizationlayer_instance_normalizationlayer_maxoutlayer_multi_head_attentionlayer_nas_celllayer_norm_lstm_celllayer_poincare_normalizelayer_sparsemaxlayer_weight_normalizationlookahead_mechanismloss_contrastiveloss_giouloss_hammingloss_lifted_structloss_npairsloss_npairs_multilabelloss_pinballloss_sequenceloss_sigmoid_focal_crossentropyloss_sparsemaxloss_triplet_hardloss_triplet_semihardmetric_cohen_kappametric_fbetascoremetric_hamming_distancemetric_mccmetric_multilabel_confusion_matrixmetric_rsquaremetrics_f1scoreoptimizer_conditional_gradientoptimizer_decay_adamwoptimizer_decay_sgdwoptimizer_lamboptimizer_lazy_adamoptimizer_moving_averageoptimizer_novogradoptimizer_radamoptimizer_swaoptimizer_yogiparse_timeregister_allregister_custom_kernelsregister_keras_objectssafe_cumprodsample_bernoullisample_categoricalsamplersampler_customsampler_greedy_embeddingsampler_inferencesampler_sample_embeddingsampler_scheduled_embedding_trainingsampler_scheduled_output_trainingsampler_trainingskip_gram_sampleskip_gram_sample_with_text_vocabtftfaddons_versiontile_batchviterbi_decode

Dependencies:backportsbase64enccliconfiggenericsglueherejsonlitekeraslatticelifecyclemagrittrMatrixpngprocessxpspurrrR6rappdirsRcppRcppTOMLreticulaterlangrprojrootrstudioapitensorflowtfautographtfrunstidyselectvctrswhiskerwithryamlzeallot

Neural Machine Translation

Rendered fromNMT.Rmdusingknitr::rmarkdownon Nov 11 2024.

