Skip to content

N
ngraph
Commit 5f4e2290 authored by Leona C's avatar Leona C Committed by Scott Cyphers
Browse files
Options

Update documentation for ngraph_onnx building (#3528)

parent 7c540e52
Hide whitespace changes
Inline Side-by-side
Showing with 5 additions and 96 deletions
doc/sphinx/source/core/constructing-graphs/import.rst
View file @ 5f4e2290
...@@ -27,100 +27,25 @@ usually named ``<some_model>.onnx`` or ``<some_model>.onnx.pb``. These ...@@ -27,100 +27,25 @@ usually named ``<some_model>.onnx`` or ``<some_model>.onnx.pb``. These
needing to dig into anything from the "Frameworks" sections. You will, however, needing to dig into anything from the "Frameworks" sections. You will, however,
need to have completed the steps outlined in our :doc:`../../buildlb` guide. need to have completed the steps outlined in our :doc:`../../buildlb` guide.
To demonstrate functionality, we'll use an already-serialized CIFAR10 model To demonstrate functionality, we'll use an already-serialized CIFAR10 model
trained via ResNet20. Remember that this model has already been trained and trained via ResNet20. Remember that this model has already been trained and
exported from a framework such as Caffe2, PyTorch or CNTK; we are simply going exported from a framework such as Caffe2, PyTorch or CNTK; we are simply going
to build an nGraph representation of the model, execute it, and produce some to build an nGraph representation of the model, execute it, and produce some
outputs. outputs.
Installing ``ngraph_onnx`` with nGraph from scratch Installing ``ngraph_onnx`` with nGraph from scratch
==================================================== ====================================================
To use ONNX models with nGraph, you will also need the companion tool See the documentation on: `building nGraph and nGraph-ONNX`_ for the latest
``ngraph_onnx``, which requires Python 3.4 or higher. If nGraph has not instructions.
yet been installed to your system, you can follow these steps to install
everything at once; if an `ngraph_dist` is already installed on your system,
skip ahead to the next section, :ref:`install_ngonnx`.
#. Install prerequisites for the system and install nGraph as ``ngraph_dist``.
.. code-block:: console
$ apt update
$ apt install python3 python3-pip python3-dev python3-venv
$ apt install build-essential cmake curl clang-3.9 git zlib1g zlib1g-dev libtinfo-dev
$ git clone https://github.com/NervanaSystems/ngraph.git
$ cd ngraph && mkdir build
$ cd build && cmake ../ -DCMAKE_INSTALL_PREFIX=~/ngraph_dist
$ make install
#. Build the Python package (binary wheel) for ngraph and set up an env for ONNX;
be sure to export the ``NGRAPH_CPP_BUILD_PATH`` where the ``ngraph_dist`` was
installed.
.. code-block:: console
$ cd ngraph/python
$ git clone --recursive -b allow-nonconstructible-holders https://github.com/jagerman/pybind11.git
$ export PYBIND_HEADERS_PATH=$PWD/pybind11
$ export NGRAPH_CPP_BUILD_PATH=~/ngraph_dist
$ python3 setup.py bdist_wheel
$ cd .. python3 -m venv onnx
$ cd onnx/
$ . bin/activate
#. Check for the binary wheel file under ``ngraph/python/dist`` and install it
with pip.
.. code-block:: console
(onnx)$ pip install -U python/dist/ngraph-[version]-cp36-cp36m-linux_x86_64.whl
Where ``[version]`` is the version number of the nGraph Python module
you see in that directory.
#. Confirm ``ngraph`` is properly installed through a Python interpreter:
.. code-block:: console
(onnx)$ python3
.. code-block:: python
import ngraph as ng
ng.abs([[1, 2, 3], [4, 5, 6]])
<Abs: 'Abs_1' ([2, 3])>
If you don't see any errors, ngraph should be installed correctly.
.. _install_ngonnx:
Installing ngraph-onnx
-----------------------
Add the dependencies for ONNX:
.. code-block:: console
$ apt install protobuf-compiler libprotobuf-dev
Install the ``ngraph-onnx`` companion tool using pip:
.. code-block:: console
(onnx) $ pip install git+https://github.com/NervanaSystems/ngraph-onnx/
.. _import_model:
Importing a serialized model Importing a serialized model
============================= =============================
With the dependencies added, we can now import a model that has After building and installing ``ngraph_onnx``, we can import a model that has
been serialized by ONNX, interact locally with the model by running been serialized by ONNX, interact locally with the model by running
Python code, create and load objects, and run inference. Python code, create and load objects, and run inference.
...@@ -229,23 +154,7 @@ demonstration purposes, the code will look something like: ...@@ -229,23 +154,7 @@ demonstration purposes, the code will look something like:
dtype=float32) dtype=float32)
.. _building nGraph and nGraph-ONNX: https://github.com/NervanaSystems/ngraph-onnx/blob/master/BUILDING.md
.. Importing models from NNVM
---------------------------
.. if you work on NNVM you can add this instruction here.
.. Importing models serialized with XLA
-------------------------------------
.. if you work on XLA you can add this instruction here.
.. etc, eof
.. _ngraph-onnx: https://github.com/NervanaSystems/ngraph-onnx#ngraph .. _ngraph-onnx: https://github.com/NervanaSystems/ngraph-onnx#ngraph
.. _ONNX: http://onnx.ai .. _ONNX: http://onnx.ai
.. _tutorials from ONNX: https://github.com/onnx/tutorials .. _tutorials from ONNX: https://github.com/onnx/tutorials
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment