Metadata-Version: 2.1
Name: tfhubartifact
Version: 0.0.4
Summary: BentoML artifact framework for TensorFlow Hub models
Home-page: https://github.com/markmo/tfhubartifact
Author: Mark Moloney
Author-email: m4rkmo@gmail.com
License: UNKNOWN
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.6
Description-Content-Type: text/markdown
Requires-Dist: BentoML (==0.10.1)
Requires-Dist: tensorflow (==2.0.0)
Requires-Dist: tensorflow-hub (==0.5.0)

# tfhubartifact

BentoML artifact framework for TensorFlow Hub models.

Installation:

    pip install tfhubartifact==0.0.1

Usage example (decorate service):

    from tfhubartifact.TensorFlowHubModelArtifact import TensorFlowHubModelArtifact

    @artifacts([TensorFlowHubModelArtifact('embedder')])
    class MyBentoService(BentoService):


Usage example (package model):

    svc = MyBentoService()

    svc.pack('embedder', my_embedding_model_path)

Alternatively, during training:

    svc.pack('embedder', {'embedder': my_embedder})


