Skip to content

AllenNLP v2.10.1

layer_norm

Initializing search

AllenNLP v2.10.1

Home
Repository
Versions
Versions
- Latest
- Stable
- Commit
API
API
- commands
  commands
- common
  common
  - cached_transformers
  - checks
  - file_utils
  - from_params
  - lazy
  - logging
  - meta
  - model_card
  - params
  - plugins
  - push_to_hf
  - registrable
  - sequences
  - task_card
  - testing
    testing
    
    checklist_test
    
    confidence_check_test
    
    distributed_test
    
    interpret_test
    
    model_test_case
    
    test_case
  - tqdm
  - util
- confidence_checks
  confidence_checks
  - normalization_bias_verification
  - task_checklists
    task_checklists
    
    question_answering_suite
    
    sentiment_analysis_suite
    
    task_suite
    
    textual_entailment_suite
    
    utils
  - verification_base
- data
  data
  - batch
  - data_loaders
    data_loaders
    
    data_collator
    
    data_loader
    
    multiprocess_data_loader
    
    multitask_data_loader
    
    multitask_epoch_sampler
    
    multitask_scheduler
    
    simple_data_loader
  - dataset_readers
    dataset_readers
    
    babi
    
    conll2003
    
    dataset_reader
    
    dataset_utils
    dataset_utils
    
    span_utils
    
    interleaving_dataset_reader
    
    multitask
    
    sequence_tagging
    
    sharded_dataset_reader
    
    text_classification_json
  - fields
    fields
    
    adjacency_field
    
    array_field
    
    field
    
    flag_field
    
    index_field
    
    label_field
    
    list_field
    
    metadata_field
    
    multilabel_field
    
    namespace_swapping_field
    
    sequence_field
    
    sequence_label_field
    
    span_field
    
    tensor_field
    
    text_field
    
    transformer_text_field
  - image_loader
  - instance
  - samplers
    samplers
    
    batch_sampler
    
    bucket_batch_sampler
    
    max_tokens_batch_sampler
  - token_indexers
    token_indexers
    
    elmo_indexer
    
    pretrained_transformer_indexer
    
    pretrained_transformer_mismatched_indexer
    
    single_id_token_indexer
    
    spacy_indexer
    
    token_characters_indexer
    
    token_indexer
  - tokenizers
    tokenizers
    
    character_tokenizer
    
    letters_digits_tokenizer
    
    pretrained_transformer_tokenizer
    
    sentence_splitter
    
    spacy_tokenizer
    
    token_class
    
    tokenizer
    
    whitespace_tokenizer
  - vocabulary
- evaluation
  evaluation
  - evaluator
  - serializers
    serializers
    
    serializers
- fairness
  fairness
- interpret
  interpret
  - attackers
    attackers
    
    attacker
    
    hotflip
    
    input_reduction
    
    utils
  - influence_interpreters
    influence_interpreters
    
    influence_interpreter
    
    simple_influence
  - saliency_interpreters
    saliency_interpreters
    
    integrated_gradient
    
    saliency_interpreter
    
    simple_gradient
    
    smooth_gradient
- models
  models
  - archival
  - basic_classifier
  - heads
    heads
    
    classifier_head
    
    head
  - model
  - multitask
  - simple_tagger
- modules
  modules
  - attention
    attention
    
    additive_attention
    
    attention
    
    bilinear_attention
    
    cosine_attention
    
    dot_product_attention
    
    linear_attention
    
    scaled_dot_product_attention
  - augmented_lstm
  - backbones
    backbones
    
    backbone
    
    pretrained_transformer_backbone
    
    vilbert_backbone
  - bimpm_matching
  - conditional_random_field
    conditional_random_field
    
    conditional_random_field
    
    conditional_random_field_wemission
    
    conditional_random_field_wlannoy
    
    conditional_random_field_wtrans
  - elmo
  - elmo_lstm
  - encoder_base
  - feedforward
  - gated_sum
  - highway
  - input_variational_dropout
  - layer_norm
  - lstm_cell_with_projection
  - masked_layer_norm
  - matrix_attention
    matrix_attention
    
    bilinear_matrix_attention
    
    cosine_matrix_attention
    
    dot_product_matrix_attention
    
    linear_matrix_attention
    
    matrix_attention
    
    scaled_dot_product_matrix_attention
  - maxout
  - residual_with_layer_dropout
  - sampled_softmax_loss
  - scalar_mix
  - seq2seq_encoders
    seq2seq_encoders
    
