{ "_id": "6a1f2e0db401979e7342690f", "Package": "keras", "Type": "Package", "Title": "R Interface to 'Keras'", "Version": "2.16.1", "Authors@R": "c(\nperson(\"Tomasz\", \"Kalinowski\", role = c(\"ctb\", \"cph\", \"cre\"),\nemail = \"tomasz@posit.co\"),\nperson(\"Daniel\", \"Falbel\", role = c(\"ctb\", \"cph\"), email = \"daniel@rstudio.com\"),\nperson(\"JJ\", \"Allaire\", role = c(\"aut\", \"cph\")),\nperson(\"François\", \"Chollet\", role = c(\"aut\", \"cph\")),\nperson(\"RStudio\", role = c(\"ctb\", \"cph\", \"fnd\")),\nperson(\"Google\", role = c(\"ctb\", \"cph\", \"fnd\")),\nperson(\"Yuan\", \"Tang\", role = c(\"ctb\", \"cph\"),\nemail = \"terrytangyuan@gmail.com\",\ncomment = c(ORCID = \"0000-0001-5243-233X\")),\nperson(\"Wouter\", \"Van Der Bijl\", role = c(\"ctb\", \"cph\")),\nperson(\"Martin\", \"Studer\", role = c(\"ctb\", \"cph\")),\nperson(\"Sigrid\", \"Keydana\", role = c(\"ctb\"))\n)", "Description": "Interface to 'Keras' , a high-level\nneural networks 'API'. 'Keras' was developed with a focus on\nenabling fast experimentation, supports both convolution based\nnetworks and recurrent networks (as well as combinations of the\ntwo), and runs seamlessly on both 'CPU' and 'GPU' devices.", "Encoding": "UTF-8", "License": "MIT + file LICENSE", "URL": "https://tensorflow.rstudio.com/,\nhttps://github.com/rstudio/keras3/tree/r2", "BugReports": "https://github.com/rstudio/keras3/issues", "RoxygenNote": "7.3.3", "VignetteBuilder": "knitr", "NeedsCompilation": "no", "Packaged": { "Date": "2026-05-15 09:32:39 UTC", "User": "root" }, "Author": "Tomasz Kalinowski [ctb, cph, cre], Daniel Falbel [ctb, cph], JJ\nAllaire [aut, cph], François Chollet [aut, cph], RStudio [ctb,\ncph, fnd], Google [ctb, cph, fnd], Yuan Tang [ctb, cph] (ORCID:\n), Wouter Van Der Bijl\n[ctb, cph], Martin Studer [ctb, cph], Sigrid Keydana [ctb]", "Maintainer": "Tomasz Kalinowski ", "Config/pak/sysreqs": "libpng-dev python3", "Repository": "https://t-kalinowski.r-universe.dev", "Date/Publication": "2026-02-14 06:10:03 UTC", "RemoteUrl": "https://github.com/cran/keras", "RemoteRef": "HEAD", "RemoteSha": "458707c2f1cd154ae8e998ca2789cb73531753b4", "MD5sum": "4eea8b9cf122d6f548469b2f76306e01", "_user": "t-kalinowski", "_type": "src", "_file": "keras_2.16.1.tar.gz", "_fileid": "e7426c1979a689d9b01f358214f65fdb7b725a2bfd6c3c266909dd2636940d02", "_filesize": 4819914, "_sha256": "e7426c1979a689d9b01f358214f65fdb7b725a2bfd6c3c266909dd2636940d02", "_created": "2026-05-15T09:32:39.000Z", "_published": "2026-06-02T19:25:01.368Z", "_distro": "noble", "_jobs": [ { "job": 79153894455, "time": 172, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "7014194124" }, { "job": 79153894981, "time": 167, "config": "linux-release-x86_64", "r": "4.6.0", "check": "OK", "artifact": "7014194285" }, { "job": 79153894972, "time": 133, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "7014182552" }, { "job": 79153895087, "time": 104, "config": "macos-release-arm64", "r": "4.6.0", "check": "OK", "artifact": "7014173739" }, { "job": 79153893940, "time": 263, "config": "source", "r": "4.6.0", "check": "OK", "artifact": "7014140593" }, { "job": 79153894097, "time": 121, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "7367680244" }, { "job": 79153894742, "time": 148, "config": "windows-devel", "r": "4.7.0", "check": "OK", "artifact": "7014186903" }, { "job": 79153894942, "time": 135, "config": "windows-oldrel", "r": "4.5.3", "check": "OK", "artifact": "7014183113" }, { "job": 79153894910, "time": 134, "config": "windows-release", "r": "4.6.0", "check": "OK", "artifact": "7014182637" } ], "_buildurl": "https://github.com/r-universe/t-kalinowski/actions/runs/25910619203", "_status": "success", "_host": "GitHub-Actions", "_upstream": "https://github.com/cran/keras", "_commit": { "id": "458707c2f1cd154ae8e998ca2789cb73531753b4", "author": "Tomasz Kalinowski ", "committer": "cran-robot ", "message": "version 2.16.1\n", "time": 1771049403 }, "_maintainer": { "name": "Tomasz Kalinowski", "email": "tomasz@posit.co", "login": "t-kalinowski", "mastodon": "@t_kalinowski@fosstodon.org", "bluesky": "@t-kalinowski.bsky.social", "uuid": 8462255 }, "_registered": true, "_dependencies": [ { "package": "R", "version": ">= 3.6", "role": "Depends" }, { "package": "generics", "version": ">= 0.0.1", "role": "Imports" }, { "package": "reticulate", "version": ">= 1.31", "role": "Imports" }, { "package": "tensorflow", "version": ">= 2.13.0.9000", "role": "Imports" }, { "package": "tfruns", "version": ">= 1.0", "role": "Imports" }, { "package": "magrittr", "role": "Imports" }, { "package": "zeallot", "role": "Imports" }, { "package": "glue", "role": "Imports" }, { "package": "methods", "role": "Imports" }, { "package": "R6", "role": "Imports" }, { "package": "rlang", "role": "Imports" }, { "package": "ggplot2", "role": "Suggests" }, { "package": "testthat", "version": ">= 2.1.0", "role": "Suggests" }, { "package": "knitr", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" }, { "package": "callr", "role": "Suggests" }, { "package": "tfdatasets", "role": "Suggests" }, { "package": "withr", "role": "Suggests" }, { "package": "png", "role": "Suggests" }, { "package": "jpeg", "role": "Suggests" } ], "_owner": "cran", "_selfowned": true, "_usedby": 53, "_updates": [ { "week": "2025-34", "n": 1 }, { "week": "2026-07", "n": 1 } ], "_tags": [ { "name": "2.16.0", "date": "2025-08-18" }, { "name": "2.16.1", "date": "2026-02-14" } ], "_stars": 1, "_contributors": [ { "user": "jjallaire", "count": 11, "uuid": 104391 }, { "user": "t-kalinowski", "count": 11, "uuid": 8462255 } ], "_userbio": { "uuid": 8462255, "type": "user", "name": "Tomasz Kalinowski" }, "_downloads": { "count": 20234, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/keras" }, "_mentions": 141, "_devurl": "https://github.com/rstudio/keras3", "_searchresults": 11328, "_rbuild": "4.6.0", "_assets": [ "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/keras.html", "extra/NEWS.html", "extra/NEWS.txt", "manual.pdf" ], "_realowner": "t-kalinowski", "_cranurl": false, "_releases": [ { "version": "2.0.5", "date": "2017-07-30" }, { "version": "2.0.6", "date": "2017-08-30" }, { "version": "2.0.8", "date": "2017-09-30" }, { "version": "2.0.9", "date": "2017-11-17" }, { "version": "2.1.2", "date": "2017-12-17" }, { "version": "2.1.3", "date": "2018-01-17" }, { "version": "2.1.4", "date": "2018-02-24" }, { "version": "2.1.5", "date": "2018-03-28" }, { "version": "2.1.6", "date": "2018-04-29" }, { "version": "2.2.0", "date": "2018-08-24" }, { "version": "2.2.4", "date": "2018-11-22" }, { "version": "2.2.4.1", "date": "2019-04-06" }, { "version": "2.2.5.0", "date": "2019-10-08" }, { "version": "2.3.0.0", "date": "2020-05-19" }, { "version": "2.4.0", "date": "2021-03-29" }, { "version": "2.6.0", "date": "2021-08-21" }, { "version": "2.6.1", "date": "2021-09-30" }, { "version": "2.7.0", "date": "2021-11-09" }, { "version": "2.8.0", "date": "2022-02-10" }, { "version": "2.9.0", "date": "2022-05-23" }, { "version": "2.11.0", "date": "2022-12-20" }, { "version": "2.11.1", "date": "2023-03-20" }, { "version": "2.13.0", "date": "2023-08-15" }, { "version": "2.15.0", "date": "2024-04-20" }, { "version": "2.16.0", "date": "2025-08-18" }, { "version": "2.16.1", "date": "2026-02-16" } ], "_exports": [ "%<-%", "%<-active%", "%<>%", "%>%", "%py_class%", "activation_elu", "activation_exponential", "activation_gelu", "activation_hard_sigmoid", "activation_linear", "activation_relu", "activation_selu", "activation_sigmoid", "activation_softmax", "activation_softplus", "activation_softsign", "activation_swish", "activation_tanh", "adapt", "application_densenet", "application_densenet121", "application_densenet169", "application_densenet201", "application_efficientnet_b0", "application_efficientnet_b1", "application_efficientnet_b2", "application_efficientnet_b3", "application_efficientnet_b4", "application_efficientnet_b5", "application_efficientnet_b6", "application_efficientnet_b7", "application_inception_resnet_v2", "application_inception_v3", "application_mobilenet", "application_mobilenet_v2", "application_mobilenet_v3_large", "application_mobilenet_v3_small", "application_nasnet", "application_nasnetlarge", "application_nasnetmobile", "application_resnet101", "application_resnet101_v2", "application_resnet152", "application_resnet152_v2", "application_resnet50", "application_resnet50_v2", "application_vgg16", "application_vgg19", "application_xception", "array_reshape", "as_tensor", "backend", "bidirectional", "callback_backup_and_restore", "callback_csv_logger", "callback_early_stopping", "callback_lambda", "callback_learning_rate_scheduler", "callback_model_checkpoint", "callback_progbar_logger", "callback_reduce_lr_on_plateau", "callback_remote_monitor", "callback_tensorboard", "callback_terminate_on_naan", "clone_model", "compile", "constraint_maxnorm", "constraint_minmaxnorm", "constraint_nonneg", "constraint_unitnorm", "count_params", "create_layer", "create_layer_wrapper", "create_wrapper", "custom_metric", "dataset_boston_housing", "dataset_cifar10", "dataset_cifar100", "dataset_fashion_mnist", "dataset_imdb", "dataset_imdb_word_index", "dataset_mnist", "dataset_reuters", "dataset_reuters_word_index", "densenet_preprocess_input", "evaluate", "evaluate_generator", "export_savedmodel", "fit", "fit_generator", "fit_image_data_generator", "fit_text_tokenizer", "flag_boolean", "flag_integer", "flag_numeric", "flag_string", "flags", "flow_images_from_data", "flow_images_from_dataframe", "flow_images_from_directory", "freeze_weights", "from_config", "generator_next", "get_config", "get_file", "get_input_at", "get_input_mask_at", "get_input_shape_at", "get_layer", "get_output_at", "get_output_mask_at", "get_output_shape_at", "get_vocabulary", "get_weights", "hdf5_matrix", "image_array_resize", "image_array_save", "image_data_generator", "image_dataset_from_directory", "image_load", "image_to_array", "imagenet_decode_predictions", "imagenet_preprocess_input", "implementation", "inception_resnet_v2_preprocess_input", "inception_v3_preprocess_input", "initializer_constant", "initializer_glorot_normal", "initializer_glorot_uniform", "initializer_he_normal", "initializer_he_uniform", "initializer_identity", "initializer_lecun_normal", "initializer_lecun_uniform", "initializer_ones", "initializer_orthogonal", "initializer_random_normal", "initializer_random_uniform", "initializer_truncated_normal", "initializer_variance_scaling", "initializer_zeros", "install_keras", "is_keras_available", "k_abs", "k_all", "k_any", "k_arange", "k_argmax", "k_argmin", "k_backend", "k_batch_dot", "k_batch_flatten", "k_batch_get_value", "k_batch_normalization", "k_batch_set_value", "k_bias_add", "k_binary_crossentropy", "k_cast", "k_cast_to_floatx", "k_categorical_crossentropy", "k_clear_session", "k_clip", "k_concatenate", "k_constant", "k_conv1d", "k_conv2d", "k_conv2d_transpose", "k_conv3d", "k_conv3d_transpose", "k_cos", "k_count_params", "k_ctc_batch_cost", "k_ctc_decode", "k_ctc_label_dense_to_sparse", "k_cumprod", "k_cumsum", "k_depthwise_conv2d", "k_dot", "k_dropout", "k_dtype", "k_elu", "k_epsilon", "k_equal", "k_eval", "k_exp", "k_expand_dims", "k_eye", "k_flatten", "k_floatx", "k_foldl", "k_foldr", "k_function", "k_gather", "k_get_session", "k_get_uid", "k_get_value", "k_get_variable_shape", "k_gradients", "k_greater", "k_greater_equal", "k_hard_sigmoid", "k_identity", "k_image_data_format", "k_in_test_phase", "k_in_top_k", "k_in_train_phase", "k_int_shape", "k_is_keras_tensor", "k_is_placeholder", "k_is_sparse", "k_is_tensor", "k_l2_normalize", "k_learning_phase", "k_less", "k_less_equal", "k_local_conv1d", "k_local_conv2d", "k_log", "k_logsumexp", "k_manual_variable_initialization", "k_map