replace 'master' branch ref to 'main' for onnx repo (microsoft#12678)

docs/Reduced_Operator_Kernel_build.md

@@ -60,7 +60,7 @@ The opset can match either the opset import for each model, or the initial ONNX
 e.g. if a model imports opset 12 of ONNX, all ONNX operators in that model can be listed under opset 12 for the 'ai.onnx' domain.
 
 [Netron](https://netron.app/) can be used to view an ONNX model properties to discover the opset imports.
-Additionally, the ONNX operator specs for [DNN](https://github.com/onnx/onnx/blob/master/docs/Operators.md) and [traditional ML](https://github.com/onnx/onnx/blob/master/docs/Operators-ml.md) operators list the individual operator versions.
+Additionally, the ONNX operator specs for [DNN](https://github.com/onnx/onnx/blob/main/docs/Operators.md) and [traditional ML](https://github.com/onnx/onnx/blob/main/docs/Operators-ml.md) operators list the individual operator versions.
 
 ### Type reduction format
 

docs/Versioning.md

@@ -22,7 +22,7 @@ models that are stamped with ONNX opset versions in the range [7-9].
 ### Version matrix
 The [table](https://onnxruntime.ai/docs/reference/compatibility.html#onnx-opset-support) summarizes the relationship between the ONNX Runtime version and the ONNX opset version implemented in that release.
 Please note the backward compatibility notes above.
-For more details on ONNX Release versions, see [this page](https://github.com/onnx/onnx/blob/master/docs/Versioning.md).
+For more details on ONNX Release versions, see [this page](https://github.com/onnx/onnx/blob/main/docs/Versioning.md).
 
 ## Tool Compatibility
 A variety of tools can be used to create ONNX models. Unless otherwise noted, please use the latest released version of the tools to convert/export the ONNX model. Most tools are backwards compatible and support multiple ONNX versions. Join this with the table above to evaluate ONNX Runtime compatibility.
@@ -40,4 +40,3 @@ A variety of tools can be used to create ONNX models. Unless otherwise noted, pl
 |[Paddle2ONNX](https://pypi.org/project/paddle2onnx/)| [Latest stable](https://github.com/PaddlePaddle/Paddle2ONNX/releases) | 1.6-1.9 |
 |[AutoML](https://docs.microsoft.com/en-us/azure/machine-learning/service/concept-automated-ml)|[1.0.39+](https://pypi.org/project/azureml-automl-core)|1.5|
 | |[1.0.33](https://pypi.org/project/azureml-automl-core/1.0.33/)|1.4|
-

docs/onnxruntime_extensions.md

@@ -79,7 +79,7 @@ e2e_graph = helper.make_graph(
 )
 # ...
 ```
-For more usage of ONNX helper, please visit the document [Python API Overview](https://github.com/onnx/onnx/blob/master/docs/PythonAPIOverview.md).
+For more usage of ONNX helper, please visit the document [Python API Overview](https://github.com/onnx/onnx/blob/main/docs/PythonAPIOverview.md).
 
 ### Run E2E Model in Python
 ```python

docs/python/inference/api_summary.rst

@@ -17,7 +17,7 @@ Load and run a model
 --------------------
 
 InferenceSession is the main class of ONNX Runtime. It is used to load and run an ONNX model,
-as well as specify environment and application configuration options. 
+as well as specify environment and application configuration options.
 
 .. code-block:: python
 
@@ -65,7 +65,7 @@ Data on CPU
 ^^^^^^^^^^^
 
 On CPU (the default), OrtValues can be mapped to and from native Python data structures: numpy arrays, dictionaries and lists of
-numpy arrays. 
+numpy arrays.
 
 .. code-block:: python
 
@@ -95,15 +95,15 @@ this called `IOBinding`.
 
 To use the `IOBinding` feature, replace `InferenceSession.run()` with `InferenceSession.run_with_iobinding()`.
 
-A graph is executed on a device other than CPU, for instance CUDA. Users can 
+A graph is executed on a device other than CPU, for instance CUDA. Users can
 use IOBinding to copy the data onto the GPU.
 
