Skip to content

Releases: BrikerMan/Kashgari

Release v2.0.2

04 Jul 10:44
7d18e08
Compare
Choose a tag to compare
  • 🐛 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

30 Oct 12:37
75bd4ac
Compare
Choose a tag to compare
  • ✨ Add convert_to_saved_model API for tf-serving use case.
  • ✨ Add tf-serving documents.

v2.0.0

10 Sep 10:28
Compare
Choose a tag to compare

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

25 Apr 05:05
Compare
Choose a tag to compare
  • 🐛 Fix transformer embedding error, loaded custom objects. ([#358])

v1.1.4

30 Mar 10:56
Compare
Choose a tag to compare
  • 🐛Fix bert embedding v2 error, set default to not-trainable.

v1.1.3

29 Mar 01:12
Compare
Choose a tag to compare
  • 🐛 Fixing vocab_path typo.

v1.1.2

27 Mar 03:43
6d2970e
Compare
Choose a tag to compare
  • ✨ Add save best model callback KashgariModelCheckpoint.
  • ⬆️ Upgrading bert4keras version to 0.6.5.

v1.1.1

13 Mar 03:27
9f5b972
Compare
Choose a tag to compare

v1.1.0

27 Dec 09:06
9d72b7b
Compare
Choose a tag to compare
  • ✨ Add Scoring task. ([#303])
  • ✨ Add tokenizers.
  • 🐛 Fixing multi-label classification model loading. #304

v1.0.0

18 Oct 08:09
822169e
Compare
Choose a tag to compare

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.