_fn", "k_max", "k_maximum", "k_mean", "k_min", "k_minimum", "k_moving_average_update", "k_ndim", "k_normalize_batch_in_training", "k_not_equal", "k_one_hot", "k_ones", "k_ones_like", "k_permute_dimensions", "k_placeholder", "k_pool2d", "k_pool3d", "k_pow", "k_print_tensor", "k_prod", "k_random_bernoulli", "k_random_binomial", "k_random_normal", "k_random_normal_variable", "k_random_uniform", "k_random_uniform_variable", "k_relu", "k_repeat", "k_repeat_elements", "k_reset_uids", "k_reshape", "k_resize_images", "k_resize_volumes", "k_reverse", "k_rnn", "k_round", "k_separable_conv2d", "k_set_epsilon", "k_set_floatx", "k_set_image_data_format", "k_set_learning_phase", "k_set_session", "k_set_value", "k_shape", "k_sigmoid", "k_sign", "k_sin", "k_softmax", "k_softplus", "k_softsign", "k_sparse_categorical_crossentropy", "k_spatial_2d_padding", "k_spatial_3d_padding", "k_sqrt", "k_square", "k_squeeze", "k_stack", "k_std", "k_stop_gradient", "k_sum", "k_switch", "k_tanh", "k_temporal_padding", "k_tile", "k_to_dense", "k_transpose", "k_truncated_normal", "k_unstack", "k_update", "k_update_add", "k_update_sub", "k_var", "k_variable", "k_zeros", "k_zeros_like", "keras", "keras_array", "keras_model", "keras_model_custom", "keras_model_sequential", "KerasCallback", "KerasConstraint", "KerasLayer", "KerasWrapper", "Layer", "layer_activation", "layer_activation_elu", "layer_activation_leaky_relu", "layer_activation_parametric_relu", "layer_activation_relu", "layer_activation_selu", "layer_activation_softmax", "layer_activation_thresholded_relu", "layer_activity_regularization", "layer_add", "layer_additive_attention", "layer_alpha_dropout", "layer_attention", "layer_average", "layer_average_pooling_1d", "layer_average_pooling_2d", "layer_average_pooling_3d", "layer_batch_normalization", "layer_category_encoding", "layer_center_crop", "layer_concatenate", "layer_conv_1d", "layer_conv_1d_transpose", "layer_conv_2d", "layer_conv_2d_transpose", "layer_conv_3d", "layer_conv_3d_transpose", "layer_conv_lstm_1d", "layer_conv_lstm_2d", "layer_conv_lstm_3d", "layer_cropping_1d", "layer_cropping_2d", "layer_cropping_3d", "layer_cudnn_gru", "layer_cudnn_lstm", "layer_dense", "layer_dense_features", "layer_depthwise_conv_1d", "layer_depthwise_conv_2d", "layer_discretization", "layer_dot", "layer_dropout", "layer_embedding", "layer_flatten", "layer_gaussian_dropout", "layer_gaussian_noise", "layer_global_average_pooling_1d", "layer_global_average_pooling_2d", "layer_global_average_pooling_3d", "layer_global_max_pooling_1d", "layer_global_max_pooling_2d", "layer_global_max_pooling_3d", "layer_gru", "layer_gru_cell", "layer_hashing", "layer_input", "layer_integer_lookup", "layer_lambda", "layer_layer_normalization", "layer_locally_connected_1d", "layer_locally_connected_2d", "layer_lstm", "layer_lstm_cell", "layer_masking", "layer_max_pooling_1d", "layer_max_pooling_2d", "layer_max_pooling_3d", "layer_maximum", "layer_minimum", "layer_multi_head_attention", "layer_multiply", "layer_normalization", "layer_permute", "layer_random_brightness", "layer_random_contrast", "layer_random_crop", "layer_random_flip", "layer_random_height", "layer_random_rotation", "layer_random_translation", "layer_random_width", "layer_random_zoom", "layer_repeat_vector", "layer_rescaling", "layer_reshape", "layer_resizing", "layer_rnn", "layer_separable_conv_1d", "layer_separable_conv_2d", "layer_simple_rnn", "layer_simple_rnn_cell", "layer_spatial_dropout_1d", "layer_spatial_dropout_2d", "layer_spatial_dropout_3d", "layer_stacked_rnn_cells", "layer_string_lookup", "layer_subtract", "layer_text_vectorization", "layer_unit_normalization", "layer_upsampling_1d", "layer_upsampling_2d", "layer_upsampling_3d", "layer_zero_padding_1d", "layer_zero_padding_2d", "layer_zero_padding_3d", "learning_rate_schedule_cosine_decay", "learning_rate_schedule_cosine_decay_restarts", "learning_rate_schedule_exponential_decay", "learning_rate_schedule_inverse_time_decay", "learning_rate_schedule_piecewise_constant_decay", "learning_rate_schedule_polynomial_decay", "load_model_hdf5", "load_model_tf", "load_model_weights_hdf5", "load_model_weights_tf", "load_text_tokenizer", "loss_binary_crossentropy", "loss_categorical_crossentropy", "loss_categorical_hinge", "loss_cosine_proximity", "loss_cosine_similarity", "loss_hinge", "loss_huber", "loss_kl_divergence", "loss_kullback_leibler_divergence", "loss_logcosh", "loss_mean_absolute_error", "loss_mean_absolute_percentage_error", "loss_mean_squared_error", "loss_mean_squared_logarithmic_error", "loss_poisson", "loss_sparse_categorical_crossentropy", "loss_squared_hinge", "make_sampling_table", "mark_active", "metric_accuracy", "metric_auc", "metric_binary_accuracy", "metric_binary_crossentropy", "metric_categorical_accuracy", "metric_categorical_crossentropy", "metric_categorical_hinge", "metric_cosine_proximity", "metric_cosine_similarity", "metric_false_negatives", "metric_false_positives", "metric_hinge", "metric_kullback_leibler_divergence", "metric_logcosh_error", "metric_mean", "metric_mean_absolute_error", "metric_mean_absolute_percentage_error", "metric_mean_iou", "metric_mean_relative_error", "metric_mean_squared_error", "metric_mean_squared_logarithmic_error", "metric_mean_tensor", "metric_mean_wrapper", "metric_poisson", "metric_precision", "metric_precision_at_recall", "metric_recall", "metric_recall_at_precision", "metric_root_mean_squared_error", "metric_sensitivity_at_specificity", "metric_sparse_categorical_accuracy", "metric_sparse_categorical_crossentropy", "metric_sparse_top_k_categorical_accuracy", "metric_specificity_at_sensitivity", "metric_squared_hinge", "metric_sum", "metric_top_k_categorical_accuracy", "metric_true_negatives", "metric_true_positives", "mobilenet_decode_predictions", "mobilenet_load_model_hdf5", "mobilenet_preprocess_input", "mobilenet_v2_decode_predictions", "mobilenet_v2_load_model_hdf5", "mobilenet_v2_preprocess_input", "model_from_json", "model_from_saved_model", "model_from_yaml", "model_to_json", "model_to_saved_model", "model_to_yaml", "multi_gpu_model", "nasnet_preprocess_input", "new_callback_class", "new_layer_class", "new_learning_rate_schedule_class", "new_loss_class", "new_metric_class", "new_model_class", "normalize", "optimizer_adadelta", "optimizer_adagrad", "optimizer_adam", "optimizer_adamax", "optimizer_ftrl", "optimizer_nadam", "optimizer_rmsprop", "optimizer_sgd", "pad_sequences", "pop_layer", "predict_classes", "predict_generator", "predict_on_batch", "predict_proba", "py_require_legacy_keras", "regularizer_l1", "regularizer_l1_l2", "regularizer_l2", "regularizer_orthogonal", "reset_states", "resnet_preprocess_input", "resnet_v2_preprocess_input", "run_dir", "save_model_hdf5", "save_model_tf", "save_model_weights_hdf5", "save_model_weights_tf", "save_text_tokenizer", "sequences_to_matrix", "serialize_model", "set_vocabulary", "set_weights", "shape", "skipgrams", "tensorboard", "test_on_batch", "text_dataset_from_directory", "text_hashing_trick", "text_one_hot", "text_to_word_sequence", "text_tokenizer", "texts_to_matrix", "texts_to_sequences", "texts_to_sequences_generator", "time_distributed", "timeseries_dataset_from_array", "timeseries_generator", "to_categorical", "train_on_batch", "tuple", "unfreeze_weights", "unserialize_model", "use_backend", "use_condaenv", "use_implementation", "use_python", "use_session_with_seed", "use_virtualenv", "with_custom_object_scope", "xception_preprocess_input", "zip_lists" ], "_help": [ { "page": "keras-package", "title": "R interface to Keras", "topics": [ "keras-package" ] }, { "page": "grapes-set-active-grapes", "title": "Make an Active Binding", "topics": [ "%<-active%" ] }, { "page": "grapes-py_class-grapes", "title": "Make a python class constructor", "topics": [ "%py_class%", "py_class" ] }, { "page": "activation_relu", "title": "Activation functions", "topics": [ "activation_elu", "activation_exponential", "activation_gelu", "activation_hard_sigmoid", "activation_linear", "activation_relu", "activation_selu", "activation_sigmoid", "activation_softmax", "activation_softplus", "activation_softsign", "activation_swish", "activation_tanh" ] }, { "page": "adapt", "title": "Fits the state of the preprocessing layer to the data being passed", "concept": [ "preprocessing layer methods" ], "topics": [ "adapt" ] }, { "page": "application_densenet", "title": "Instantiates the DenseNet architecture.", "topics": [ "application_densenet", "application_densenet121", "application_densenet169", "application_densenet201", "densenet_preprocess_input" ] }, { "page": "application_efficientnet", "title": "Instantiates the EfficientNetB0 architecture", "topics": [ "application_efficientnet", "application_efficientnet_b0", "application_efficientnet_b1", "application_efficientnet_b2", "application_efficientnet_b3", "application_efficientnet_b4", "application_efficientnet_b5", "application_efficientnet_b6", "application_efficientnet_b7" ] }, { "page": "application_inception_resnet_v2", "title": "Inception-ResNet v2 model, with weights trained on ImageNet", "topics": [ "application_inception_resnet_v2", "inception_resnet_v2_preprocess_input" ] }, { "page": "application_inception_v3", "title": "Inception V3 model, with weights pre-trained on ImageNet.", "topics": [ "application_inception_v3", "inception_v3_preprocess_input" ] }, { "page": "application_mobilenet", "title": "MobileNet model architecture.", "topics": [ "application_mobilenet", "mobilenet_decode_predictions", "mobilenet_load_model_hdf5", "mobilenet_preprocess_input" ] }, { "page": "application_mobilenet_v2", "title": "MobileNetV2 model architecture", "topics": [ "application_mobilenet_v2", "mobilenet_v2_decode_predictions", "mobilenet_v2_load_model_hdf5", "mobilenet_v2_preprocess_input" ] }, { "page": "application_mobilenet_v3", "title": "Instantiates the MobileNetV3Large architecture", "topics": [ "application_mobilenet_v3", "application_mobilenet_v3_large", "application_mobilenet_v3_small" ] }, { "page": "application_nasnet", "title": "Instantiates a NASNet model.", "topics": [ "application_nasnet", "application_nasnetlarge", "application_nasnetmobile", "nasnet_preprocess_input" ] }, { "page": "application_resnet", "title": "Instantiates the ResNet architecture", "topics": [ "application_resnet", "application_resnet101", "application_resnet101_v2", "application_resnet152", "application_resnet152_v2", "application_resnet50", "application_resnet50_v2", "resnet_preprocess_input", "resnet_v2_preprocess_input" ] }, { "page": "application_vgg", "title": "VGG16 and VGG19 models for Keras.", "topics": [ "application_vgg", "application_vgg16", "application_vgg19" ] }, { "page": "application_xception", "title": "Instantiates the Xception architecture", "topics": [ "application_xception", "xception_preprocess_input" ] }, { "page": "backend", "title": "Keras backend tensor engine", "topics": [ "backend" ] }, { "page": "bidirectional", "title": "Bidirectional wrapper for RNNs", "concept": [ "layer wrappers" ], "topics": [ "bidirectional" ] }, { "page": "callback_backup_and_restore", "title": "Callback to back up and restore the training state", "topics": [ "callback_backup_and_restore" ] }, { "page": "callback_csv_logger", "title": "Callback that streams epoch results to a csv file", "concept": [ "callbacks" ], "topics": [ "callback_csv_logger" ] }, { "page": "callback_early_stopping", "title": "Stop training when a monitored quantity has stopped improving.", "concept": [ "callbacks" ], "topics": [ "callback_early_stopping" ] }, { "page": "callback_lambda", "title": "Create a custom callback", "concept": [ "callbacks" ], "topics": [ "callback_lambda" ] }, { "page": "callback_learning_rate_scheduler", "title": "Learning rate