Release v2.0.2

• 🐛 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.

v2.0.1

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

v2.0.0

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

v1.1.5

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

v1.1.4

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

v1.1.3

• 🐛 Fixing vocab_path typo.

v1.1.2

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

v1.1.1

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

v1.1.0

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

v1.0.0

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

Backend	pypi version	desc
TensorFlow 2.x	kashgari 2.x.x	coming soon
TensorFlow 1.14+	kashgari 1.x.x	current version
Keras	kashgari 0.x.x	legacy version

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

Supported Backend	Kashgari Versions	Kahgsari-tf Version
TensorFlow 2.x	kashgari 2.x.x	-
TensorFlow 1.14+	kashgari 1.0.1	-
TensorFlow 1.14+	kashgari 1.0.0	0.5.5
TensorFlow 1.14+	-	0.5.4
TensorFlow 1.14+	-	0.5.3
TensorFlow 1.14+	-	0.5.2
TensorFlow 1.14+	-	0.5.1
Keras (legacy)	kashgari 0.2.6	-
Keras (legacy)	kashgari 0.2.5	-
Keras (legacy)	kashgari 0.x.x	-

• 💥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.