Change the default opset to 15. (#2145)

* Change the default opset to 15.
* Update the ONNX version for one CI test.

Signed-off-by: Jay Zhang <[email protected]>

Author: fatcat-z

README.md

@@ -17,8 +17,8 @@ The common issues we run into we try to document here [Troubleshooting Guide](Tr
 
 | Build Type | OS | Python | TensorFlow | ONNX opset | Status |
 | ---        | ---    | ---    | ---        | ---        | ---    |
-| Unit Test - Basic | Linux, MacOS<sup>\*</sup>, Windows<sup>\*</sup> | 3.7-3.10 | 1.13-1.15, 2.1-2.10 | 13-17 | [![Build Status](https://dev.azure.com/tensorflow-onnx/tensorflow-onnx/_apis/build/status/unit_test?branchName=main)](https://dev.azure.com/tensorflow-onnx/tensorflow-onnx/_build/latest?definitionId=16&branchName=main) |
-| Unit Test - Full | Linux, MacOS, Windows | 3.7-3.10 | 1.13-1.15, 2.1-2.10 | 13-17 | [![Build Status](https://dev.azure.com/tensorflow-onnx/tensorflow-onnx/_apis/build/status/unit_test-matrix?branchName=main)](https://dev.azure.com/tensorflow-onnx/tensorflow-onnx/_build/latest?definitionId=18&branchName=main) | |
+| Unit Test - Basic | Linux, MacOS<sup>\*</sup>, Windows<sup>\*</sup> | 3.7-3.10 | 1.13-1.15, 2.1-2.10 | 14-18 | [![Build Status](https://dev.azure.com/tensorflow-onnx/tensorflow-onnx/_apis/build/status/unit_test?branchName=main)](https://dev.azure.com/tensorflow-onnx/tensorflow-onnx/_build/latest?definitionId=16&branchName=main) |
+| Unit Test - Full | Linux, MacOS, Windows | 3.7-3.10 | 1.13-1.15, 2.1-2.10 | 14-18 | [![Build Status](https://dev.azure.com/tensorflow-onnx/tensorflow-onnx/_apis/build/status/unit_test-matrix?branchName=main)](https://dev.azure.com/tensorflow-onnx/tensorflow-onnx/_build/latest?definitionId=18&branchName=main) | |
 <br/>
 
 ## Supported Versions
@@ -27,10 +27,10 @@ The common issues we run into we try to document here [Troubleshooting Guide](Tr
 
 tf2onnx will use the ONNX version installed on your system and installs the latest ONNX version if none is found.
 
-We support and test ONNX opset-13 to opset-17. opset-6 to opset-12 should work but we don't test them.
-By default we use ```opset-13``` for the resulting ONNX graph.
+We support and test ONNX opset-14 to opset-18. opset-6 to opset-13 should work but we don't test them.
+By default we use ```opset-15``` for the resulting ONNX graph.
 
-If you want the graph to be generated with a specific opset, use ```--opset``` in the command line, for example ```--opset 13```.
+If you want the graph to be generated with a specific opset, use ```--opset``` in the command line, for example ```--opset 15```.
 
 ### TensorFlow
 
@@ -97,9 +97,9 @@ To get started with `tensorflow-onnx`, run the `t2onnx.convert` command, providi
 
 ```python -m tf2onnx.convert --saved-model tensorflow-model-path --output model.onnx```
 
-The above command uses a default of `13` for the ONNX opset. If you need a newer opset, or want to limit your model to use an older opset then you can provide the `--opset` argument to the command. If you are unsure about which opset to use, refer to the [ONNX operator documentation](https://github.com/onnx/onnx/releases).
+The above command uses a default of `15` for the ONNX opset. If you need a newer opset, or want to limit your model to use an older opset then you can provide the `--opset` argument to the command. If you are unsure about which opset to use, refer to the [ONNX operator documentation](https://github.com/onnx/onnx/releases).
 
-```python -m tf2onnx.convert --saved-model tensorflow-model-path --opset 17 --output model.onnx```
+```python -m tf2onnx.convert --saved-model tensorflow-model-path --opset 18 --output model.onnx```
 
 If your TensorFlow model is in a format other than `saved model`, then you need to provide the inputs and outputs of the model graph.
 
@@ -192,7 +192,7 @@ ONNX requires default values for graph inputs to be constant, while Tensorflow's
 
 #### --opset
 
-By default we use the opset 13 to generate the graph. By specifying ```--opset``` the user can override the default to generate a graph with the desired opset. For example ```--opset 17``` would create a onnx graph that uses only ops available in opset 17. Because older opsets have in most cases fewer ops, some models might not convert on a older opset.
+By default we use the opset 15 to generate the graph. By specifying ```--opset``` the user can override the default to generate a graph with the desired opset. For example ```--opset 17``` would create a onnx graph that uses only ops available in opset 17. Because older opsets have in most cases fewer ops, some models might not convert on an older opset.
 
 #### --dequantize
 

ci_build/azure_pipelines/keras2onnx_application_tests.yml

@@ -105,9 +105,9 @@ jobs:
         INSTALL_NUMPY:
         NIGHTLY_BUILD_TEST: python run_all_v2.py
 
-      Python310-onnx1.13-tf2.9:
+      Python310-onnx1.12-tf2.9:
         python.version: '3.10'
-        ONNX_PATH: onnx==1.13.0
+        ONNX_PATH: onnx==1.12.0
         INSTALL_KERAS:
         UNINSTALL_KERAS:
         INSTALL_TENSORFLOW: pip install tensorflow==2.9.0

ci_build/azure_pipelines/templates/job_generator.yml

@@ -5,7 +5,7 @@ parameters:
   python_versions: ['3.7']
   tf_versions: ['']
   onnx_versions: ['1.13.1']
-  onnx_opsets: ['18', '17', '16', '15', '14', '13']
+  onnx_opsets: ['18', '17', '16', '15', '14']
   onnx_backends: {onnxruntime: ['1.14.1']}
   job: {}
   run_setup: 'True'

ci_build/azure_pipelines/templates/setup.yml

@@ -70,6 +70,10 @@ steps:
       if [[ $CI_TF_VERSION == 2.9* ]] ;
         then
           pip install "tensorflow-text>=2.9,<2.10"
+      fi
+      if [[ $CI_TF_VERSION == 2.10* ]] || [[ $CI_TF_VERSION == 2.11* ]] ;
+        then
+          pip install "tensorflow-text>=2.10,<2.12"
       else
         pip install tensorflow-text
       fi

ci_build/azure_pipelines/templates/unit_test.yml

@@ -1,7 +1,7 @@
 # Run unit test
 
 parameters:
-    onnx_opsets: ['18', '17', '16', '15', '14', '13']
+    onnx_opsets: ['18', '17', '16', '15', '14']
     skip_tflite_tests: 'True'
     skip_tfjs_tests: 'True'
     skip_tf_tests: 'False'

tf2onnx/constants.py

@@ -18,8 +18,8 @@
 # Default opset version for onnx domain.
 # The current update policy is that the default should be set to
 # the latest released version as of 18 months ago.
-# Opset 13 was released in ONNX v1.8.0 (Nov, 2020).
-PREFERRED_OPSET = 13
+# Opset 15 was released in ONNX v1.10.0 (Jul, 2021).
+PREFERRED_OPSET = 15
 
 # Default opset for custom ops
 TENSORFLOW_OPSET = helper.make_opsetid("ai.onnx.converters.tensorflow", 1)