scheduler.", "concept": [ "callbacks" ], "topics": [ "callback_learning_rate_scheduler" ] }, { "page": "callback_model_checkpoint", "title": "Save the model after every epoch.", "concept": [ "callbacks" ], "topics": [ "callback_model_checkpoint" ] }, { "page": "callback_progbar_logger", "title": "Callback that prints metrics to stdout.", "concept": [ "callbacks" ], "topics": [ "callback_progbar_logger" ] }, { "page": "callback_reduce_lr_on_plateau", "title": "Reduce learning rate when a metric has stopped improving.", "concept": [ "callbacks" ], "topics": [ "callback_reduce_lr_on_plateau" ] }, { "page": "callback_remote_monitor", "title": "Callback used to stream events to a server.", "concept": [ "callbacks" ], "topics": [ "callback_remote_monitor" ] }, { "page": "callback_tensorboard", "title": "TensorBoard basic visualizations", "concept": [ "callbacks" ], "topics": [ "callback_tensorboard" ] }, { "page": "callback_terminate_on_naan", "title": "Callback that terminates training when a NaN loss is encountered.", "concept": [ "callbacks" ], "topics": [ "callback_terminate_on_naan" ] }, { "page": "clone_model", "title": "Clone a model instance.", "topics": [ "clone_model" ] }, { "page": "compile.keras.engine.training.Model", "title": "Configure a Keras model for training", "concept": [ "model functions" ], "topics": [ "compile.keras.engine.training.Model" ] }, { "page": "constraints", "title": "Weight constraints", "topics": [ "constraints", "constraint_maxnorm", "constraint_minmaxnorm", "constraint_nonneg", "constraint_unitnorm" ] }, { "page": "count_params", "title": "Count the total number of scalars composing the weights.", "concept": [ "layer methods" ], "topics": [ "count_params" ] }, { "page": "create_layer", "title": "Create a Keras Layer", "topics": [ "create_layer" ] }, { "page": "create_layer_wrapper", "title": "Create a Keras Layer wrapper", "topics": [ "create_layer_wrapper" ] }, { "page": "custom_metric", "title": "Custom metric function", "concept": [ "metrics" ], "topics": [ "custom_metric" ] }, { "page": "dataset_boston_housing", "title": "Boston housing price regression dataset", "concept": [ "datasets" ], "topics": [ "dataset_boston_housing" ] }, { "page": "dataset_cifar10", "title": "CIFAR10 small image classification", "concept": [ "datasets" ], "topics": [ "dataset_cifar10" ] }, { "page": "dataset_cifar100", "title": "CIFAR100 small image classification", "concept": [ "datasets" ], "topics": [ "dataset_cifar100" ] }, { "page": "dataset_fashion_mnist", "title": "Fashion-MNIST database of fashion articles", "concept": [ "datasets" ], "topics": [ "dataset_fashion_mnist" ] }, { "page": "dataset_imdb", "title": "IMDB Movie reviews sentiment classification", "concept": [ "datasets" ], "topics": [ "dataset_imdb", "dataset_imdb_word_index" ] }, { "page": "dataset_mnist", "title": "MNIST database of handwritten digits", "concept": [ "datasets" ], "topics": [ "dataset_mnist" ] }, { "page": "dataset_reuters", "title": "Reuters newswire topics classification", "concept": [ "datasets" ], "topics": [ "dataset_reuters", "dataset_reuters_word_index" ] }, { "page": "evaluate.keras.engine.training.Model", "title": "Evaluate a Keras model", "concept": [ "model functions" ], "topics": [ "evaluate.keras.engine.training.Model" ] }, { "page": "export_savedmodel.keras.engine.training.Model", "title": "Export a Saved Model", "topics": [ "export_savedmodel.keras.engine.training.Model" ] }, { "page": "fit_image_data_generator", "title": "Fit image data generator internal statistics to some sample data.", "concept": [ "image preprocessing" ], "topics": [ "fit_image_data_generator" ] }, { "page": "fit_text_tokenizer", "title": "Update tokenizer internal vocabulary based on a list of texts or list of sequences.", "concept": [ "text tokenization" ], "topics": [ "fit_text_tokenizer" ] }, { "page": "fit.keras.engine.training.Model", "title": "Train a Keras model", "concept": [ "model functions" ], "topics": [ "fit.keras.engine.training.Model" ] }, { "page": "flow_images_from_data", "title": "Generates batches of augmented/normalized data from image data and labels", "concept": [ "image preprocessing" ], "topics": [ "flow_images_from_data" ] }, { "page": "flow_images_from_dataframe", "title": "Takes the dataframe and the path to a directory and generates batches of augmented/normalized data.", "concept": [ "image preprocessing" ], "topics": [ "flow_images_from_dataframe" ] }, { "page": "flow_images_from_directory", "title": "Generates batches of data from images in a directory (with optional augmented/normalized data)", "concept": [ "image preprocessing" ], "topics": [ "flow_images_from_directory" ] }, { "page": "freeze_weights", "title": "Freeze and unfreeze weights", "topics": [ "freeze_weights", "unfreeze_weights" ] }, { "page": "generator_next", "title": "Retrieve the next item from a generator", "topics": [ "generator_next" ] }, { "page": "get_config", "title": "Layer/Model configuration", "concept": [ "layer methods", "model functions" ], "topics": [ "from_config", "get_config" ] }, { "page": "get_file", "title": "Downloads a file from a URL if it not already in the cache.", "topics": [ "get_file" ] }, { "page": "get_input_at", "title": "Retrieve tensors for layers with multiple nodes", "concept": [ "layer methods" ], "topics": [ "get_input_at", "get_input_mask_at", "get_input_shape_at", "get_output_at", "get_output_mask_at", "get_output_shape_at" ] }, { "page": "get_layer", "title": "Retrieves a layer based on either its name (unique) or index.", "concept": [ "model functions" ], "topics": [ "get_layer" ] }, { "page": "get_weights", "title": "Layer/Model weights as R arrays", "concept": [ "layer methods", "model persistence" ], "topics": [ "get_weights", "set_weights" ] }, { "page": "hdf5_matrix", "title": "Representation of HDF5 dataset to be used instead of an R array", "topics": [ "hdf5_matrix" ] }, { "page": "image_data_generator", "title": "Deprecated Generate batches of image data with real-time data augmentation. The data will be looped over (in batches).", "topics": [ "image_data_generator" ] }, { "page": "image_dataset_from_directory", "title": "Create a dataset from a directory", "topics": [ "image_dataset_from_directory" ] }, { "page": "image_load", "title": "Loads an image into PIL format.", "concept": [ "image preprocessing" ], "topics": [ "image_load" ] }, { "page": "image_to_array", "title": "3D array representation of images", "concept": [ "image preprocessing" ], "topics": [ "image_array_resize", "image_array_save", "image_to_array" ] }, { "page": "imagenet_decode_predictions", "title": "Decodes the prediction of an ImageNet model.", "topics": [ "imagenet_decode_predictions" ] }, { "page": "imagenet_preprocess_input", "title": "Preprocesses a tensor or array encoding a batch of images.", "topics": [ "imagenet_preprocess_input" ] }, { "page": "implementation", "title": "Keras implementation", "topics": [ "implementation" ] }, { "page": "initializer_constant", "title": "Initializer that generates tensors initialized to a constant value.", "concept": [ "initializers" ], "topics": [ "initializer_constant" ] }, { "page": "initializer_glorot_normal", "title": "Glorot normal initializer, also called Xavier normal initializer.", "concept": [ "initializers" ], "topics": [ "initializer_glorot_normal" ] }, { "page": "initializer_glorot_uniform", "title": "Glorot uniform initializer, also called Xavier uniform initializer.", "concept": [ "initializers" ], "topics": [ "initializer_glorot_uniform" ] }, { "page": "initializer_he_normal", "title": "He normal initializer.", "concept": [ "initializers" ], "topics": [ "initializer_he_normal" ] }, { "page": "initializer_he_uniform", "title": "He uniform variance scaling initializer.", "concept": [ "initializers" ], "topics": [ "initializer_he_uniform" ] }, { "page": "initializer_identity", "title": "Initializer that generates the identity matrix.", "concept": [ "initializers" ], "topics": [ "initializer_identity" ] }, { "page": "initializer_lecun_normal", "title": "LeCun normal initializer.", "concept": [ "initializers" ], "topics": [ "initializer_lecun_normal" ] }, { "page": "initializer_lecun_uniform", "title": "LeCun uniform initializer.", "concept": [ "initializers" ], "topics": [ "initializer_lecun_uniform" ] }, { "page": "initializer_ones", "title": "Initializer that generates tensors initialized to 1.", "concept": [ "initializers" ], "topics": [ "initializer_ones" ] }, { "page": "initializer_orthogonal", "title": "Initializer that generates a random orthogonal matrix.", "concept": [ "initializers" ], "topics": [ "initializer_orthogonal" ] }, { "page": "initializer_random_normal", "title": "Initializer that generates tensors with a normal distribution.", "concept": [ "initializers" ], "topics": [ "initializer_random_normal" ] }, { "page": "initializer_random_uniform", "title": "Initializer that generates tensors with a uniform distribution.", "concept": [ "initializers" ], "topics": [ "initializer_random_uniform" ] }, { "page": "initializer_truncated_normal", "title": "Initializer that generates a truncated normal distribution.", "concept": [ "initializers" ], "topics": [ "initializer_truncated_normal" ] }, { "page": "initializer_variance_scaling", "title": "Initializer capable of adapting its scale to the shape of weights.", "concept": [ "initializers" ], "topics": [ "initializer_variance_scaling" ] }, { "page": "initializer_zeros", "title": "Initializer that generates tensors initialized to 0.", "concept": [ "initializers" ], "topics": [ "initializer_zeros" ] }, { "page": "install_keras", "title": "Install TensorFlow and Legacy Keras, including all Python dependencies", "topics": [ "install_keras", "py_require_legacy_keras" ] }, { "page": "is_keras_available", "title": "Check if Keras is Available", "topics": [ "is_keras_available" ] }, { "page": "k_abs", "title": "Element-wise absolute value.", "topics": [ "k_abs" ] }, { "page": "k_all", "title": "Bitwise reduction (logical AND).", "topics": [ "k_all" ] }, { "page": "k_any", "title": "Bitwise reduction (logical OR).", "topics": [ "k_any" ] }, { "page": "k_arange", "title": "Creates a 1D tensor containing a sequence of integers.", "topics": [ "k_arange" ] }, { "page": "k_argmax", "title": "Returns the index of the maximum value along an axis.", "topics": [ "k_argmax" ] }, { "page": "k_argmin", "title": "Returns the index of the minimum value along an axis.", "topics": [ "k_argmin" ] }, { "page": "k_backend", "title": "Active Keras backend", "topics": [ "k_backend" ] }, { "page": "k_batch_dot", "title": "Batchwise dot product.", "topics": [ "k_batch_dot" ] }, { "page": "k_batch_flatten", "title": "Turn a nD tensor into a 2D tensor with same 1st dimension.", "topics": [ "k_batch_flatten" ] }, { "page": "k_batch_get_value", "title": "Returns the value of more than one tensor variable.", "topics": [ "k_batch_get_value" ] }, { "page": "k_batch_normalization", "title": "Applies batch normalization on x given mean, var, beta and gamma.", "topics": [ "k_batch_normalization" ] }, { "page": "k_batch_set_value", "title": "Sets the values of many tensor variables at once.", "topics": [ "k_batch_set_value" ] }, { "page": "k_bias_add", "title": "Adds a bias vector to a tensor.", "topics": [ "k_bias_add" ] }, { "page": "k_binary_crossentropy", "title": "Binary crossentropy between an output tensor and a target tensor.", "topics": [ "k_binary_crossentropy" ] }, { "page": "k_cast", "title": "Casts a tensor to a different dtype and returns it.", "topics": [ "k_cast" ] }, { "page": "k_cast_to_floatx", "title": "Cast an array to the default Keras float type.", "topics": [ "k_cast_to_floatx" ] }, { "page": "k_categorical_crossentropy", "title": "Categorical crossentropy