Release notes¶
Upgrading¶
To upgrade Kashgari to the latest version, use pip
:
pip uninstall -y kashgari-tf
pip install --upgrade kashgari
To inspect the currently installed version, use the following command:
pip show kashgari
Current Release¶
[2.0.1] - 2020.10.28¶
✨ Add
convert_to_saved_model
API for tf-serving use case.✨ Add tf-serving documents.
[2.0.0] - 2020.09.10¶
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
1.1.1 - 2020.03.13¶
✨ Add BERTEmbeddingV2.
💥 Migrate documents to https://readthedoc.org for the version control.
1.1.0 - 2019.12.27¶
✨ Add Scoring task. (#303)
✨ Add tokenizers.
🐛 Fixing multi-label classification model loading. #304
1.0.0 - 2019.10.18¶
Unfortunately, we have to change the package name for clarity and consistency. Here is the new naming sytle.
Backend | pypi version | desc |
---|---|---|
TensorFlow 2.x | kashgari 2.x.x | coming soon |
TensorFlow 1.14+ | kashgari 1.x.x | |
Keras | kashgari 0.x.x | legacy version |
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 | - |
0.5.4 - 2019.09.30¶
✨ Add shuffle parameter to fit function (#249)
✨ Improved type hinting for loaded model (#248)
🐛 Fix the configuration changes during embedding save/load (#224)
🐛 Fix stacked embedding save/load (#224)
🐛 Fix evaluate function where the list has int instead of str ([#222])
💥 Renaming model.pre_processor to model.processor
🚨 Removing TensorFlow and numpy warnings
📝 Add docs how to specify which CPU or GPU
📝 Add docs how to compile model with custom optimizer
0.5.1 - 2019.07.15¶
📝 Rewrite documents with mkdocs
📝 Add Chinese documents
✨ Add
predict_top_k_class
for classification model to get predict probabilities (#146)🚸 Add
label2idx
,token2idx
properties to Embeddings and Models🚸 Add
tokenizer
property for BERT Embedding. (#136)🚸 Add
predict_kwargs
for modelspredict()
function⚡️ Change multi-label classification’s default loss function to binary_crossentropy (#151)
Legacy Version Changelog¶
0.2.0¶
multi-label classification for all classification models
support cuDNN cell for sequence labeling
add option for output
BOS
andEOS
in sequence labeling result, fix #31
0.1.9¶
add
AVCNNModel
,KMaxCNNModel
,RCNNModel
,AVRNNModel
,DropoutBGRUModel
,DropoutAVRNNModel
model to classification task.fix several small bugs
0.1.8¶
fix BERT Embedding model’s
to_json
function, issue #19
0.1.7¶
remove class candidates filter to fix #16
overwrite init function in CustomEmbedding
add parameter check to custom_embedding layer
add
keras-bert
version to setup.py file
0.1.6¶
add
output_dict
,debug_info
params to text_classification modeladd
output_dict
,debug_info
andchunk_joiner
params to text_classification modelfix possible crash at data_generator
0.1.5¶
fix sequence labeling evaluate result output
refactor model save and load function
0.1.4¶
fix classification model evaluate result output
change test settings