About the 'axis' transformation

TensorFlow Backend for ONNX

Note this repo is not actively maintained and will be deprecated. If you are interested in becoming the owner, please contact the ONNX Steering Committee (https://github.com/onnx/steering-committee).

Open Neural Network Exchange (ONNX) is an open standard format for representing machine learning models. ONNX is supported by a community of partners who have implemented it in many frameworks and tools.

TensorFlow Backend for ONNX makes it possible to use ONNX models as input for TensorFlow. The ONNX model is first converted to a TensorFlow model and then delegated for execution on TensorFlow to produce the output.

This is one of the two TensorFlow converter projects which serve different purposes in the ONNX community:

onnx-tensorflow converts ONNX models to Tensorflow
tf2onnx converts Tensorflow models to ONNX

Converting Models from ONNX to TensorFlow

Use CLI

Command Line Interface Documentation

From ONNX to TensorFlow: onnx-tf convert -i /path/to/input.onnx -o /path/to/output

Convert Programmatically

From ONNX to TensorFlow

Migrating from `onnx-tf` to `tf-onnx`

We have joined force with Microsoft to co-develop ONNX TensorFlow frontend. For current onnx-tf frontend users, please migrate to use tf-onnx (https://github.com/onnx/tensorflow-onnx) where our code had been merged into.

ONNX Model Inference with TensorFlow Backend

import onnx
from onnx_tf.backend import prepare

onnx_model = onnx.load("input_path")  # load onnx model
output = prepare(onnx_model).run(input)  # run the loaded model

Production Installation

ONNX-TF requires ONNX (Open Neural Network Exchange) as an external dependency, for any issues related to ONNX installation, we refer our users to ONNX project repository for documentation and help. Notably, please ensure that protoc is available if you plan to install ONNX via pip.

The specific ONNX release version that we support in the master branch of ONNX-TF can be found here. This information about ONNX version requirement is automatically encoded in setup.py, therefore users needn't worry about ONNX version requirement when installing ONNX-TF.

To install the latest version of ONNX-TF via pip, run pip install onnx-tf.

Because users often have their own preferences for which variant of TensorFlow to install (i.e., a GPU version instead of a CPU version), we do not explicitly require tensorflow in the installation script. It is therefore users' responsibility to ensure that the proper variant of TensorFlow is available to ONNX-TF. Moreover, we require TensorFlow version == 2.8.0.

Development

Coverage Status

ONNX-TensorFlow Op Coverage Status

API

ONNX-TensorFlow API

Installation

Install ONNX master branch from source.
Install TensorFlow >= 2.8.0, tensorflow-probability and tensorflow-addons. (Note TensorFlow 1.x is no longer supported)
Run git clone https://github.com/onnx/onnx-tensorflow.git && cd onnx-tensorflow.
Run pip install -e ..

Folder Structure

onnx_tf: main source code file.
test: test files.

Code Standard

Format code

pip install yapf
yapf -rip --style="{based_on_style: google, indent_width: 2}" $FilePath$

Install pylint

pip install pylint
wget -O /tmp/pylintrc https://raw.githubusercontent.com/tensorflow/tensorflow/master/tensorflow/tools/ci_build/pylintrc

Check format

pylint --rcfile=/tmp/pylintrc myfile.py

Documentation Standard

Google Style Python Docstrings

Testing

Unit Tests

To perfom unit tests:

pip install pytest tabulate
python -m unittest discover test

Note: Only the ONNX backend tests found in test_onnx_backend.py require the pytest and tabulate packages.

Testing requires significant hardware resources, but nonetheless, we highly recommend that users run through the complete test suite before deploying onnx-tf. The complete test suite typically takes between 15 and 45 minutes to complete, depending on hardware configurations.

Model Zoo Tests

The tests in test_modelzoo.py verify whether the ONNX Model Zoo models can be successfully validated against the ONNX specification and converted to a TensorFlow representation. Model inferencing on the converted model is not tested currently.

Prerequisites

The model zoo uses Git LFS (Large File Storage) to store ONNX model files. Make sure that Git LFS is installed on your operating system.

Running

By default, the tests assume that the model zoo repository has been cloned into this project directory. The model zoo directory is scanned for ONNX models. For each model found: download the model, convert the model to TensorFlow, generate a test status, and delete the model. By default, the generated test report is created in the system temporary directory. Run python test/test_modelzoo.py -h for help on command line options.

git clone https://github.com/onnx/models
python test/test_modelzoo.py

Testing all models can take at least an hour to complete, depending on hardware configuration and model download times. If you expect to test some models frequently, we recommend using Git LFS to download those models before running the tests so the large files are cached locally.

Reports

When making code contributions, the model zoo tests are run when a commit is merged. Generated test reports are published on the onnx-tensorflow wiki.

	def _onnx_node_to_tensorflow_op(cls, node, input_dict):
	op_name_lowered = cls.op_name_to_lower(node.op_type)
	if op_name_lowered in cls.onnx_tf_op_map.keys():
	return cls.handle_trivial(node, input_dict)

	handler_name = "handle_" + op_name_lowered
	# Check if specialized handler exists.
	if handler_name in dir(cls):
	method_to_call = getattr(cls, handler_name)
	return method_to_call(node, input_dict)
	else:
	raise NotImplementedError("{} op is not implemented.".format(node.op_type))

	elif node.op in TF_OP_STR_TO_ONNX_OP.keys():
	# Remove tensorflow-specific attrs that are not
	# needed/allowed in ONNX.
	attr_to_remove = ["_output_shapes", "T", "seed2", "Tidx"]
	node.attr = dict(filter(lambda pair: pair[0]
	not in attr_to_remove, node.attr.items()))

	node_output = node.name
	ops_proto.append(make_node(TF_OP_STR_TO_ONNX_OP[node.op],
	node.inputs,
	[node_output],
	name=node.name,
	**node.attr))
	else:
	handler_name = "handle_" + op_name_to_lower(node.op)

	# Check if specialized handler exists.
	if handler_name in dir(cls):
	method_to_call = getattr(cls, handler_name)
	ops_proto.append(method_to_call(node, consts))
	else:
	raise NotImplementedError("{} op is not implemented.".format(node.op))

	external_output = dict(filter(lambda kv: kv[0] in self.predict_net.external_output, list(self.predict_net.output_dict.items())))

	output_values = sess.run(list(external_output.values()), feed_dict=feed_dict)

onnx / onnx-tensorflow Goto Github PK

onnx-tensorflow's Introduction

TensorFlow Backend for ONNX

Note this repo is not actively maintained and will be deprecated. If you are interested in becoming the owner, please contact the ONNX Steering Committee (https://github.com/onnx/steering-committee).

Converting Models from ONNX to TensorFlow

Use CLI

Convert Programmatically

Migrating from onnx-tf to tf-onnx

ONNX Model Inference with TensorFlow Backend

More Tutorials

Production Installation

Development

Coverage Status

API

Installation

Folder Structure

Code Standard

Documentation Standard

Testing

Unit Tests

Model Zoo Tests

Prerequisites

Running

Reports

onnx-tensorflow's People

Contributors

Stargazers

Watchers

Forkers

onnx-tensorflow's Issues

Recommend Projects

Recommend Topics

Recommend Org

Migrating from `onnx-tf` to `tf-onnx`