Logo
latest
  • Overview
    • Key Features
    • Library API Example
    • Installation
    • Getting Started
    • Reference
    • License
  • Examples
    • Examples by Models/Algorithms
      • RNN / Seq2seq
      • Transformer (Self-attention)
      • Variational Autoencoder (VAE)
      • GANs / Discriminator-supervision
      • Reinforcement Learning
      • Memory Network
      • Classifier / Sequence Prediction
      • Reward Augmented Maximum Likelihood (RAML)
    • Examples by Tasks
      • Language Modeling
      • Machine Translation
      • Dialog
      • Text Summarization
      • Text Style Transfer
      • Classification
      • Sequence Tagging
      • Games
    • MISC
      • Distributed training
  • HParams
  • Data
    • Tokenizers
      • TokenizerBase
      • BERTTokenizer
      • XLNetTokenizer
    • Vocabulary
      • SpecialTokens
      • Vocab
    • Embedding
      • Embedding
      • load_word2vec
      • load_glove
    • Data
      • DataBase
      • MonoTextData
      • PairedTextData
      • ScalarData
      • TFRecordData
      • MultiAlignedData
      • TextDataBase
    • Data Iterators
      • DataIteratorBase
      • DataIterator
      • TrainTestDataIterator
      • FeedableDataIterator
      • TrainTestFeedableDataIterator
    • Data Utils
      • random_shard_dataset
      • maybe_tuple
      • make_partial
      • maybe_download
      • read_words
      • make_vocab
      • count_file_lines
      • make_chained_transformation
      • make_combined_transformation
  • Core
    • Cells
      • default_rnn_cell_hparams
      • get_rnn_cell
      • get_rnn_cell_trainable_variables
    • Layers
      • get_layer
      • MaxReducePooling1D
      • AverageReducePooling1D
      • get_pooling_layer_hparams
      • MergeLayer
      • SequentialLayer
      • default_regularizer_hparams
      • get_regularizer
      • get_initializer
      • get_activation_fn
      • get_constraint_fn
      • default_conv1d_kwargs
      • default_dense_kwargs
    • Optimization
      • default_optimization_hparams
      • get_train_op
      • get_optimizer_fn
      • get_optimizer
      • get_learning_rate_decay_fn
      • get_gradient_clip_fn
    • Exploration
      • EpsilonLinearDecayExploration
      • ExplorationBase
    • Replay Memories
      • DequeReplayMemory
      • ReplayMemoryBase
  • Modules
    • ModuleBase
    • Embedders
      • WordEmbedder
      • PositionEmbedder
      • SinusoidsPositionEmbedder
      • EmbedderBase
    • Encoders
      • UnidirectionalRNNEncoder
      • BidirectionalRNNEncoder
      • HierarchicalRNNEncoder
      • MultiheadAttentionEncoder
      • TransformerEncoder
      • BERTEncoder
      • Conv1DEncoder
      • EncoderBase
      • RNNEncoderBase
      • XLNetEncoder
      • default_transformer_poswise_net_hparams
    • Decoders
      • RNNDecoderBase
      • BasicRNNDecoder
      • BasicRNNDecoderOutput
      • AttentionRNNDecoder
      • AttentionRNNDecoderOutput
      • GPT2Decoder
      • beam_search_decode
      • TransformerDecoder
      • TransformerDecoderOutput
      • Helper
      • GreedyEmbeddingHelper
      • SampleEmbeddingHelper
      • TopKSampleEmbeddingHelper
      • SoftmaxEmbeddingHelper
      • GumbelSoftmaxEmbeddingHelper
      • TrainingHelper
      • ScheduledEmbeddingTrainingHelper
      • ScheduledOutputTrainingHelper
      • InferenceHelper
      • CustomHelper
      • get_helper
    • Classifiers
      • Conv1DClassifier
      • UnidirectionalRNNClassifier
      • BertClassifier
      • XLNetClassifier
    • Regressors
      • XLNetRegressor
    • Pre-trained
      • PretrainedMixin
      • PretrainedBERTMixin
      • PretrainedXLNetMixin
    • Connectors
      • ConnectorBase
      • ConstantConnector
      • ForwardConnector
      • MLPTransformConnector
      • ReparameterizedStochasticConnector
      • StochasticConnector
    • Networks
      • FeedForwardNetworkBase
      • FeedForwardNetwork
      • Conv1DNetwork
    • Memory
      • MemNetBase
      • MemNetRNNLike
      • default_memnet_embed_fn_hparams
    • Policy
      • PolicyNetBase
      • CategoricalPolicyNet
    • Q-Nets
      • QNetBase
      • CategoricalPolicyNet
  • Agents
    • Sequence Agents
      • SeqPGAgent
    • Episodic Agents
      • EpisodicAgentBase
      • PGAgent
      • DQNAgent
      • ActorCriticAgent
    • Agent Utils
      • Space
      • EnvConfig
      • convert_gym_space
      • get_gym_env_config
  • Loss Functions
    • MLE Loss
      • sequence_softmax_cross_entropy
      • sequence_sparse_softmax_cross_entropy
      • sequence_sigmoid_cross_entropy
      • binary_sigmoid_cross_entropy
      • binary_sigmoid_cross_entropy_with_clas
    • Policy Gradient Loss
      • pg_loss_with_logits
      • pg_loss_with_log_probs
    • Reward
      • discount_reward
    • Adversarial Loss
      • binary_adversarial_losses
    • Entropy
      • entropy_with_logits
      • sequence_entropy_with_logits
    • Loss Utils
      • mask_and_reduce
      • reduce_batch_time
      • reduce_dimensions
  • Evaluations
    • BLEU
      • sentence_bleu
      • corpus_bleu
      • sentence_bleu_moses
      • corpus_bleu_moses
    • Accuracy
      • accuracy
      • binary_clas_accurac
  • Models
    • ModelBase
    • Seq2seqBase
    • BasicSeq2seq
  • Executor
  • Context
    • Global Mode
      • global_mode
      • global_mode_train
      • global_mode_eval
      • global_mode_predict
      • valid_modes
  • Utils
    • Frequent Use
      • AverageRecorder
      • collect_trainable_variables
      • compat_as_text
      • map_ids_to_strs
      • write_paired_text
      • straight_through
    • Variables
      • collect_trainable_variables
      • get_unique_named_variable_scope
      • add_variable
    • IO
      • write_paired_text
      • load_config
      • maybe_create_dir
      • get_files
    • DType
      • compat_as_text
      • get_tf_dtype
      • is_callable
      • is_str
      • is_placeholder
      • maybe_hparams_to_dict
    • Shape
      • mask_sequences
      • transpose_batch_time
      • get_batch_size
      • get_rank
      • shape_list
      • pad_and_concat
      • reduce_with_weights
      • flatten
      • varlength_concat
      • varlength_concat_py
      • varlength_roll
    • Dictionary
      • dict_patch
      • dict_lookup
      • dict_fetch
      • dict_pop
      • flatten_dict
    • String
      • map_ids_to_strs
      • strip_token
      • strip_eos
      • strip_special_tokens
      • str_join
      • default_str
      • uniquify_str
    • Meta
      • check_or_get_class
      • get_class
      • check_or_get_instance
      • get_instance
      • check_or_get_instance_with_redundant_kwargs
      • get_instance_with_redundant_kwargs
      • get_function
      • call_function_with_redundant_kwargs
      • get_args
      • get_default_arg_values
      • get_instance_kwargs
    • Mode
      • switch_dropout
      • maybe_global_mode
      • is_train_mode
      • is_eval_mode
      • is_predict_mode
      • is_train_mode_py
      • is_eval_mode_py
      • is_predict_mode_py
    • Misc
      • ceildiv
      • straight_through
      • truncate_seq_pair
    • AverageRecorder
Texar
  • Docs »
  • Welcome to Texar’s documentation!
  • Edit on GitHub