between an output tensor and a target tensor.", "topics": [ "k_categorical_crossentropy" ] }, { "page": "k_clear_session", "title": "Destroys the current TF graph and creates a new one.", "topics": [ "k_clear_session" ] }, { "page": "k_clip", "title": "Element-wise value clipping.", "topics": [ "k_clip" ] }, { "page": "k_concatenate", "title": "Concatenates a list of tensors alongside the specified axis.", "topics": [ "k_concatenate" ] }, { "page": "k_constant", "title": "Creates a constant tensor.", "topics": [ "k_constant" ] }, { "page": "k_conv1d", "title": "1D convolution.", "topics": [ "k_conv1d" ] }, { "page": "k_conv2d", "title": "2D convolution.", "topics": [ "k_conv2d" ] }, { "page": "k_conv2d_transpose", "title": "2D deconvolution (i.e. transposed convolution).", "topics": [ "k_conv2d_transpose" ] }, { "page": "k_conv3d", "title": "3D convolution.", "topics": [ "k_conv3d" ] }, { "page": "k_conv3d_transpose", "title": "3D deconvolution (i.e. transposed convolution).", "topics": [ "k_conv3d_transpose" ] }, { "page": "k_cos", "title": "Computes cos of x element-wise.", "topics": [ "k_cos" ] }, { "page": "k_count_params", "title": "Returns the static number of elements in a Keras variable or tensor.", "topics": [ "k_count_params" ] }, { "page": "k_ctc_batch_cost", "title": "Runs CTC loss algorithm on each batch element.", "topics": [ "k_ctc_batch_cost" ] }, { "page": "k_ctc_decode", "title": "Decodes the output of a softmax.", "topics": [ "k_ctc_decode" ] }, { "page": "k_ctc_label_dense_to_sparse", "title": "Converts CTC labels from dense to sparse.", "topics": [ "k_ctc_label_dense_to_sparse" ] }, { "page": "k_cumprod", "title": "Cumulative product of the values in a tensor, alongside the specified axis.", "topics": [ "k_cumprod" ] }, { "page": "k_cumsum", "title": "Cumulative sum of the values in a tensor, alongside the specified axis.", "topics": [ "k_cumsum" ] }, { "page": "k_depthwise_conv2d", "title": "Depthwise 2D convolution with separable filters.", "topics": [ "k_depthwise_conv2d" ] }, { "page": "k_dot", "title": "Multiplies 2 tensors (and/or variables) and returns a _tensor_.", "topics": [ "k_dot" ] }, { "page": "k_dropout", "title": "Sets entries in 'x' to zero at random, while scaling the entire tensor.", "topics": [ "k_dropout" ] }, { "page": "k_dtype", "title": "Returns the dtype of a Keras tensor or variable, as a string.", "topics": [ "k_dtype" ] }, { "page": "k_elu", "title": "Exponential linear unit.", "topics": [ "k_elu" ] }, { "page": "k_epsilon", "title": "Fuzz factor used in numeric expressions.", "topics": [ "k_epsilon", "k_set_epsilon" ] }, { "page": "k_equal", "title": "Element-wise equality between two tensors.", "topics": [ "k_equal" ] }, { "page": "k_eval", "title": "Evaluates the value of a variable.", "topics": [ "k_eval" ] }, { "page": "k_exp", "title": "Element-wise exponential.", "topics": [ "k_exp" ] }, { "page": "k_expand_dims", "title": "Adds a 1-sized dimension at index 'axis'.", "topics": [ "k_expand_dims" ] }, { "page": "k_eye", "title": "Instantiate an identity matrix and returns it.", "topics": [ "k_eye" ] }, { "page": "k_flatten", "title": "Flatten a tensor.", "topics": [ "k_flatten" ] }, { "page": "k_floatx", "title": "Default float type", "topics": [ "k_floatx", "k_set_floatx" ] }, { "page": "k_foldl", "title": "Reduce elems using fn to combine them from left to right.", "topics": [ "k_foldl" ] }, { "page": "k_foldr", "title": "Reduce elems using fn to combine them from right to left.", "topics": [ "k_foldr" ] }, { "page": "k_function", "title": "Instantiates a Keras function", "topics": [ "k_function" ] }, { "page": "k_gather", "title": "Retrieves the elements of indices 'indices' in the tensor 'reference'.", "topics": [ "k_gather" ] }, { "page": "k_get_session", "title": "TF session to be used by the backend.", "topics": [ "k_get_session", "k_set_session" ] }, { "page": "k_get_uid", "title": "Get the uid for the default graph.", "topics": [ "k_get_uid" ] }, { "page": "k_get_value", "title": "Returns the value of a variable.", "topics": [ "k_get_value" ] }, { "page": "k_get_variable_shape", "title": "Returns the shape of a variable.", "topics": [ "k_get_variable_shape" ] }, { "page": "k_gradients", "title": "Returns the gradients of 'variables' w.r.t. 'loss'.", "topics": [ "k_gradients" ] }, { "page": "k_greater", "title": "Element-wise truth value of (x > y).", "topics": [ "k_greater" ] }, { "page": "k_greater_equal", "title": "Element-wise truth value of (x >= y).", "topics": [ "k_greater_equal" ] }, { "page": "k_hard_sigmoid", "title": "Segment-wise linear approximation of sigmoid.", "topics": [ "k_hard_sigmoid" ] }, { "page": "k_identity", "title": "Returns a tensor with the same content as the input tensor.", "topics": [ "k_identity" ] }, { "page": "k_image_data_format", "title": "Default image data format convention ('channels_first' or 'channels_last').", "topics": [ "k_image_data_format", "k_set_image_data_format" ] }, { "page": "k_in_test_phase", "title": "Selects 'x' in test phase, and 'alt' otherwise.", "topics": [ "k_in_test_phase" ] }, { "page": "k_in_top_k", "title": "Returns whether the 'targets' are in the top 'k' 'predictions'.", "topics": [ "k_in_top_k" ] }, { "page": "k_in_train_phase", "title": "Selects 'x' in train phase, and 'alt' otherwise.", "topics": [ "k_in_train_phase" ] }, { "page": "k_int_shape", "title": "Returns the shape of tensor or variable as a list of int or NULL entries.", "topics": [ "k_int_shape" ] }, { "page": "k_is_keras_tensor", "title": "Returns whether 'x' is a Keras tensor.", "topics": [ "k_is_keras_tensor" ] }, { "page": "k_is_placeholder", "title": "Returns whether 'x' is a placeholder.", "topics": [ "k_is_placeholder" ] }, { "page": "k_is_sparse", "title": "Returns whether a tensor is a sparse tensor.", "topics": [ "k_is_sparse" ] }, { "page": "k_is_tensor", "title": "Returns whether 'x' is a symbolic tensor.", "topics": [ "k_is_tensor" ] }, { "page": "k_l2_normalize", "title": "Normalizes a tensor wrt the L2 norm alongside the specified axis.", "topics": [ "k_l2_normalize" ] }, { "page": "k_learning_phase", "title": "Returns the learning phase flag.", "topics": [ "k_learning_phase" ] }, { "page": "k_less", "title": "Element-wise truth value of (x < y).", "topics": [ "k_less" ] }, { "page": "k_less_equal", "title": "Element-wise truth value of (x <= y).", "topics": [ "k_less_equal" ] }, { "page": "k_local_conv1d", "title": "Apply 1D conv with un-shared weights.", "topics": [ "k_local_conv1d" ] }, { "page": "k_local_conv2d", "title": "Apply 2D conv with un-shared weights.", "topics": [ "k_local_conv2d" ] }, { "page": "k_log", "title": "Element-wise log.", "topics": [ "k_log" ] }, { "page": "k_manual_variable_initialization", "title": "Sets the manual variable initialization flag.", "topics": [ "k_manual_variable_initialization" ] }, { "page": "k_map_fn", "title": "Map the function fn over the elements elems and return the outputs.", "topics": [ "k_map_fn" ] }, { "page": "k_max", "title": "Maximum value in a tensor.", "topics": [ "k_max" ] }, { "page": "k_maximum", "title": "Element-wise maximum of two tensors.", "topics": [ "k_maximum" ] }, { "page": "k_mean", "title": "Mean of a tensor, alongside the specified axis.", "topics": [ "k_mean" ] }, { "page": "k_min", "title": "Minimum value in a tensor.", "topics": [ "k_min" ] }, { "page": "k_minimum", "title": "Element-wise minimum of two tensors.", "topics": [ "k_minimum" ] }, { "page": "k_moving_average_update", "title": "Compute the moving average of a variable.", "topics": [ "k_moving_average_update" ] }, { "page": "k_ndim", "title": "Returns the number of axes in a tensor, as an integer.", "topics": [ "k_ndim" ] }, { "page": "k_normalize_batch_in_training", "title": "Computes mean and std for batch then apply batch_normalization on batch.", "topics": [ "k_normalize_batch_in_training" ] }, { "page": "k_not_equal", "title": "Element-wise inequality between two tensors.", "topics": [ "k_not_equal" ] }, { "page": "k_one_hot", "title": "Computes the one-hot representation of an integer tensor.", "topics": [ "k_one_hot" ] }, { "page": "k_ones", "title": "Instantiates an all-ones tensor variable and returns it.", "topics": [ "k_ones" ] }, { "page": "k_ones_like", "title": "Instantiates an all-ones variable of the same shape as another tensor.", "topics": [ "k_ones_like" ] }, { "page": "k_permute_dimensions", "title": "Permutes axes in a tensor.", "topics": [ "k_permute_dimensions" ] }, { "page": "k_placeholder", "title": "Instantiates a placeholder tensor and returns it.", "topics": [ "k_placeholder" ] }, { "page": "k_pool2d", "title": "2D Pooling.", "topics": [ "k_pool2d" ] }, { "page": "k_pool3d", "title": "3D Pooling.", "topics": [ "k_pool3d" ] }, { "page": "k_pow", "title": "Element-wise exponentiation.", "topics": [ "k_pow" ] }, { "page": "k_print_tensor", "title": "Prints 'message' and the tensor value when evaluated.", "topics": [ "k_print_tensor" ] }, { "page": "k_prod", "title": "Multiplies the values in a tensor, alongside the specified axis.", "topics": [ "k_prod" ] }, { "page": "k_random_bernoulli", "title": "Returns a tensor with random binomial distribution of values.", "topics": [ "k_random_bernoulli", "k_random_binomial" ] }, { "page": "k_random_normal", "title": "Returns a tensor with normal distribution of values.", "topics": [ "k_random_normal" ] }, { "page": "k_random_normal_variable", "title": "Instantiates a variable with values drawn from a normal distribution.", "topics": [ "k_random_normal_variable" ] }, { "page": "k_random_uniform", "title": "Returns a tensor with uniform distribution of values.", "topics": [ "k_random_uniform" ] }, { "page": "k_random_uniform_variable", "title": "Instantiates a variable with values drawn from a uniform distribution.", "topics": [ "k_random_uniform_variable" ] }, { "page": "k_relu", "title": "Rectified linear unit.", "topics": [ "k_relu" ] }, { "page": "k_repeat", "title": "Repeats a 2D tensor.", "topics": [ "k_repeat" ] }, { "page": "k_repeat_elements", "title": "Repeats the elements of a tensor along an axis.", "topics": [ "k_repeat_elements" ] }, { "page": "k_reset_uids", "title": "Reset graph identifiers.", "topics": [ "k_reset_uids" ] }, { "page": "k_reshape", "title": "Reshapes a tensor to the specified shape.", "topics": [ "k_reshape" ] }, { "page": "k_resize_images", "title": "Resizes the images contained in a 4D tensor.", "topics": [ "k_resize_images" ] }, { "page": "k_resize_volumes", "title": "Resizes the volume contained in a 5D tensor.", "topics": [ "k_resize_volumes" ] }, { "page": "k_reverse", "title": "Reverse a tensor along the specified axes.", "topics": [ "k_reverse" ] }, { "page": "k_rnn", "title": "Iterates over the time dimension of a tensor", "topics": [ "k_rnn" ] }, { "page": "k_round", "title": "Element-wise rounding to the closest integer.", "topics": [ "k_round" ] }, { "page": "k_separable_conv2d", "title": "2D convolution with separable filters.", "topics": [ "k_separable_conv2d" ] }, { "page": "k_set_learning_phase", "title": "Sets the learning phase to a fixed value.", "topics": [ "k_set_learning_phase" ] }, { "page": "k_set_value", "title": "Sets the value of a variable, from an R array.", "topics": [ "k_set_value" ] }, { "page": "k_shape", "title": "Returns the symbolic shape of a tensor or variable.", "topics": [ "k_shape" ] }, { "page": "k_sigmoid", "title": "Element-wise sigmoid.", "topics": [ "k_sigmoid" ] }, { "page": "k_sign", "title": "Element-wise sign.", "topics": [ "k_sign" ] }, { "page": "k_sin", "title": "Computes sin of x element-wise.", "topics": [ "k_sin" ] }, { "page": "k_softmax", "title": "Softmax of a tensor.", "topics": [ "k_softmax" ] }, { "page": "k_softplus", "title": "Softplus of