Tensorflow Onnx Versions Save

Convert TensorFlow, Keras, Tensorflow.js and Tflite models to ONNX

v1.16.1

3 months ago

What's Changed

Correct the required version of protobuf. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/2288
Support latest version(2.15/2.14) of TensorFlow. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/2292

Full Changelog: https://github.com/onnx/tensorflow-onnx/compare/v1.16.0...v1.16.1

v1.16.0

4 months ago

What's Changed

Fix CI nightly test issues. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/2229
Bump ONNX 1.14.1 by @jcwchen in https://github.com/onnx/tensorflow-onnx/pull/2220
Support tf ResizeArea op. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/2241
Keep activations in bidirectional LSTM (fixes: https://github.com/onnx/tensorflow-onnx/issues/2211) by @MaximeChurin in https://github.com/onnx/tensorflow-onnx/pull/2234
Support bool inputs for MatrixBandPart by @Gerstenberger in https://github.com/onnx/tensorflow-onnx/pull/2269
Fix unsupported ops TF 2.14.0: OnesLike by @Gerstenberger in https://github.com/onnx/tensorflow-onnx/pull/2270
Add a condition when remove a transpose node in TransposeOptimizer. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/2272
Change the way to set node name. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/2278
Enable support to ONNX 1.15. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/2279
Adjust CI tests coverage in different pipelines. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/2281
Enable support to ONNXRUNTIME 1.16.3. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/2283

A huge thank you to our community for this release!

@MaximeChurin
@Gerstenberger
@jcwchen

Full Changelog: https://github.com/onnx/tensorflow-onnx/compare/v1.15.1...v1.16.0

v1.15.1

8 months ago

What's Changed

Loose flatbuffers version constraints by @yan12125 in https://github.com/onnx/tensorflow-onnx/pull/2225

A huge thank you to our community for this release!

@yan12125

Full Changelog: https://github.com/onnx/tensorflow-onnx/compare/v1.15.0...v1.15.1

v1.15.0

8 months ago

What's Changed

Fix None shape error when one input to ConcatV2 has a shape. by @klasma in https://github.com/onnx/tensorflow-onnx/pull/2135
Change Equal 11 for string input by @mikeessen in https://github.com/onnx/tensorflow-onnx/pull/2149
Update tf_loader.py to remove unnecessary slices by @DLumi in https://github.com/onnx/tensorflow-onnx/pull/2159
Fix fusing of Conv and Mul in TransposeOptimizer (#2088) by @cosineFish in https://github.com/onnx/tensorflow-onnx/pull/2152
Support for more TensorScatter* operations by @javidcf in https://github.com/onnx/tensorflow-onnx/pull/2179
Added support for int64 -> string CategoryMapper updated by @pagran in https://github.com/onnx/tensorflow-onnx/pull/2181
Fixed group attribute in convolution op by @javidcf in https://github.com/onnx/tensorflow-onnx/pull/2090
Fix a bug that multiple (conv, batch_norm) ops could not be optimized. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/2187
Support bitwise ops by @f-salvetti in https://github.com/onnx/tensorflow-onnx/pull/2192
Update parent graph in loop "cond" subgraphs by @f-salvetti in https://github.com/onnx/tensorflow-onnx/pull/2201
Fix wrong shapes in loop body inputs if shape invariances are set in TF by @f-salvetti in https://github.com/onnx/tensorflow-onnx/pull/2203
Support unique_with_counts by @f-salvetti in https://github.com/onnx/tensorflow-onnx/pull/2195
Some minor fixes for keras-resnet50 tutorial by @shreyas-bk in https://github.com/onnx/tensorflow-onnx/pull/2207
Use TFLite Interpreter's public instead of private API to get tensor details by @q-ycong-p in https://github.com/onnx/tensorflow-onnx/pull/2204
Support latest version of TensorFlow (both 2.12 and 2.13) and ONNX opset 18. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/2216

A huge thank you to our community for this release!