Welcome to Texar’s documentation!¶

Texar is a modularized, versatile, and extensible toolkit for text generation tasks and beyond.

  • Overview
  • Examples
    • Examples by Models/Algorithms
    • Examples by Tasks
    • MISC

API¶

  • HParams
  • Data
    • Tokenizers
    • Vocabulary
    • Embedding
    • Data
    • Data Iterators
    • Data Utils
  • Core
    • Cells
    • Layers
    • Optimization
    • Exploration
    • Replay Memories
  • Modules
    • ModuleBase
    • Embedders
    • Encoders
    • Decoders
    • Classifiers
    • Regressors
    • Pre-trained
    • Connectors
    • Networks
    • Memory
    • Policy
    • Q-Nets
  • Agents
    • Sequence Agents
    • Episodic Agents
    • Agent Utils
  • Loss Functions
    • MLE Loss
    • Policy Gradient Loss
    • Reward
    • Adversarial Loss
    • Entropy
    • Loss Utils
  • Evaluations
    • BLEU
    • Accuracy
  • Models
    • ModelBase
    • Seq2seqBase
    • BasicSeq2seq
  • Executor
  • Context
    • Global Mode
  • Utils
    • Frequent Use
    • Variables
    • IO
    • DType
    • Shape
    • Dictionary
    • String
    • Meta
    • Mode
    • Misc
    • AverageRecorder
Next

© Copyright 2019, Texar Revision a23f021d.

Built with Sphinx using a theme provided by Read the Docs.
Read the Docs v: latest
Versions
latest
stable
Downloads
On Read the Docs
Project Home
Builds

Free document hosting provided by Read the Docs.