Kashgari Versions Save

• 🐛 Fixed Custom Model load issue.
• 🐛 Fixed model save issue on Windows.
• 🐛 Fixed multi-label model load issue.
• 🐛 Fixed CRF model load issue.
• 🐛 Fixed TensorFlow 2.3+ Support.

• ✨ Add convert_to_saved_model API for tf-serving use case.
• ✨ Add tf-serving documents.

This is a fully re-implemented version with TF2.

• ✨ Embeddings
• ✨ Text Classification Task
• ✨ Text Labeling Task
• ✨ Seq2Seq Task
• ✨ Examples
  • ✨ Neural machine translation with Seq2Seq
  • ✨ Benchmarks

• 🐛 Fix transformer embedding error, loaded custom objects. ([#358])

• 🐛Fix bert embedding v2 error, set default to not-trainable.

• 🐛 Fixing vocab_path typo.

• ✨ Add save best model callback KashgariModelCheckpoint.
• ⬆️ Upgrading bert4keras version to 0.6.5.

• ✨ Add BERTEmbeddingV2.
• 💥 Migrate documents to https://readthedoc.org for the version control.

• ✨ Add Scoring task. ([#303])
• ✨ Add tokenizers.
• 🐛 Fixing multi-label classification model loading. #304

Unfortunately, we renamed again for consistency and clarity. Here is the new naming style.

If you are using the kashgari-tf version. You only need to run this command to install the new version.

pip uninstall -y kashgari-tf
pip install kashgari

Here is how the existing versions changes

• 💥Renaming pypi package name to kashgari.
• ✨Allows custom average types, logs to an array for easy access to the last epoch.
• ✨Add min_count parameter to the base_processor.
• ✨Add disable_auto_summary config.