PyText
master

Getting Started

  • Installation
  • Train your first model
  • Execute your first model
  • Visualize Model Training with TensorBoard
  • Use PyText models in your app
  • Serve Models in Production
  • Config Files Explained
  • Config Commands

Training More Advanced Models

  • Train Intent-Slot model on ATIS Dataset
  • Hierarchical intent and slot filling
  • Multitask training with disjoint datasets
  • Data Parallel Distributed Training
  • XLM-RoBERTa
  • Semantic parsing with sequence-to-sequence models

Extending PyText

  • Architecture Overview
  • Custom Data Format
  • Custom Tensorizer
  • Using External Dense Features
  • Creating A New Model
  • Hacking PyText

References

  • pytext
    • config
    • data
    • exporters
    • loss
    • metric_reporters
    • models
      • bert_classification_models
      • bert_regression_model
      • decoders
        • decoder_base
        • intent_slot_model_decoder
        • mlp_decoder
        • mlp_decoder_query_response
        • mlp_decoder_two_tower
      • disjoint_multitask_model
      • doc_model
      • embeddings
      • ensembles
      • joint_model
      • language_models
      • masked_lm
      • model
      • module
      • output_layers
      • pair_classification_model
      • qna
      • query_document_pairwise_ranking_model
      • r3f_models
      • representations
      • roberta
      • semantic_parsers
      • seq_models
      • two_tower_classification_model
      • word_model
    • optimizer
    • task
    • torchscript
    • trainers
  • pytext package
PyText
  • Docs »
  • pytext »
  • models »
  • decoders
  • Edit on GitHub

decodersΒΆ

  • decoder_base
    • DecoderBase.Config
  • intent_slot_model_decoder
    • IntentSlotModelDecoder.Config
  • mlp_decoder
    • MLPDecoder.Config
  • mlp_decoder_query_response
    • MLPDecoderQueryResponse.Config
  • mlp_decoder_two_tower
    • MLPDecoderTwoTower.Config
Next Previous

© Copyright 2018, PyText Contributors Revision e407685a.

Built with Sphinx using a theme provided by Read the Docs.