==========================================
Tensorflow gRPC and RESTful API Server
==========================================
Introduce
==============
**tfserver** is an example for serving *gRPC* for Tensorflow/Pytorch thing's models.
It can serve not only through **gRPC** but also **RESTful API** with `Skitai App Engine`_ and Atila_ WSGI container.
This project is inspired by `issue #176`_.
I'm so sorry about this soulless manual.
Installation
=====================
- from version 0.3, it is now TensorFlow 2+ compatible (deprecated, no longer support)
- from version 0.4, TensorFlow 2+ only
Building Model and Deploy
=======================================
Please see https://gitlab.com/hansroh/skitai/-/blob/master/tests/level4-2/build_model.py
It is mostly used tensorflow keras and dnn_.
Creating Your Own gRPC Server
========================================
Please see https://gitlab.com/hansroh/skitai/-/blob/master/tests/examples/tfserve.py
You can know how to serve gRPC service and make yoyr own APIs.
APIs
================
Please see https://gitlab.com/hansroh/tfserver/-/blob/master/tfserver/export/skitai/\_\_export\_\_.py
APIs to manage models and basic inference.
And for usage see, https://gitlab.com/hansroh/skitai/-/blob/master/tests/level4-2/test_tfserver.py
Release History
=============================
- 0.4 (2021. 4)
- upgrade for tensorflow 2
- 0.3 (2020. 6. 28)
- add model management APIs
- reactivate project and compatible with TF2+
- 0.2 (2020. 6. 26): integrated with dnn 0.3
- 0.1b8 (2018. 4. 13): fix grpc trailers, skitai upgrade is required
- 0.1b6 (2018. 3. 19): found works only grpcio 1.4.0
- 0.1b3 (2018. 2. 4): add @app.umounted decorator for clearing resource
- 0.1b2: remove self.tfsess.run (tf.global_variables_initializer())
- 0.1b1 (2018. 1. 28): Beta release
- 0.1a (2018. 1. 4): Alpha release
.. _`issue #176` : https://github.com/tensorflow/serving/issues/176
.. _`Skitai App Engine`: https://pypi.python.org/pypi/skitai
.. _Atila: https://pypi.python.org/pypi/atila
.. _dnn: https://pypi.python.org/pypi/dnn
Raw data
{
"_id": null,
"home_page": "https://gitlab.com/tfserver/tfserver",
"name": "tfserver",
"maintainer": "",
"docs_url": null,
"requires_python": "",
"maintainer_email": "",
"keywords": "",
"author": "Hans Roh",
"author_email": "hansroh@gmail.com",
"download_url": "https://pypi.python.org/pypi/tfserver",
"platform": "posix",
"description": "==========================================\nTensorflow gRPC and RESTful API Server\n==========================================\n\nIntroduce\n==============\n\n**tfserver** is an example for serving *gRPC* for Tensorflow/Pytorch thing's models.\n\nIt can serve not only through **gRPC** but also **RESTful API** with `Skitai App Engine`_ and Atila_ WSGI container.\n\nThis project is inspired by `issue #176`_.\n\nI'm so sorry about this soulless manual.\n\n\nInstallation\n=====================\n\n- from version 0.3, it is now TensorFlow 2+ compatible (deprecated, no longer support)\n- from version 0.4, TensorFlow 2+ only\n\n\nBuilding Model and Deploy\n=======================================\n\nPlease see https://gitlab.com/hansroh/skitai/-/blob/master/tests/level4-2/build_model.py\n\nIt is mostly used tensorflow keras and dnn_.\n\n\nCreating Your Own gRPC Server\n========================================\n\nPlease see https://gitlab.com/hansroh/skitai/-/blob/master/tests/examples/tfserve.py\n\nYou can know how to serve gRPC service and make yoyr own APIs.\n\n\nAPIs\n================\n\nPlease see https://gitlab.com/hansroh/tfserver/-/blob/master/tfserver/export/skitai/\\_\\_export\\_\\_.py\n\nAPIs to manage models and basic inference.\n\nAnd for usage see, https://gitlab.com/hansroh/skitai/-/blob/master/tests/level4-2/test_tfserver.py\n\n\nRelease History\n=============================\n\n- 0.4 (2021. 4)\n\n - upgrade for tensorflow 2\n\n- 0.3 (2020. 6. 28)\n\n - add model management APIs\n - reactivate project and compatible with TF2+\n\n- 0.2 (2020. 6. 26): integrated with dnn 0.3\n\n- 0.1b8 (2018. 4. 13): fix grpc trailers, skitai upgrade is required\n\n- 0.1b6 (2018. 3. 19): found works only grpcio 1.4.0\n\n- 0.1b3 (2018. 2. 4): add @app.umounted decorator for clearing resource\n\n- 0.1b2: remove self.tfsess.run (tf.global_variables_initializer())\n\n- 0.1b1 (2018. 1. 28): Beta release\n\n- 0.1a (2018. 1. 4): Alpha release\n\n\n.. _`issue #176` : https://github.com/tensorflow/serving/issues/176\n.. _`Skitai App Engine`: https://pypi.python.org/pypi/skitai\n.. _Atila: https://pypi.python.org/pypi/atila\n.. _dnn: https://pypi.python.org/pypi/dnn\n\n\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Tensor Flow Model Server",
"version": "0.4.11",
"project_urls": {
"Download": "https://pypi.python.org/pypi/tfserver",
"Homepage": "https://gitlab.com/tfserver/tfserver"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "42639e65d4f97191f7544baa037766c40ebf94e15c7233ccaed636fa600c218f",
"md5": "7b492511090252fcedb9fa8c5bea3c74",
"sha256": "f16d795e135049555c10c3f3daa505d204906591d9d186fcae9f0666db7d6411"
},
"downloads": -1,
"filename": "tfserver-0.4.11-py3-none-any.whl",
"has_sig": false,
"md5_digest": "7b492511090252fcedb9fa8c5bea3c74",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 27141,
"upload_time": "2023-11-02T23:39:47",
"upload_time_iso_8601": "2023-11-02T23:39:47.765661Z",
"url": "https://files.pythonhosted.org/packages/42/63/9e65d4f97191f7544baa037766c40ebf94e15c7233ccaed636fa600c218f/tfserver-0.4.11-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-11-02 23:39:47",
"github": false,
"gitlab": true,
"bitbucket": false,
"codeberg": false,
"gitlab_user": "tfserver",
"gitlab_project": "tfserver",
"lcname": "tfserver"
}