    compose_encoder
    
    feedforward_encoder
    
    gated_cnn_encoder
    
    pass_through_encoder
    
    pytorch_seq2seq_wrapper
    
    pytorch_transformer_wrapper
    
    seq2seq_encoder
  - seq2vec_encoders
    seq2vec_encoders
    
    bert_pooler
    
    boe_encoder
    
    cls_pooler
    
    cnn_encoder
    
    cnn_highway_encoder
    
    pytorch_seq2vec_wrapper
    
    seq2vec_encoder
  - softmax_loss
  - span_extractors
    span_extractors
    
    bidirectional_endpoint_span_extractor
    
    endpoint_span_extractor
    
    max_pooling_span_extractor
    
    self_attentive_span_extractor
    
    span_extractor
    
    span_extractor_with_span_width_embedding
  - stacked_alternating_lstm
  - stacked_bidirectional_lstm
  - text_field_embedders
    text_field_embedders
    
    basic_text_field_embedder
    
    text_field_embedder
  - time_distributed
  - token_embedders
    token_embedders
    
    bag_of_word_counts_token_embedder
    
    elmo_token_embedder
    
    embedding
    
    empty_embedder
    
    pass_through_token_embedder
    
    pretrained_transformer_embedder
    
    pretrained_transformer_mismatched_embedder
    
    token_characters_encoder
    
    token_embedder
  - transformer
    transformer
    
    activation_layer
    
    attention_module
    
    bimodal_attention
    
    bimodal_connection_layer
    
    bimodal_encoder
    
    layer_norm layer_norm
    Table of contents
    
    LayerNorm
    
    output_layer
    
    positional_encoding
    
    t5
    
    transformer_embeddings
    
    transformer_layer
    
    transformer_module
    
    transformer_pooler
    
    transformer_stack
    
    util
  - util
  - vision
    vision
    
    grid_embedder
    
    image2image
    
    region_detector
- nn
  nn
  - activations
  - beam_search
  - checkpoint
    checkpoint
    
    checkpoint_wrapper
    
    fairscale_checkpoint_wrapper
  - chu_liu_edmonds
  - initializers
  - module
  - parallel
    parallel
    
    ddp_accelerator
    
    fairscale_fsdp_accelerator
    
    sharded_module_mixin
  - regularizers
    regularizers
    
    regularizer
    
    regularizer_applicator
    
    regularizers
  - util
- predictors
  predictors
- tools
  tools
- training
  training
  - callbacks
    callbacks
    
    backward
    
    callback
    
    confidence_checks
    
    console_logger
    
    log_writer
    
    should_validate
    
    tensorboard
    
    track_epoch
    
    wandb
  - checkpointer
  - gradient_descent_trainer
  - learning_rate_schedulers
    learning_rate_schedulers
    
    combined
    
    cosine
    
    learning_rate_scheduler
    
    linear_with_warmup
    
    noam
    
    polynomial_decay
    
    pytorch_lr_schedulers
    
    slanted_triangular
  - metric_tracker
  - metrics
    metrics
    
    attachment_scores
    
    auc
    
    average
    
    bleu
    
    boolean_accuracy
    
    categorical_accuracy
    
    covariance
    
    entropy
    
    evalb_bracketing_scorer
    
    f1_measure
    
    fbeta_measure
    
    fbeta_multi_label_measure
    
    fbeta_verbose_measure
    
    mean_absolute_error
    
    metric
    
    pearson_correlation
    
    perplexity
    
    rouge
    
    sequence_accuracy
    
    span_based_f1_measure
    
    spearman_correlation
    
    unigram_recall
  - momentum_schedulers
    momentum_schedulers
    
    inverted_triangular
    
    momentum_scheduler
  - moving_average
  - no_op_trainer
  - optimizers
  - scheduler
  - trainer
  - util
Contributing
CHANGELOG
License

Table of contents

LayerNorm

layer_norm

allennlp.modules.transformer.layer_norm

LayerNorm¶

class LayerNorm(torch.nn.LayerNorm,  TransformerModule)

Previous bimodal_encoder

Next output_layer

Made with Material for MkDocs