Last update: 2020-05-25
Started: 2020-05-14

Readme and manuals

Help Manual

Help pageTopics
Geluactivation_gelu
Hardshrinkactivation_hardshrink
Lishtactivation_lisht
Mishactivation_mish
Rreluactivation_rrelu
Softshrinkactivation_softshrink
Sparsemaxactivation_sparsemax
Tanhshrinkactivation_tanhshrink
Bahdanau Attentionattention_bahdanau
Bahdanau Monotonic Attentionattention_bahdanau_monotonic
Implements Luong-style (multiplicative) attention scoring.attention_luong
Monotonic attention mechanism with Luong-style energy function.attention_luong_monotonic
Monotonic attentionattention_monotonic
Attention Wrapperattention_wrapper
Attention Wrapper Stateattention_wrapper_state
Average Model Checkpointcallback_average_model_checkpoint
Time Stoppingcallback_time_stopping
TQDM Progress Barcallback_tqdm_progress_bar
CRF binary scorecrf_binary_score
CRF decodecrf_decode
CRF decode backwardcrf_decode_backward
CRF decode forwardcrf_decode_forward
CRF forwardcrf_forward
CRF log likelihoodcrf_log_likelihood
CRF log normcrf_log_norm
CRF multitag sequence scorecrf_multitag_sequence_score
CRF sequence scorecrf_sequence_score
CRF unary scorecrf_unary_score
Dynamic decodedecode_dynamic
An RNN Decoder abstract interface object.decoder
Base Decoderdecoder_base
Basic Decoderdecoder_basic
Basic decoder outputdecoder_basic_output
BeamSearch sampling decoderdecoder_beam_search
Beam Search Decoder Outputdecoder_beam_search_output
Beam Search Decoder Statedecoder_beam_search_state
Final Beam Search Decoder Outputdecoder_final_beam_search_output
Factory function returning an optimizer class with decoupled weight decayextend_with_decoupled_weight_decay
Gather treegather_tree
Gather tree from arraygather_tree_from_array
Hardmaxhardmax
Adjust hsv in yiqimg_adjust_hsv_in_yiq
Angles to projective transformsimg_angles_to_projective_transforms
Blendimg_blend
Compose transformsimg_compose_transforms
Connected componentsimg_connected_components
Cutoutimg_cutout
Dense image warpimg_dense_image_warp
Equalizeimg_equalize
Euclidean dist transformimg_euclidean_dist_transform
Flat transforms to matricesimg_flat_transforms_to_matrices
From 4D imageimg_from_4D
Get ndimsimg_get_ndims
Interpolate bilinearimg_interpolate_bilinear
Interpolate splineimg_interpolate_spline
Matrices to flat transformsimg_matrices_to_flat_transforms
Mean filter2dimg_mean_filter2d
Median filter2dimg_median_filter2d
Random cutoutimg_random_cutout
Random hsv in yiqimg_random_hsv_in_yiq
Resamplerimg_resampler
Rotateimg_rotate
Sharpnessimg_sharpness
Shear x-axisimg_shear_x
Shear y-axisimg_shear_y
Sparse image warpimg_sparse_image_warp
To 4D imageimg_to_4D
Transformimg_transform
Translateimg_translate
Translate xy dimsimg_translate_xy
Translations to projective transformsimg_translations_to_projective_transforms
Uwrapimg_unwrap
Wrapimg_wrap
Install TensorFlow SIG Addonsinstall_tfaddons
Gaussian Error Linear Unitlayer_activation_gelu
Correlation Cost Layer.layer_correlation_cost
FilterResponseNormalizationlayer_filter_response_normalization
Group normalization layerlayer_group_normalization
Instance normalization layerlayer_instance_normalization
Maxout layerlayer_maxout
Keras-based multi head attention layerlayer_multi_head_attention
Neural Architecture Search (NAS) recurrent network cell.layer_nas_cell
LSTM cell with layer normalization and recurrent dropout.layer_norm_lstm_cell
Project into the Poincare ball with norm <= 1.0 - epsilonlayer_poincare_normalize
Sparsemax activation functionlayer_sparsemax
Weight Normalization layerlayer_weight_normalization
Lookahead mechanismlookahead_mechanism
Contrastive lossloss_contrastive
Implements the GIoU loss function.loss_giou
Hamming lossloss_hamming
Lifted structured lossloss_lifted_struct
Npairs lossloss_npairs
Npairs multilabel lossloss_npairs_multilabel
Pinball lossloss_pinball
Weighted cross-entropy loss for a sequence of logits.loss_sequence
Sigmoid focal crossentropy lossloss_sigmoid_focal_crossentropy
Sparsemax lossloss_sparsemax
Triplet hard lossloss_triplet_hard
Triplet semihard lossloss_triplet_semihard
Computes Kappa score between two ratersmetric_cohen_kappa
FBetaScoremetric_fbetascore
Hamming distancemetric_hamming_distance
MatthewsCorrelationCoefficientmetric_mcc
MultiLabelConfusionMatrixmetric_multilabel_confusion_matrix
RSquare This is also called as coefficient of determination. It tells how close are data to the fitted regression line. Highest score can be 1.0 and it indicates that the predictors perfectly accounts for variation in the target. Score 0.0 indicates that the predictors do not account for variation in the target. It can also be negative if the model is worse.metric_rsquare
F1Scoremetrics_f1score
Conditional Gradientoptimizer_conditional_gradient
Optimizer that implements the Adam algorithm with weight decayoptimizer_decay_adamw
Optimizer that implements the Momentum algorithm with weight_decayoptimizer_decay_sgdw
Layer-wise Adaptive Momentsoptimizer_lamb
Lazy Adamoptimizer_lazy_adam
Moving Averageoptimizer_moving_average
NovoGradoptimizer_novograd
Rectified Adam (a.k.a. RAdam)optimizer_radam
Stochastic Weight Averagingoptimizer_swa
Yogioptimizer_yogi
Parse timeparse_time
Register allregister_all
Register custom kernelsregister_custom_kernels
Register keras objectsregister_keras_objects
Safe cumprodsafe_cumprod
Bernoulli samplesample_bernoulli
Categorical samplesample_categorical
Samplersampler
Base abstract class that allows the user to customize sampling.sampler_custom
Greedy Embedding Samplersampler_greedy_embedding
Inference Samplersampler_inference
Sample Embedding Samplersampler_sample_embedding
A training sampler that adds scheduled samplingsampler_scheduled_embedding_training
Scheduled Output Training Samplersampler_scheduled_output_training
A Sampler for use during training.sampler_training
Skip gram sampleskip_gram_sample
Skip gram sample with text vocabskip_gram_sample_with_text_vocab
Version of TensorFlow SIG Addonstfaddons_version
Tile batchtile_batch
Viterbi decodeviterbi_decode