@klasma
@mikeessen
@DLumi
@javidcf
@pagran
@shreyas-bk

Full Changelog: https://github.com/onnx/tensorflow-onnx/compare/v1.14.0...v1.15.0

v1.14.0

1 year ago

What's Changed

Update the dtype since latest version of Numpy has removed str. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/2112
Fix Infinite Loop in constant folding by @ilyasher in https://github.com/onnx/tensorflow-onnx/pull/2119
Update tf2onnx to support TensorFlow 2.11. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/2131
Allow --extra_opset to accept a list of extra opsets. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/2136
Fix the axis of inserted QDQ for ConvTranspose by @sdua-nv in https://github.com/onnx/tensorflow-onnx/pull/2134
Adding tf.strings.reduce_join mapping by @fsalv in https://github.com/onnx/tensorflow-onnx/pull/2091
A fix for seed attribute in the keras random normal generator by @inonbe in https://github.com/onnx/tensorflow-onnx/pull/2126
Fix ResizeBilinear and ResizeNearestNeighbor and update related tests by @cosineFish in https://github.com/onnx/tensorflow-onnx/pull/2130
Update Resize (opset 11) layer to support scales option when dims are… by @qant-um in https://github.com/onnx/tensorflow-onnx/pull/2137
Fix issue #2102: Set reduction axis of mean to height and width for tf adjust_contrast op by @cosineFish in https://github.com/onnx/tensorflow-onnx/pull/2140
support cumprod op by @f-salvetti in https://github.com/onnx/tensorflow-onnx/pull/2133
Support ONNXRUNTIME 1.14 and opset 18. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/2143
Change the default opset to 15. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/2145

A huge thank you to our community for this release!

ilyasher sdua-nv fsalv inonbe cosineFish qant-um f-salvetti

Full Changelog: https://github.com/onnx/tensorflow-onnx/compare/v1.13.0...v1.14.0

v1.13.0

1 year ago

What's Changed

Update CLI reference doc, adjust perameters order and add output-as-nchw by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/2028
Update the way to get opset version for running tests. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/2033
Update left tests in test_subclassing for the opset version issue. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/2034
Fix Select op with Mul inf input to nan error by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/2035
Improve several issue templates by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/2043
Upgrade the required version for flatbuffers. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/2050
Remove extract_sub_graph function from tf_optimize method. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/2051
Replace distutils.version with packaging.version namespace. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/2056
Add Support for MatMulInteger by @GregoryMorse in https://github.com/onnx/tensorflow-onnx/pull/2072

A huge thank you to our community for this release!

GregoryMorse

Full Changelog: https://github.com/onnx/tensorflow-onnx/compare/v1.12.1...v1.13.0

v1.12.1

1 year ago

Summary

Enabling opset 17 support.
Focusing on bug fix.

What's Changed

ONNX opset 17 with IR version 8 support by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/2014
Upgrade test opsets and remove deprecated numpy and version usage by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/2018
Turn on graph tf optimize grappler dependency by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/2020
Fix output node in rewrite random normal by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/2023
Skip failed RFFT tests for TF-2.4.x by @q-ycong-p in https://github.com/onnx/tensorflow-onnx/pull/2026
Add lstm sigmoid dropout test for dependency optimization by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/2027
Update CLI reference doc, adjust perameters order and add output-as-nchw @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/2028
Fix Select op with Mul inf input to nan error by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/2035

A huge thank you to our community for this release!

q-ycong-p

v.1.12.0

1 year ago

Summary

added support for python 3.10, onnx 1.12, onnxruntime 1.12, tensorflow 2.9
added --outputs_as_nchw option to transpose output to from nhwc to nchw
enhanced optimizer and exception handing
improved keras pattern and ci
misc fixes

