saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-07-23 19:32:23 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Update Python documentation (#2210)

Browse source
This commit is contained in:
Faith Xu 2019-10-21 16:56:31 -07:00 committed by Changming Sun
parent e8ec52814f
commit 303a78c301
3 changed files with 7 additions and 45 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

9
docs/python/README.rst
View file

@ -1,12 +1,9 @@
ONNX Runtime
============
ONNX Runtime
enables high-performance evaluation of trained machine learning (ML)
models while keeping resource usage low once converted into ONNX format.
See `project information <https://github.com/microsoft/onnxruntime>`_
and `Python API documentation and examples <https://aka.ms/onnxruntime-python>`_
for further details.
ONNX Runtime is a performance-focused scoring engine for Open Neural Network Exchange (ONNX) models.
For more information on ONNX Runtime, please see `aka.ms/onnxruntime <https://aka.ms/onnxruntime/>`_ or the `Github project <https://github.com/microsoft/onnxruntime/>`_.
Changes
-------

33
docs/python/index.rst
View file

@ -2,13 +2,8 @@
Python Bindings for ONNX Runtime
================================
ONNX Runtime enables high-performance evaluation of trained machine learning (ML)
models while keeping resource usage low.
Building on Microsoft's dedication to the
`Open Neural Network Exchange (ONNX) <https://onnx.ai/>`_
community, it supports traditional ML models as well
as Deep Learning algorithms in the
`ONNX-ML format <https://github.com/onnx/onnx/blob/master/docs/IR.md>`_.
ONNX Runtime is a performance-focused scoring engine for Open Neural Network Exchange (ONNX) models.
For more information on ONNX Runtime, please see `aka.ms/onnxruntime <https://aka.ms/onnxruntime/>`_ or the `Github project <https://github.com/microsoft/onnxruntime/>`_.
.. toctree::
:maxdepth: 1
@ -16,27 +11,3 @@ as Deep Learning algorithms in the
tutorial
api_summary
auto_examples/index
:ref:`genindex`
The core library is implemented in C++.
*ONNX Runtime* is available on
PyPi for Linux Ubuntu 16.04, Python 3.5+ for both
`CPU <https://pypi.org/project/onnxruntime/>`_ and
`GPU <https://pypi.org/project/onnxruntime-gpu/>`_.
Please see `system requirements <https://github.com/Microsoft/onnxruntime#system-requirements>`_ before installating the packages.
This example demonstrates a simple prediction for an
`ONNX-ML format <https://github.com/onnx/onnx/blob/master/docs/IR.md>`_
model. The following file ``model.onnx`` is taken from
github `onnx...test_sigmoid <https://github.com/onnx/onnx/tree/master/onnx/backend/test/data/node/test_sigmoid>`_.
.. runpython::
:showcode:
import numpy
import onnxruntime as rt
sess = rt.InferenceSession("model.onnx")
input_name = sess.get_inputs()[0].name
X = numpy.random.random((3,4,5)).astype(numpy.float32)
pred_onnx = sess.run(None, {input_name: X})
print(pred_onnx)

10
onnxruntime/__init__.py
View file

@ -3,14 +3,8 @@
# Licensed under the MIT License.
# --------------------------------------------------------------------------
"""
ONNX Runtime
enables high-performance evaluation of trained machine learning (ML)
models while keeping resource usage low.
Building on Microsoft's dedication to the
`Open Neural Network Exchange (ONNX) <https://onnx.ai/>`_
community, it supports traditional ML models as well
as Deep Learning algorithms in the
`ONNX-ML format <https://github.com/onnx/onnx/blob/master/docs/IR.md>`_.
ONNX Runtime is a performance-focused scoring engine for Open Neural Network Exchange (ONNX) models.
For more information on ONNX Runtime, please see `aka.ms/onnxruntime <https://aka.ms/onnxruntime/>`_ or the `Github project <https://github.com/microsoft/onnxruntime/>`_.
"""
__version__ = "0.5.0"
__author__ = "Microsoft"