a tensor.", "topics": [ "k_softplus" ] }, { "page": "k_softsign", "title": "Softsign of a tensor.", "topics": [ "k_softsign" ] }, { "page": "k_sparse_categorical_crossentropy", "title": "Categorical crossentropy with integer targets.", "topics": [ "k_sparse_categorical_crossentropy" ] }, { "page": "k_spatial_2d_padding", "title": "Pads the 2nd and 3rd dimensions of a 4D tensor.", "topics": [ "k_spatial_2d_padding" ] }, { "page": "k_spatial_3d_padding", "title": "Pads 5D tensor with zeros along the depth, height, width dimensions.", "topics": [ "k_spatial_3d_padding" ] }, { "page": "k_sqrt", "title": "Element-wise square root.", "topics": [ "k_sqrt" ] }, { "page": "k_square", "title": "Element-wise square.", "topics": [ "k_square" ] }, { "page": "k_squeeze", "title": "Removes a 1-dimension from the tensor at index 'axis'.", "topics": [ "k_squeeze" ] }, { "page": "k_stack", "title": "Stacks a list of rank 'R' tensors into a rank 'R+1' tensor.", "topics": [ "k_stack" ] }, { "page": "k_std", "title": "Standard deviation of a tensor, alongside the specified axis.", "topics": [ "k_std" ] }, { "page": "k_stop_gradient", "title": "Returns 'variables' but with zero gradient w.r.t. every other variable.", "topics": [ "k_stop_gradient" ] }, { "page": "k_sum", "title": "Sum of the values in a tensor, alongside the specified axis.", "topics": [ "k_sum" ] }, { "page": "k_switch", "title": "Switches between two operations depending on a scalar value.", "topics": [ "k_switch" ] }, { "page": "k_tanh", "title": "Element-wise tanh.", "topics": [ "k_tanh" ] }, { "page": "k_temporal_padding", "title": "Pads the middle dimension of a 3D tensor.", "topics": [ "k_temporal_padding" ] }, { "page": "k_tile", "title": "Creates a tensor by tiling 'x' by 'n'.", "topics": [ "k_tile" ] }, { "page": "k_to_dense", "title": "Converts a sparse tensor into a dense tensor and returns it.", "topics": [ "k_to_dense" ] }, { "page": "k_transpose", "title": "Transposes a tensor and returns it.", "topics": [ "k_transpose" ] }, { "page": "k_truncated_normal", "title": "Returns a tensor with truncated random normal distribution of values.", "topics": [ "k_truncated_normal" ] }, { "page": "k_unstack", "title": "Unstack rank 'R' tensor into a list of rank 'R-1' tensors.", "topics": [ "k_unstack" ] }, { "page": "k_update", "title": "Update the value of 'x' to 'new_x'.", "topics": [ "k_update" ] }, { "page": "k_update_add", "title": "Update the value of 'x' by adding 'increment'.", "topics": [ "k_update_add" ] }, { "page": "k_update_sub", "title": "Update the value of 'x' by subtracting 'decrement'.", "topics": [ "k_update_sub" ] }, { "page": "k_var", "title": "Variance of a tensor, alongside the specified axis.", "topics": [ "k_var" ] }, { "page": "k_variable", "title": "Instantiates a variable and returns it.", "topics": [ "k_variable" ] }, { "page": "k_zeros", "title": "Instantiates an all-zeros variable and returns it.", "topics": [ "k_zeros" ] }, { "page": "k_zeros_like", "title": "Instantiates an all-zeros variable of the same shape as another tensor.", "topics": [ "k_zeros_like" ] }, { "page": "keras", "title": "Main Keras module", "topics": [ "keras" ] }, { "page": "keras_array", "title": "Keras array object", "topics": [ "keras_array" ] }, { "page": "keras_model", "title": "Keras Model", "concept": [ "model functions" ], "topics": [ "keras_model" ] }, { "page": "keras_model_sequential", "title": "Keras Model composed of a linear stack of layers", "concept": [ "model functions" ], "topics": [ "keras_model_sequential" ] }, { "page": "layer_activation", "title": "Apply an activation function to an output.", "concept": [ "activation layers", "core layers" ], "topics": [ "layer_activation" ] }, { "page": "layer_activation_elu", "title": "Exponential Linear Unit.", "concept": [ "activation layers" ], "topics": [ "layer_activation_elu" ] }, { "page": "layer_activation_leaky_relu", "title": "Leaky version of a Rectified Linear Unit.", "concept": [ "activation layers" ], "topics": [ "layer_activation_leaky_relu" ] }, { "page": "layer_activation_parametric_relu", "title": "Parametric Rectified Linear Unit.", "concept": [ "activation layers" ], "topics": [ "layer_activation_parametric_relu" ] }, { "page": "layer_activation_relu", "title": "Rectified Linear Unit activation function", "concept": [ "activation layers" ], "topics": [ "layer_activation_relu" ] }, { "page": "layer_activation_selu", "title": "Scaled Exponential Linear Unit.", "concept": [ "activation layers" ], "topics": [ "layer_activation_selu" ] }, { "page": "layer_activation_softmax", "title": "Softmax activation function.", "concept": [ "activation layers" ], "topics": [ "layer_activation_softmax" ] }, { "page": "layer_activation_thresholded_relu", "title": "Thresholded Rectified Linear Unit.", "concept": [ "activation layers" ], "topics": [ "layer_activation_thresholded_relu" ] }, { "page": "layer_activity_regularization", "title": "Layer that applies an update to the cost function based input activity.", "concept": [ "core layers" ], "topics": [ "layer_activity_regularization" ] }, { "page": "layer_add", "title": "Layer that adds a list of inputs.", "concept": [ "merging_layers" ], "topics": [ "layer_add" ] }, { "page": "layer_additive_attention", "title": "Additive attention layer, a.k.a. Bahdanau-style attention", "topics": [ "layer_additive_attention" ] }, { "page": "layer_alpha_dropout", "title": "Applies Alpha Dropout to the input.", "concept": [ "noise layers" ], "topics": [ "layer_alpha_dropout" ] }, { "page": "layer_attention", "title": "Dot-product attention layer, a.k.a. Luong-style attention", "concept": [ "attention layers", "core layers" ], "topics": [ "layer_attention" ] }, { "page": "layer_average", "title": "Layer that averages a list of inputs.", "concept": [ "merge layers" ], "topics": [ "layer_average" ] }, { "page": "layer_average_pooling_1d", "title": "Average pooling for temporal data.", "concept": [ "pooling layers" ], "topics": [ "layer_average_pooling_1d" ] }, { "page": "layer_average_pooling_2d", "title": "Average pooling operation for spatial data.", "concept": [ "pooling layers" ], "topics": [ "layer_average_pooling_2d" ] }, { "page": "layer_average_pooling_3d", "title": "Average pooling operation for 3D data (spatial or spatio-temporal).", "concept": [ "pooling layers" ], "topics": [ "layer_average_pooling_3d" ] }, { "page": "layer_batch_normalization", "title": "Layer that normalizes its inputs", "topics": [ "layer_batch_normalization" ] }, { "page": "layer_category_encoding", "title": "A preprocessing layer which encodes integer features.", "concept": [ "categorical features preprocessing layers", "preprocessing layers" ], "topics": [ "layer_category_encoding" ] }, { "page": "layer_center_crop", "title": "Crop the central portion of the images to target height and width", "concept": [ "image preprocessing layers", "preprocessing layers" ], "topics": [ "layer_center_crop" ] }, { "page": "layer_concatenate", "title": "Layer that concatenates a list of inputs.", "concept": [ "merge layers" ], "topics": [ "layer_concatenate" ] }, { "page": "layer_conv_1d", "title": "1D convolution layer (e.g. temporal convolution).", "concept": [ "convolutional layers" ], "topics": [ "layer_conv_1d" ] }, { "page": "layer_conv_1d_transpose", "title": "Transposed 1D convolution layer (sometimes called Deconvolution).", "concept": [ "convolutional layers" ], "topics": [ "layer_conv_1d_transpose" ] }, { "page": "layer_conv_2d", "title": "2D convolution layer (e.g. spatial convolution over images).", "concept": [ "convolutional layers" ], "topics": [ "layer_conv_2d" ] }, { "page": "layer_conv_2d_transpose", "title": "Transposed 2D convolution layer (sometimes called Deconvolution).", "concept": [ "convolutional layers" ], "topics": [ "layer_conv_2d_transpose" ] }, { "page": "layer_conv_3d", "title": "3D convolution layer (e.g. spatial convolution over volumes).", "concept": [ "convolutional layers" ], "topics": [ "layer_conv_3d" ] }, { "page": "layer_conv_3d_transpose", "title": "Transposed 3D convolution layer (sometimes called Deconvolution).", "concept": [ "convolutional layers" ], "topics": [ "layer_conv_3d_transpose" ] }, { "page": "layer_conv_lstm_1d", "title": "1D Convolutional LSTM", "topics": [ "layer_conv_lstm_1d" ] }, { "page": "layer_conv_lstm_2d", "title": "Convolutional LSTM.", "concept": [ "convolutional layers" ], "topics": [ "layer_conv_lstm_2d" ] }, { "page": "layer_conv_lstm_3d", "title": "3D Convolutional LSTM", "topics": [ "layer_conv_lstm_3d" ] }, { "page": "layer_cropping_1d", "title": "Cropping layer for 1D input (e.g. temporal sequence).", "concept": [ "convolutional layers" ], "topics": [ "layer_cropping_1d" ] }, { "page": "layer_cropping_2d", "title": "Cropping layer for 2D input (e.g. picture).", "concept": [ "convolutional layers" ], "topics": [ "layer_cropping_2d" ] }, { "page": "layer_cropping_3d", "title": "Cropping layer for 3D data (e.g. spatial or spatio-temporal).", "concept": [ "convolutional layers" ], "topics": [ "layer_cropping_3d" ] }, { "page": "layer_dense", "title": "Add a densely-connected NN layer to an output", "concept": [ "core layers" ], "topics": [ "layer_dense" ] }, { "page": "layer_dense_features", "title": "Constructs a DenseFeatures.", "concept": [ "core layers" ], "topics": [ "layer_dense_features" ] }, { "page": "layer_depthwise_conv_1d", "title": "Depthwise 1D convolution", "concept": [ "convolutional layers" ], "topics": [ "layer_depthwise_conv_1d" ] }, { "page": "layer_depthwise_conv_2d", "title": "Depthwise separable 2D convolution.", "concept": [ "convolutional layers" ], "topics": [ "layer_depthwise_conv_2d" ] }, { "page": "layer_discretization", "title": "A preprocessing layer which buckets continuous features by ranges.", "concept": [ "numerical features preprocessing layers", "preprocessing layers" ], "topics": [ "layer_discretization" ] }, { "page": "layer_dot", "title": "Layer that computes a dot product between samples in two tensors.", "concept": [ "merge layers" ], "topics": [ "layer_dot" ] }, { "page": "layer_dropout", "title": "Applies Dropout to the input.", "concept": [ "core layers", "dropout layers" ], "topics": [ "layer_dropout" ] }, { "page": "layer_embedding", "title": "Turns positive integers (indexes) into dense vectors of fixed size", "topics": [ "layer_embedding" ] }, { "page": "layer_flatten", "title": "Flattens an input", "concept": [ "core layers" ], "topics": [ "layer_flatten" ] }, { "page": "layer_gaussian_dropout", "title": "Apply multiplicative 1-centered Gaussian noise.", "concept": [ "noise layers" ], "topics": [ "layer_gaussian_dropout" ] }, { "page": "layer_gaussian_noise", "title": "Apply additive zero-centered Gaussian noise.", "concept": [ "noise layers" ], "topics": [ "layer_gaussian_noise" ] }, { "page": "layer_global_average_pooling_1d", "title": "Global average pooling operation for temporal data.", "concept": [ "pooling layers" ], "topics": [ "layer_global_average_pooling_1d" ] }, { "page": "layer_global_average_pooling_2d", "title": "Global average pooling operation for spatial data.", "concept": [ "pooling layers" ], "topics": [ "layer_global_average_pooling_2d" ] }, { "page": "layer_global_average_pooling_3d", "title": "Global Average pooling operation for 3D data.", "concept": [ "pooling layers" ], "topics": [ "layer_global_average_pooling_3d" ] }, { "page": "layer_global_max_pooling_1d", "title": "Global max pooling operation for temporal data.", "concept": [ "pooling layers" ], "topics": [ "layer_global_max_pooling_1d" ] }, { "page": "layer_global_max_pooling_2d", "title": "Global max pooling operation for spatial data.", "concept": [ "pooling layers" ], "topics": [ "layer_global_max_pooling_2d" ] }, { "page": "layer_global_max_pooling_3d", "title": "Global Max pooling operation for 3D data.", "concept": [ "pooling layers" ], "topics": [ "layer_global_max_pooling_3d" ] }, { "page": "layer_gru", "title": "Gated Recurrent Unit - Cho et al.", "concept": [ "recurrent layers" ], "topics": [ "layer_gru" ] }, { "page": "layer_gru_cell", "title": "Cell class for the GRU layer", "concept": [ "RNN cell layers" ], "topics": [ "layer_gru_cell" ] }, { "page": "layer_hashing", "title": "A preprocessing layer which hashes and bins categorical features.", "concept": [ "categorical features preprocessing layers", "preprocessing layers" ], "topics": [ "layer_hashing" ] }, { "page": "layer_input", "title": "Input layer", "concept": [ "core layers" ], "topics": [ "layer_input" ] }, { "page": "layer_integer_lookup", "title": "A preprocessing layer which maps integer features to contiguous ranges.", "concept": [ "categorical features preprocessing layers", "preprocessing layers" ], "topics": [ "layer_integer_lookup" ] }, { "page": "layer_lambda", "title": "Wraps arbitrary expression as a layer", "concept": [ "core layers" ], "topics": [ "layer_lambda" ] }, { "page": "layer_layer_normalization", "title": "Layer normalization layer (Ba et al., 2016).", "topics": [ "layer_layer_normalization" ] }, { "page": "layer_locally_connected_1d", "title": "Locally-connected layer for 1D inputs.", "concept": [ "locally connected layers" ], "topics": [ "layer_locally_connected_1d" ] }, { "page": "layer_locally_connected_2d", "title": "Locally-connected layer for 2D inputs.", "concept": [ "locally connected layers" ], "topics": [ "layer_locally_connected_2d" ] }, { "page": "layer_lstm", "title": "Long Short-Term Memory unit - Hochreiter 1997.", "concept": [ "recurrent layers" ], "topics": [ "layer_lstm" ] }, { "page": "layer_lstm_cell", "title": "Cell class for the LSTM layer", "concept": [ "RNN cell layers" ], "topics": [ "layer_lstm_cell" ] }, { "page": "layer_masking", "title": "Masks a sequence by using a mask value to skip timesteps.", "concept": [ "core layers" ], "topics": [ "layer_masking" ] }, { "page": "layer_max_pooling_1d", "title": "Max pooling operation for temporal data.", "concept": [ "pooling layers" ], "topics": [ "layer_max_pooling_1d" ] }, { "page": "layer_max_pooling_2d", "title": "Max pooling operation for spatial data.", "concept": [ "pooling layers" ], "topics": [ "layer_max_pooling_2d" ] }, { "page": "layer_max_pooling_3d", "title": "Max pooling operation for 3D data (spatial or spatio-temporal).", "concept": [ "pooling layers" ], "topics": [ "layer_max_pooling_3d" ] }, { "page": "layer_maximum", "title": "Layer that computes the maximum (element-wise) a list of inputs.", "concept": [ "merge layers" ], "topics": [ "layer_maximum" ] }, { "page": "layer_minimum", "title": "Layer that computes the minimum (element-wise) a list of inputs.", "concept": [ "merge layers" ], "topics": [ "layer_minimum" ] }, { "page": "layer_multi_head_attention", "title": "MultiHeadAttention layer", "topics": [ "layer_multi_head_attention" ] }, { "page": "layer_multiply", "title": "Layer that multiplies (element-wise) a list of inputs.", "concept": [ "merge layers" ], "topics": [ "layer_multiply" ] }, { "page": "layer_normalization", "title": "A preprocessing layer which normalizes continuous features.", "concept": [ "numerical features preprocessing layers", "preprocessing layers" ], "topics": [ "layer_normalization" ] }, { "page": "layer_permute", "title": "Permute the dimensions of an input according to a given pattern", "concept": [ "core layers" ], "topics": [ "layer_permute" ] }, { "page": "layer_random_brightness", "title": "A preprocessing layer which randomly adjusts brightness during training", "concept": [ "image augmentation layers", "preprocessing layers" ], "topics": [ "layer_random_brightness" ] }, { "page": "layer_random_contrast", "title": "Adjust the contrast of an image or images by a random factor", "concept": [ "image augmentation layers", "preprocessing layers" ], "topics": [ "layer_random_contrast" ] }, { "page": "layer_random_crop", "title": "Randomly crop the images to target height and width", "concept": [ "image augmentation layers", "preprocessing layers" ], "topics": [ "layer_random_crop" ] }, { "page": "layer_random_flip", "title": "Randomly flip each image horizontally and vertically", "concept": [ "image augmentation layers", "preprocessing layers" ], "topics": [ "layer_random_flip" ] }, { "page": "layer_random_height", "title": "Randomly vary the height of a batch of images during training", "concept": [ "image augmentation layers", "preprocessing layers" ], "topics": [ "layer_random_height" ] }, { "page": "layer_random_rotation", "title": "Randomly rotate each image", "concept": [ "image augmentation layers", "preprocessing layers" ], "topics": [ "layer_random_rotation" ] }, { "page": "layer_random_translation", "title": "Randomly translate each image during training", "concept": [ "image augmentation layers", "preprocessing layers" ], "topics": [ "layer_random_translation" ] }, { "page": "layer_random_width", "title": "Randomly vary the width of a batch of images during training", "concept": [ "image augmentation layers", "preprocessing layers" ], "topics": [ "layer_random_width" ] }, { "page": "layer_random_zoom", "title": "A preprocessing layer which randomly zooms images during training.", "concept": [ "image augmentation layers", "preprocessing layers" ], "topics": [ "layer_random_zoom" ] }, { "page": "layer_repeat_vector", "title": "Repeats the input n times.", "concept": [ "core layers" ], "topics": [ "layer_repeat_vector" ] }, { "page": "layer_rescaling", "title": "Multiply inputs by 'scale' and adds 'offset'", "concept": [ "image preprocessing layers", "preprocessing layers" ], "topics": [ "layer_rescaling" ] }, { "page": "layer_reshape", "title": "Reshapes an output to a certain shape.", "concept": [ "core layers" ], "topics": [ "layer_reshape" ] }, { "page": "layer_resizing", "title": "Image resizing layer", "concept": [ "image preprocessing layers", "preprocessing layers" ], "topics": [ "layer_resizing" ] }, { "page": "layer_rnn", "title": "Base class for recurrent layers", "concept": [ "recurrent layers" ], "topics": [ "layer_rnn" ] }, { "page": "layer_separable_conv_1d", "title": "Depthwise separable 1D convolution.", "concept": [ "convolutional layers" ], "topics": [ "layer_separable_conv_1d" ] }, { "page": "layer_separable_conv_2d", "title": "Separable 2D convolution.", "concept": [ "convolutional layers" ], "topics": [ "layer_separable_conv_2d" ] }, { "page": "layer_simple_rnn", "title": "Fully-connected RNN where the output is to be fed back to input.", "concept": [ "recurrent layers" ], "topics": [ "layer_simple_rnn" ] }, { "page": "layer_simple_rnn_cell", "title": "Cell class for SimpleRNN", "concept": [ "RNN cell layers" ], "topics": [ "layer_simple_rnn_cell" ] }, { "page": "layer_spatial_dropout_1d", "title": "Spatial 1D version of Dropout.", "concept": [ "dropout layers" ], "topics": [ "layer_spatial_dropout_1d" ] }, { "page": "layer_spatial_dropout_2d", "title": "Spatial 2D version of Dropout.", "concept": [ "dropout layers" ], "topics": [ "layer_spatial_dropout_2d" ] }, { "page": "layer_spatial_dropout_3d", "title": "Spatial 3D version of Dropout.", "concept": [ "dropout layers" ], "topics": [ "layer_spatial_dropout_3d" ] }, { "page": "layer_stacked_rnn_cells", "title": "Wrapper allowing a stack of RNN cells to behave as a single cell", "concept": [ "RNN cell layers" ], "topics": [ "layer_stacked_rnn_cells" ] }, { "page": "layer_string_lookup", "title": "A preprocessing layer which maps string features to integer indices.", "concept": [ "categorical features preprocessing layers", "preprocessing layers" ], "topics": [ "layer_string_lookup" ] }, { "page": "layer_subtract", "title": "Layer that subtracts two inputs.", "concept": [ "merge layers" ], "topics": [ "layer_subtract" ] }, { "page": "layer_text_vectorization", "title": "A preprocessing layer which maps text features to integer sequences.", "concept": [ "preprocessing layers", "text preprocessing layers" ], "topics": [ "get_vocabulary", "layer_text_vectorization", "set_vocabulary" ] }, { "page": "layer_unit_normalization", "title": "Unit normalization layer", "topics": [ "layer_unit_normalization" ] }, { "page": "layer_upsampling_1d", "title": "Upsampling layer for 1D inputs.", "concept": [ "convolutional layers" ], "topics": [ "layer_upsampling_1d" ] }, { "page": "layer_upsampling_2d", "title": "Upsampling layer for 2D inputs.", "concept": [ "convolutional layers" ], "topics": [ "layer_upsampling_2d" ] }, { "page": "layer_upsampling_3d", "title": "Upsampling layer for 3D inputs.", "concept": [ "convolutional layers" ], "topics": [ "layer_upsampling_3d" ] }, { "page": "layer_zero_padding_1d", "title": "Zero-padding layer for 1D input (e.g. temporal sequence).", "concept": [ "convolutional layers" ], "topics": [ "layer_zero_padding_1d" ] }, { "page": "layer_zero_padding_2d", "title": "Zero-padding layer for 2D input (e.g. picture).", "concept": [ "convolutional layers" ], "topics": [ "layer_zero_padding_2d" ] }, { "page": "layer_zero_padding_3d", "title": "Zero-padding layer for 3D data (spatial or spatio-temporal).", "concept": [ "convolutional layers" ], "topics": [ "layer_zero_padding_3d" ] }, { "page": "learning_rate_schedule_cosine_decay", "title": "A LearningRateSchedule that uses a cosine decay schedule", "topics": [ "learning_rate_schedule_cosine_decay" ] }, { "page": "learning_rate_schedule_cosine_decay_restarts", "title": "A LearningRateSchedule that uses a cosine decay schedule with restarts", "topics": [ "learning_rate_schedule_cosine_decay_restarts" ] }, { "page": "learning_rate_schedule_exponential_decay", "title": "A LearningRateSchedule that uses an exponential decay schedule", "topics": [ "learning_rate_schedule_exponential_decay" ] }, { "page": "learning_rate_schedule_inverse_time_decay", "title": "A LearningRateSchedule that uses an inverse time decay schedule", "topics": [ "learning_rate_schedule_inverse_time_decay" ] }, { "page": "learning_rate_schedule_piecewise_constant_decay", "title": "A LearningRateSchedule that uses a piecewise constant decay schedule", "topics": [ "learning_rate_schedule_piecewise_constant_decay" ] }, { "page": "learning_rate_schedule_polynomial_decay", "title": "A LearningRateSchedule that uses a polynomial decay schedule", "topics": [ "learning_rate_schedule_polynomial_decay" ] }, { "page": "loss-functions", "title": "Loss functions", "topics": [ "\"BinaryCrossentropy\"", "\"binary_crossentropy\",", "loss-functions", "loss_binary_crossentropy", "loss_categorical_crossentropy", "loss_categorical_hinge", "loss_cosine_similarity", "loss_hinge", "loss_huber", "loss_kl_divergence", "loss_kullback_leibler_divergence", "loss_logcosh", "loss_mean_absolute_error", "loss_mean_absolute_percentage_error", "loss_mean_squared_error", "loss_mean_squared_logarithmic_error", "loss_poisson", "loss_sparse_categorical_crossentropy", "loss_squared_hinge" ] }, { "page": "make_sampling_table", "title": "Generates a word rank-based probabilistic sampling table.", "concept": [ "text preprocessing" ], "topics": [ "make_sampling_table" ] }, { "page": "Metric", "title": "Metric", "topics": [ "Metric" ] }, { "page": "metric_accuracy", "title": "Calculates how often predictions equal labels", "concept": [ "metrics" ], "topics": [ "metric_accuracy" ] }, { "page": "metric_auc", "title": "Approximates the AUC (Area under the curve) of the ROC or PR curves", "concept": [ "metrics" ], "topics": [ "metric_auc" ] }, { "page": "metric_binary_accuracy", "title": "Calculates how often predictions match binary labels", "concept": [ "metrics" ], "topics": [ "metric_binary_accuracy" ] }, { "page": "metric_binary_crossentropy", "title": "Computes the crossentropy metric between the labels and predictions", "concept": [ "metrics" ], "topics": [ "metric_binary_crossentropy" ] }, { "page": "metric_categorical_accuracy", "title": "Calculates how often predictions match one-hot labels", "concept": [ "metrics" ], "topics": [ "metric_categorical_accuracy" ] }, { "page": "metric_categorical_crossentropy", "title": "Computes the crossentropy metric between the labels and predictions", "concept": [ "metrics" ], "topics": [ "metric_categorical_crossentropy" ] }, { "page": "metric_categorical_hinge", "title": "Computes the categorical hinge metric between 'y_true' and 'y_pred'", "concept": [ "metrics" ], "topics": [ "metric_categorical_hinge" ] }, { "page": "metric_cosine_similarity", "title": "Computes the cosine similarity between the labels and predictions", "concept": [ "metrics" ], "topics": [ "metric_cosine_similarity" ] }, { "page": "metric_false_negatives", "title": "Calculates the number of false negatives", "concept": [ "metrics" ], "topics": [ "metric_false_negatives" ] }, { "page": "metric_false_positives", "title": "Calculates the number of false positives", "concept": [ "metrics" ], "topics": [ "metric_false_positives" ] }, { "page": "metric_hinge", "title": "Computes the hinge metric between 'y_true' and 'y_pred'", "concept": [ "metrics" ], "topics": [ "metric_hinge" ] }, { "page": "metric_kullback_leibler_divergence", "title": "Computes Kullback-Leibler divergence", "concept": [ "metrics" ], "topics": [ "metric_kullback_leibler_divergence" ] }, { "page": "metric_logcosh_error", "title": "Computes the logarithm of the hyperbolic cosine of the prediction error", "concept": [ "metrics" ], "topics": [ "metric_logcosh_error" ] }, { "page": "metric_mean", "title": "Computes the (weighted) mean of the given values", "concept": [ "metrics" ], "topics": [ "metric_mean" ] }, { "page": "metric_mean_absolute_error", "title": "Computes the mean absolute error between the labels and predictions", "concept": [ "metrics" ], "topics": [ "metric_mean_absolute_error" ] }, { "page": "metric_mean_absolute_percentage_error", "title": "Computes the mean absolute percentage error between 'y_true' and 'y_pred'", "concept": [ "metrics" ], "topics": [ "metric_mean_absolute_percentage_error" ] }, { "page": "metric_mean_iou", "title": "Computes the mean Intersection-Over-Union metric", "concept": [ "metrics" ], "topics": [ "metric_mean_iou" ] }, { "page": "metric_mean_relative_error", "title": "Computes the mean relative error by normalizing with the given values", "concept": [ "metrics" ], "topics": [ "metric_mean_relative_error" ] }, { "page": "metric_mean_squared_error", "title": "Computes the mean squared error between labels and predictions", "concept": [ "metrics" ], "topics": [ "metric_mean_squared_error" ] }, { "page": "metric_mean_squared_logarithmic_error", "title": "Computes the mean squared logarithmic error", "concept": [ "metrics" ], "topics": [ "metric_mean_squared_logarithmic_error" ] }, { "page": "metric_mean_tensor", "title": "Computes the element-wise (weighted) mean of the given tensors", "concept": [ "metrics" ], "topics": [ "metric_mean_tensor" ] }, { "page": "metric_mean_wrapper", "title": "Wraps a stateless metric function with the Mean metric", "concept": [ "metrics" ], "topics": [ "metric_mean_wrapper" ] }, { "page": "metric_poisson", "title": "Computes the Poisson metric between 'y_true' and 'y_pred'", "concept": [ "metrics" ], "topics": [ "metric_poisson" ] }, { "page": "metric_precision", "title": "Computes the precision of the predictions with respect to the labels", "concept": [ "metrics" ], "topics": [ "metric_precision" ] }, { "page": "metric_precision_at_recall", "title": "Computes best precision where recall is >= specified value", "concept": [ "metrics" ], "topics": [ "metric_precision_at_recall" ] }, { "page": "metric_recall", "title": "Computes the recall of the predictions with respect to the labels", "concept": [ "metrics" ], "topics": [ "metric_recall" ] }, { "page": "metric_recall_at_precision", "title": "Computes best recall where precision is >= specified value", "concept": [ "metrics" ], "topics": [ "metric_recall_at_precision" ] }, { "page": "metric_root_mean_squared_error", "title": "Computes root mean squared error metric between 'y_true' and 'y_pred'", "concept": [ "metrics" ], "topics": [ "metric_root_mean_squared_error" ] }, { "page": "metric_sensitivity_at_specificity", "title": "Computes best sensitivity where specificity is >= specified value", "concept": [ "metrics" ], "topics": [ "metric_sensitivity_at_specificity" ] }, { "page": "metric_sparse_categorical_accuracy", "title": "Calculates how often predictions match integer labels", "concept": [ "metrics" ], "topics": [ "metric_sparse_categorical_accuracy" ] }, { "page": "metric_sparse_categorical_crossentropy", "title": "Computes the crossentropy metric between the labels and predictions", "concept": [ "metrics" ], "topics": [ "metric_sparse_categorical_crossentropy" ] }, { "page": "metric_sparse_top_k_categorical_accuracy", "title": "Computes how often integer targets are in the top 'K' predictions", "concept": [ "metrics" ], "topics": [ "metric_sparse_top_k_categorical_accuracy" ] }, { "page": "metric_specificity_at_sensitivity", "title": "Computes best specificity where sensitivity is >= specified value", "concept": [ "metrics" ], "topics": [ "metric_specificity_at_sensitivity" ] }, { "page": "metric_squared_hinge", "title": "Computes the squared hinge metric", "concept": [ "metrics" ], "topics": [ "metric_squared_hinge" ] }, { "page": "metric_sum", "title": "Computes the (weighted) sum of the given values", "concept": [ "metrics" ], "topics": [ "metric_sum" ] }, { "page": "metric_top_k_categorical_accuracy", "title": "Computes how often targets are in the top 'K' predictions", "concept": [ "metrics" ], "topics": [ "metric_top_k_categorical_accuracy" ] }, { "page": "metric_true_negatives", "title": "Calculates the number of true negatives", "concept": [ "metrics" ], "topics": [ "metric_true_negatives" ] }, { "page": "metric_true_positives", "title": "Calculates the number of true positives", "concept": [ "metrics" ], "topics": [ "metric_true_positives" ] }, { "page": "model_from_saved_model", "title": "Load a Keras model from the Saved Model format", "concept": [ "saved_model" ], "topics": [ "model_from_saved_model" ] }, { "page": "model_to_json", "title": "Model configuration as JSON", "concept": [ "model persistence" ], "topics": [ "model_from_json", "model_to_json" ] }, { "page": "model_to_yaml", "title": "Model configuration as YAML", "concept": [ "model persistence" ], "topics": [ "model_from_yaml", "model_to_yaml" ] }, { "page": "new_learning_rate_schedule_class", "title": "Create a new learning rate schedule type", "topics": [ "new_learning_rate_schedule_class" ] }, { "page": "new-classes", "title": "Define new keras types", "topics": [ "mark_active", "new_callback_class", "new_layer_class", "new_loss_class", "new_metric_class", "new_model_class" ] }, { "page": "normalize", "title": "Normalize a matrix or nd-array", "topics": [ "normalize" ] }, { "page": "optimizer_adadelta", "title": "Optimizer that implements the Adadelta algorithm", "concept": [ "optimizers" ], "topics": [ "optimizer_adadelta" ] }, { "page": "optimizer_adagrad", "title": "Optimizer that implements the Adagrad algorithm", "concept": [ "optimizers" ], "topics": [ "optimizer_adagrad" ] }, { "page": "optimizer_adam", "title": "Optimizer that implements the Adam algorithm", "concept": [ "optimizers" ], "topics": [ "optimizer_adam" ] }, { "page": "optimizer_adamax", "title": "Optimizer that implements the Adamax algorithm", "concept": [ "optimizers" ], "topics": [ "optimizer_adamax" ] }, { "page": "optimizer_ftrl", "title": "Optimizer that implements the FTRL algorithm", "concept": [ "optimizers" ], "topics": [ "optimizer_ftrl" ] }, { "page": "optimizer_nadam", "title": "Optimizer that implements the Nadam algorithm", "concept": [ "optimizers" ], "topics": [ "optimizer_nadam" ] }, { "page": "optimizer_rmsprop", "title": "Optimizer that implements the RMSprop algorithm", "concept": [ "optimizers" ], "topics": [ "optimizer_rmsprop" ] }, { "page": "optimizer_sgd", "title": "Gradient descent (with momentum) optimizer", "concept": [ "optimizers" ], "topics": [ "optimizer_sgd" ] }, { "page": "pad_sequences", "title": "Pads sequences to the same length", "concept": [ "text preprocessing" ], "topics": [ "pad_sequences" ] }, { "page": "plot.keras_training_history", "title": "Plot training history", "topics": [ "plot.keras_training_history" ] }, { "page": "plot.keras.engine.training.Model", "title": "Plot a Keras model", "topics": [ "plot.keras.engine.training.Model" ] }, { "page": "pop_layer", "title": "Remove the last layer in a model", "concept": [ "model functions" ], "topics": [ "pop_layer" ] }, { "page": "predict_on_batch", "title": "Returns predictions for a single batch of samples.", "concept": [ "model functions" ], "topics": [ "predict_on_batch" ] }, { "page": "predict.keras.engine.training.Model", "title": "Generate predictions from a Keras model", "concept": [ "model functions" ], "topics": [ "predict.keras.engine.training.Model" ] }, { "page": "regularizer_l1", "title": "L1 and L2 regularization", "topics": [ "regularizer_l1", "regularizer_l1_l2", "regularizer_l2" ] }, { "page": "regularizer_orthogonal", "title": "A regularizer that encourages input vectors to be orthogonal to each other", "topics": [ "regularizer_orthogonal" ] }, { "page": "reset_states", "title": "Reset the states for a layer", "concept": [ "layer methods" ], "topics": [ "reset_states" ] }, { "page": "save_model_hdf5", "title": "Save/Load models using HDF5 files", "concept": [ "model persistence" ], "topics": [ "load_model_hdf5", "save_model_hdf5" ] }, { "page": "save_model_tf", "title": "Save/Load models using SavedModel format", "concept": [ "model persistence" ], "topics": [ "load_model_tf", "save_model_tf" ] }, { "page": "save_model_weights_hdf5", "title": "Save/Load model weights using HDF5 files", "concept": [ "model persistence" ], "topics": [ "load_model_weights_hdf5", "save_model_weights_hdf5" ] }, { "page": "save_model_weights_tf", "title": "Save model weights in the SavedModel format", "topics": [ "load_model_weights_tf", "save_model_weights_tf" ] }, { "page": "save_text_tokenizer", "title": "Save a text tokenizer to an external file", "concept": [ "text tokenization" ], "topics": [ "load_text_tokenizer", "save_text_tokenizer" ] }, { "page": "sequences_to_matrix", "title": "Convert a list of sequences into a matrix.", "concept": [ "text tokenization" ], "topics": [ "sequences_to_matrix" ] }, { "page": "sequential_model_input_layer", "title": "sequential_model_input_layer", "topics": [ "sequential_model_input_layer" ] }, { "page": "serialize_model", "title": "Serialize a model to an R object", "concept": [ "model persistence" ], "topics": [ "serialize_model", "unserialize_model" ] }, { "page": "skipgrams", "title": "Generates skipgram word pairs.", "concept": [ "text preprocessing" ], "topics": [ "skipgrams" ] }, { "page": "summary.keras.engine.training.Model", "title": "Print a summary of a Keras model", "concept": [ "model functions" ], "topics": [ "format.keras.engine.training.Model", "print.keras.engine.training.Model", "summary.keras.engine.training.Model" ] }, { "page": "text_dataset_from_directory", "title": "Generate a 'tf.data.Dataset' from text files in a directory", "topics": [ "text_dataset_from_directory" ] }, { "page": "text_hashing_trick", "title": "Converts a text to a sequence of indexes in a fixed-size hashing space.", "concept": [ "text