 .. code-block:: python
 
-	# X is numpy array on cpu 
+	# X is numpy array on cpu
 	session = onnxruntime.InferenceSession('model.onnx', providers=['CUDAExecutionProvider', 'CPUExecutionProvider']))
 	io_binding = session.io_binding()
-	# OnnxRuntime will copy the data over to the CUDA device if 'input' is consumed by nodes on the CUDA device 
+	# OnnxRuntime will copy the data over to the CUDA device if 'input' is consumed by nodes on the CUDA device
 	io_binding.bind_cpu_input('input', X)
 	io_binding.bind_output('output')
 	session.run_with_iobinding(io_binding)
@@ -122,7 +122,7 @@ The input data is on a device, users directly use the input. The output data is
 	session.run_with_iobinding(io_binding)
 	Y = io_binding.copy_outputs_to_cpu()[0]
 
-The input data and output data are both on a device, users directly use the input and also place output on the device.	
+The input data and output data are both on a device, users directly use the input and also place output on the device.
 
 .. code-block:: python
 
@@ -284,7 +284,7 @@ Backend
 
 In addition to the regular API which is optimized for performance and usability, 
 *ONNX Runtime* also implements the
-`ONNX backend API <https://github.com/onnx/onnx/blob/master/docs/ImplementingAnOnnxBackend.md>`_
+`ONNX backend API <https://github.com/onnx/onnx/blob/main/docs/ImplementingAnOnnxBackend.md>`_
 for verification of *ONNX* specification conformance.
 The following functions are supported:
 

docs/python/inference/examples/plot_backend.py

@@ -8,8 +8,8 @@
 ONNX Runtime Backend for ONNX
 =============================
 
-*ONNX Runtime* extends the 
-`onnx backend API <https://github.com/onnx/onnx/blob/master/docs/ImplementingAnOnnxBackend.md>`_
+*ONNX Runtime* extends the
+`onnx backend API <https://github.com/onnx/onnx/blob/main/docs/ImplementingAnOnnxBackend.md>`_
 to run predictions using this runtime.
 Let's use the API to compute the prediction
 of a simple logistic regression model.

docs/python/inference/examples/plot_load_and_predict.py

@@ -19,7 +19,7 @@
 
 #########################
 # Let's load a very simple model.
-# The model is available on github `onnx...test_sigmoid <https://github.com/onnx/onnx/tree/master/onnx/backend/test/data/node/test_sigmoid>`_.
+# The model is available on github `onnx...test_sigmoid <https://github.com/onnx/onnx/blob/main/onnx/backend/test/data/node/test_sigmoid>`_.
 
 example1 = get_example("sigmoid.onnx")
 sess = rt.InferenceSession(example1, providers=rt.get_available_providers())

docs/python/inference/examples/plot_pipeline.py

@@ -6,7 +6,7 @@
 ===============
 
 There is no other way to look into one model stored
-in ONNX format than looking into its node with 
+in ONNX format than looking into its node with
 *onnx*. This example demonstrates
 how to draw a model and to retrieve it in *json*
 format.
@@ -34,7 +34,7 @@
 #################################
 # Draw a model with ONNX
 # ++++++++++++++++++++++
-# We use `net_drawer.py <https://github.com/onnx/onnx/blob/master/onnx/tools/net_drawer.py>`_
+# We use `net_drawer.py <https://github.com/onnx/onnx/blob/main/onnx/tools/net_drawer.py>`_
 # included in *onnx* package.
 # We use *onnx* to load the model
 # in a different way than before.

js/web/README.md

@@ -46,11 +46,11 @@ Refer to the following links for development information:
 
 #### WebAssembly backend
 
-ONNX Runtime Web currently support all operators in [ai.onnx](https://github.com/onnx/onnx/blob/master/docs/Operators.md) and [ai.onnx.ml](https://github.com/onnx/onnx/blob/master/docs/Operators-ml.md).
+ONNX Runtime Web currently support all operators in [ai.onnx](https://github.com/onnx/onnx/blob/main/docs/Operators.md) and [ai.onnx.ml](https://github.com/onnx/onnx/blob/main/docs/Operators-ml.md).
 
 #### WebGL backend
 
-ONNX Runtime Web currently supports a subset of operators in [ai.onnx](https://github.com/onnx/onnx/blob/master/docs/Operators.md) operator set. See [operators.md](./docs/operators.md) for a complete, detailed list of which ONNX operators are supported by WebGL backend.
+ONNX Runtime Web currently supports a subset of operators in [ai.onnx](https://github.com/onnx/onnx/blob/main/docs/Operators.md) operator set. See [operators.md](./docs/operators.md) for a complete, detailed list of which ONNX operators are supported by WebGL backend.
 
 ## License