Skip to content

Latest commit

 

History

History
72 lines (44 loc) · 4.42 KB

CHANGELOG.md

File metadata and controls

72 lines (44 loc) · 4.42 KB

[Unreleased]

New features

Feature improvements

Fixes

  • Fix docstring of connector _mlp_transform. (#192)

v0.2.2 (2019-08-05)

New features

Feature improvements

Fixes

v0.2.1 (2019-07-28)

New features

  • Add support for GPT-2 345M model in examples/gpt-2. (#156)
  • Add BERT modules, including texar.modules.BERTEncoder (doc) and texar.modules.BERTClassifier (doc). (#167)

Feature improvements

  • Refactor TransformerEncoder and TransformerDecoder to separate position embeddings from the modules. (#126)
  • Allow passing a Tensor to output_layer of decoders' constructors -- used for weight tie b/w the output layer and input embedding matrix. (#126)
  • TransformerDecoder constructor interface made exact the same with RNN decoders constructor interfaces. (#126)
  • Refactor decoder Helpers to allow two-argument embedding_fn (supporting for position embedding). (#126)
  • Refactor SinusoidsPositionEmbedder to enable infinite large or negative position indexes. (#176)

Fixes

  • Fix texar.losses.reduce_batch_time when sequence has dtype other than tf.float32. (#143)
  • Fix texar.losses.reduce_dimensions when average_axes or sum_axes is int. (#141)
  • Fix GPT-2 tokenization loading path. (#165)
  • Fix examples/vae_text EOS bug. (#168)
  • Fix transformer bleu_tool.py when translation_length is 0. (#176)
  • Fix StochasticConnector and ReparameterizedStochasticConnector when transform=False. (#179)

v0.2.0 (2019-04-09)

New features

  • TFRecordData: A new data module for reading and processing TFRecord data, with support for, e.g., image data, feature data, etc. (#107)
  • GPT-2: OpenAI pretrained language model. (#91, example)
  • TopKSampleEmbeddingHelper to perform top_k random sample decoding. (baa09ff)

Feature improvements

  • Refactor BERT example using TFRecordData data module.
  • TransformerDecoder supports helper arguments to specify decoding strategy. (#76)

Fixes

  • Fix variable collection bug in examples/seqgan. (#110)
  • Fix error when beam_search_decode with output_layer=tf.identity (#77)
  • Fix readthedocs compilation error (#85)

v0.1.0 (2019-02-06)

New features

  • [2019-01-02] Support distributed-GPU training. See the example
  • [2018-11-29] Support pre-trained BERT model. See the example