preprocessing" ], "topics": [ "text_hashing_trick" ] }, { "page": "text_one_hot", "title": "One-hot encode a text into a list of word indexes in a vocabulary of size n.", "concept": [ "text preprocessing" ], "topics": [ "text_one_hot" ] }, { "page": "text_to_word_sequence", "title": "Convert text to a sequence of words (or tokens).", "concept": [ "text preprocessing" ], "topics": [ "text_to_word_sequence" ] }, { "page": "text_tokenizer", "title": "Text tokenization utility", "concept": [ "text tokenization" ], "topics": [ "text_tokenizer" ] }, { "page": "texts_to_matrix", "title": "Convert a list of texts to a matrix.", "concept": [ "text tokenization" ], "topics": [ "texts_to_matrix" ] }, { "page": "texts_to_sequences", "title": "Transform each text in texts in a sequence of integers.", "concept": [ "text tokenization" ], "topics": [ "texts_to_sequences" ] }, { "page": "texts_to_sequences_generator", "title": "Transforms each text in texts in a sequence of integers.", "concept": [ "text tokenization" ], "topics": [ "texts_to_sequences_generator" ] }, { "page": "time_distributed", "title": "This layer wrapper allows to apply a layer to every temporal slice of an input", "concept": [ "layer wrappers" ], "topics": [ "time_distributed" ] }, { "page": "timeseries_dataset_from_array", "title": "Creates a dataset of sliding windows over a timeseries provided as array", "topics": [ "timeseries_dataset_from_array" ] }, { "page": "timeseries_generator", "title": "Utility function for generating batches of temporal data.", "topics": [ "timeseries_generator" ] }, { "page": "to_categorical", "title": "Converts a class vector (integers) to binary class matrix.", "topics": [ "to_categorical" ] }, { "page": "train_on_batch", "title": "Single gradient update or model evaluation over one batch of samples.", "concept": [ "model functions" ], "topics": [ "test_on_batch", "train_on_batch" ] }, { "page": "use_implementation", "title": "Select a Keras implementation and backend", "topics": [ "use_backend", "use_implementation" ] }, { "page": "with_custom_object_scope", "title": "Provide a scope with mappings of names to custom objects", "topics": [ "with_custom_object_scope" ] }, { "page": "zip_lists", "title": "zip lists", "topics": [ "zip_lists" ] } ], "_rundeps": [ "backports", "base64enc", "cli", "config", "generics", "glue", "here", "jsonlite", "lattice", "lifecycle", "magrittr", "Matrix", "png", "processx", "ps", "R6", "rappdirs", "Rcpp", "RcppTOML", "reticulate", "rlang", "rprojroot", "rstudioapi", "tensorflow", "tfautograph", "tfruns", "tidyselect", "vctrs", "whisker", "withr", "yaml", "zeallot" ], "_vignettes": [ { "source": "faq.Rmd", "filename": "faq.html", "title": "Frequently Asked Questions", "engine": "knitr::rmarkdown", "headings": [ "How should I cite Keras?", "How can I run Keras on a GPU?", "TensorFlow", "Theano", "CNTK", "How can I run a Keras model on multiple GPUs?", "Data parallelism", "Device parallelism", "What does \"sample\", \"batch\", \"epoch\" mean?", "Why are Keras objects modified in place?", "How can I save a Keras model?", "Saving/loading whole models (architecture + weights + optimizer state)", "Saving/loading only a model's architecture", "Saving/loading only a model's weights", "Why is the training loss much higher than the testing loss?", "How can I obtain the output of an intermediate layer?", "How can I use Keras with datasets that don't fit in memory?", "Generator Functions", "External Data Generators", "Image Generators", "Batch Functions", "How can I interrupt training when the validation loss isn't decreasing anymore?", "How is the validation split computed?", "Is the data shuffled during training?", "How can I record the training / validation loss / accuracy at each epoch?", "How can I \"freeze\" Keras layers?", "How can I use stateful RNNs?", "How can I remove a layer from a Sequential model?", "How can I use pre-trained models in Keras?", "How can I use other Keras backends?", "How can I use the PlaidML backend?", "How can I use Keras in another R package?", "Testing on CRAN", "Keras Module", "Custom Layers", "How can I obtain reproducible results using Keras during development?", "Where is the Keras configuration filed stored?" ], "created": "2017-07-30 04:16:19", "modified": "2022-12-20 14:40:02", "commits": 14 }, { "source": "index.Rmd", "filename": "index.html", "title": "Getting Started with Keras", "engine": "knitr::rmarkdown", "headings": [ "Overview", "Installation", "MNIST Example", "Preparing the Data", "Defining the Model", "Training and Evaluation", "Deep Learning with R Book", "Why this name, Keras?" ], "created": "2020-05-19 19:30:02", "modified": "2026-02-14 06:10:03", "commits": 5 }, { "source": "guide_keras.Rmd", "filename": "guide_keras.html", "title": "Guide to Keras Basics", "engine": "knitr::rmarkdown", "headings": [ "Import keras", "Build a simple model", "Sequential model", "Configure the layers", "Train and evaluate", "Set up training", "Input data", "Evaluate and predict", "Build advanced models", "Functional API", "Custom layers", "Custom models", "Callbacks", "Save and restore", "Weights only", "Configuration only", "Entire model" ], "created": "2018-08-24 10:32:13", "modified": "2022-12-20 14:40:02", "commits": 4 }, { "source": "functional_api.Rmd", "filename": "functional_api.html", "title": "Guide to the Functional API", "engine": "knitr::rmarkdown", "headings": [ "First example: a densely-connected network", "All models are callable, just like layers", "Multi-input and multi-output models", "Shared layers", "The concept of layer \"node\"", "More examples", "Inception module", "Residual connection on a convolution layer", "Shared vision model", "Visual question answering model", "Video question answering model" ], "created": "2017-07-30 04:16:19", "modified": "2026-02-14 06:10:03", "commits": 7 }, { "source": "sequential_model.Rmd", "filename": "sequential_model.html", "title": "Guide to the Sequential Model", "engine": "knitr::rmarkdown", "headings": [ "Defining a Model", "Input Shapes", "Compilation", "Training", "Examples", "Multilayer Perceptron (MLP) for multi-class softmax classification", "MLP for binary classification", "VGG-like convnet", "Sequence classification with LSTM", "Sequence classification with 1D convolutions:", "Stacked LSTM for sequence classification", "Same stacked LSTM model, rendered \"stateful\"" ], "created": "2017-07-30 04:16:19", "modified": "2026-02-14 06:10:03", "commits": 7 }, { "source": "saving_serializing.Rmd", "filename": "saving_serializing.html", "title": "Saving and serializing models", "engine": "knitr::rmarkdown", "headings": [ "Overview", "Setup", "Saving Sequential Models or Functional models", "Whole-model saving", "Export to SavedModel", "Architecture-only saving", "Weights-only saving", "Weights-only saving in SavedModel format", "Saving Subclassed Models" ], "created": "2019-10-08 17:10:02", "modified": "2026-02-14 06:10:03", "commits": 4 }, { "source": "training_callbacks.Rmd", "filename": "training_callbacks.html", "title": "Training Callbacks", "engine": "knitr::rmarkdown", "headings": [ "Overview", "Built in Callbacks", "Custom Callbacks", "Fields", "Methods" ], "created": "2017-07-30 04:16:19", "modified": "2020-05-19 19:30:02", "commits": 3 }, { "source": "training_visualization.Rmd", "filename": "training_visualization.html", "title": "Training Visualization", "engine": "knitr::rmarkdown", "headings": [ "Overview", "Plotting History", "RStudio IDE", "TensorBoard", "Recording Data", "Viewing Data", "Comparing Runs", "Customization", "Metrics", "Options" ], "created": "2017-08-30 10:46:05", "modified": "2022-12-20 14:40:02", "commits": 5 }, { "source": "applications.Rmd", "filename": "applications.html", "title": "Using Pre-Trained Models", "engine": "knitr::rmarkdown", "headings": [ "Applications", "Usage Examples", "Classify ImageNet classes with ResNet50", "Extract features with VGG16", "Extract features from an arbitrary intermediate layer with VGG19", "Fine-tune InceptionV3 on a new set of classes", "Build InceptionV3 over a custom input tensor", "Additional examples" ], "created": "2017-07-30 04:16:19", "modified": "2022-12-20 14:40:02", "commits": 8 }, { "source": "custom_layers.Rmd", "filename": "custom_layers.html", "title": "Writing Custom Keras Layers", "engine": "knitr::rmarkdown", "headings": [ "The Layer function", "Best practice: deferring weight creation until the shape of the inputs is known", "Layers are recursively composable", "Layers recursively collect losses created during the forward pass", "You can optionally enable serialization on your layers", "Privileged training argument in the call method" ], "created": "2017-07-30 04:16:19", "modified": "2022-12-20 14:40:02", "commits": 7 }, { "source": "custom_models.Rmd", "filename": "custom_models.html", "title": "Writing Custom Keras Models", "engine": "knitr::rmarkdown", "headings": [ "Overview", "Creating a Custom Model", "Using a Custom Model" ], "created": "2018-08-24 10:32:13", "modified": "2020-05-19 19:30:02", "commits": 2 } ], "_score": 10.90405479114633, "_indexed": true, "_nocasepkg": "keras", "_universes": [ "t-kalinowski", "rstudio" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "2.16.1", "date": "2026-05-15T09:35:39.000Z", "distro": "noble", "commit": "458707c2f1cd154ae8e998ca2789cb73531753b4", "fileid": "0ddd1bc3fa720082a06d674811a077fa6a8019273145a751cb6f1fc2762928b8", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/t-kalinowski/actions/runs/25910619203" }, { "r": "4.6.0", "os": "linux", "version": "2.16.1", "date": "2026-05-15T09:35:42.000Z", "distro": "noble", "commit": "458707c2f1cd154ae8e998ca2789cb73531753b4", "fileid": "db9b5386d5eaa3ec2dfbcd2e7472ee0f0bb817df00c88fe7032bc23c108cfd2d", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/t-kalinowski/actions/runs/25910619203" }, { "r": "4.5.3", "os": "mac", "version": "2.16.1", "date": "2026-05-15T09:35:08.000Z", "commit": "458707c2f1cd154ae8e998ca2789cb73531753b4", "fileid": "851e767952df846a11b15a59a1af08f05e3ce79e25c41dfbf5a3badc0deb18b5", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/t-kalinowski/actions/runs/25910619203" }, { "r": "4.6.0", "os": "mac", "version": "2.16.1", "date": "2026-05-15T09:34:51.000Z", "commit": "458707c2f1cd154ae8e998ca2789cb73531753b4", "fileid": "b4ffb88e5bae3c9d4a314f6c5d6b3ad48695cd8d97d8431bae0e687df8930ce4", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/t-kalinowski/actions/runs/25910619203" }, { "r": "4.7.0", "os": "win", "version": "2.16.1", "date": "2026-05-15T09:35:05.000Z", "commit": "458707c2f1cd154ae8e998ca2789cb73531753b4", "fileid": "eba107f3d9bad3adf9dffbc065922ada5e9cc7024dbc49105a439a136183525f", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/t-kalinowski/actions/runs/25910619203" }, { "r": "4.5.3", "os": "win", "version": "2.16.1", "date": "2026-05-15T09:34:42.000Z", "commit": "458707c2f1cd154ae8e998ca2789cb73531753b4", "fileid": "34d2635aca0b083e75bcc7b14328a0f45f446ec1941ca930b7f6855fdd2d0a5f", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/t-kalinowski/actions/runs/25910619203" }, { "r": "4.6.0", "os": "win", "version": "2.16.1", "date": "2026-05-15T09:34:43.000Z", "commit": "458707c2f1cd154ae8e998ca2789cb73531753b4", "fileid": "6e4eb0e5b2d7c4da5c0a5c537c0c09dbb0b1201484f305095acba3e2f8d92b41", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/t-kalinowski/actions/runs/25910619203" }, { "r": "4.6.0", "os": "wasm", "version": "2.16.1", "date": "2026-06-02T19:24:38.000Z", "commit": "458707c2f1cd154ae8e998ca2789cb73531753b4", "fileid": "d5d2c81c58817431d36f7ee31b892e5b9c3fe91928723ba72df0b2cd90ea31b6", "status": "success", "buildurl": "https://github.com/r-universe/t-kalinowski/actions/runs/25910619203" } ] }