What's Changed

Transpose optimization for Softmax and LogSoftmax (fixes #1716) by @janbernloehr in https://github.com/onnx/tensorflow-onnx/pull/1964
The from_tflite() function should accept None as default value of input_names and output_names. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/1967
Change Loop op with maximum iterations input M equals to empty string by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/1971
Update README.md by @andife in https://github.com/onnx/tensorflow-onnx/pull/1976
Update CONTRIBUTING.md by @andife in https://github.com/onnx/tensorflow-onnx/pull/1978
Update Keras related tests to support latest TF version. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/1980
Fix a test issue in keras2onnx_application_tests.yml. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/1982
L2_NORMALIZATION support for tflite by @shesung in https://github.com/onnx/tensorflow-onnx/pull/1989
Replace deprecated np.object with object by @vvolhejn in https://github.com/onnx/tensorflow-onnx/pull/1990
Implement --outputs_as_nchw option to transpose output to from nhwc to nchw by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/1979
Fix transpose split optimize attr when opset >=13 by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/1996
Skip existing const node in _parse_graph_input by @q-ycong-p in https://github.com/onnx/tensorflow-onnx/pull/2000
Add handling of HardSigmoid recurrent activation for Keras LSTM by @q-ycong-p in https://github.com/onnx/tensorflow-onnx/pull/2001
Add more tests for tf 2.9.x into CI pipelines. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/2009
Fix problem with adding more than one tf.newaxis at the same time by @southfreebird in https://github.com/onnx/tensorflow-onnx/pull/2007
Improve ZerosLike implementation and optimize for opset >= 9 by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/2003
Add newly required dependencies for latest ORT version. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/2012
Add support for Python310 and ORT 1.12 by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/1975
Increment main to 1.12, TF to 2.9 by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/2015

A huge thank you to our community for this release!

janbernloehr, andife , shesung, vvolhejn, southfreebird

Full Changelog: https://github.com/onnx/tensorflow-onnx/compare/v1.11.1...v1.12.0

v1.11.1

1 year ago

Summary

added support for onnx opset 16, upgraded default opset to 13
removed python 3.6 check from CI tests
enhanced api and added new ops
misc fixes

Changes since tf2onnx-1.10.1

Minor doc tf 2.8 change by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/1934
Use make_tensor_sequence_value_info instead of a deprecated function by @jcwchen in https://github.com/onnx/tensorflow-onnx/pull/1930
Update tensorflowjs 3.17 tests by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/1942
Bug fix for concatenating node instead of str. by @FrankD412 in https://github.com/onnx/tensorflow-onnx/pull/1933
Remove python 3.6 support, upgrade CI by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/1940
Add opset 16 support and check ci by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/1937
Update the default opset version for tf2onnx. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/1946
Update the way to check input_signature in from_function(). by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/1947
Add mapping for TF lite op TFL_BATCH_MATMUL and TFL_MATMUL. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/1950
Update protobuf version in ci by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/1951
Add TensorScatterAdd op for opset 16 by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/1949
Add a new api from_tflite to improve user experience. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/1954
Upgrade opset 16 version related doc by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/1953
Remove useless sync workflow. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/1955

Full Changelog: https://github.com/onnx/tensorflow-onnx/compare/v1.10.1...v1.11.1

A huge thank you to our community for this release!

FrankD412, jcwchen

v1.10.1

2 years ago

Summary

added support for tf-2.8
enhanced optimizer
added custom op example and load_op_libraries in doc
fixed ci to support ort version 1.11
misc fixes

Changes since tf2onnx-1.9.3

Update opset 15 version supported ops doc by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/1773
add tf-2.7 in readme by @guschmue in https://github.com/onnx/tensorflow-onnx/pull/1772
Add support for one hot encoding of 0-rank tensor by @LoicDagnas in https://github.com/onnx/tensorflow-onnx/pull/1771
Fix onnxruntime-nightly-unittest-matrix CI failed by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/1784
Handle 'Neg' nodes in TransposeOptimizer by @jan-haug in https://github.com/onnx/tensorflow-onnx/pull/1785
Fix tfjs CI failure and add tfjs convert log by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/1797
Fix misspelling by @mshr-h in https://github.com/onnx/tensorflow-onnx/pull/1800
Skip the blob failed model tests by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/1806
Add unit32 unit64 type support by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/1808
Fix keras Conv2D BiasAdd fuse by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/1796
Add Rint op conversion by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/1833
Specify the version scope of tensorflow-text. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/1843
Add used opset into opset_imports argument to create an onnx model. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/1855
feat: For QDQ models, disable constant folding and ensure the conv weights are transposed without using an explicit op by @peri044 in https://github.com/onnx/tensorflow-onnx/pull/1856
Enable tensorflow 2.8.0 in CI pipeline. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/1863
Remove --fold_const parameter by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/1861
Add load_op_libraries parameter in docs by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/1853
Force to upgrade typing-extensions to a version above 4.0.0. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/1873
Fix onnx-weekly CI job failure. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/1874
Add tf custom op conversion example by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/1878
Upgrade Windows image to windows-2019. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/1879
Rename the default branch to main by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/1880
Add onnxruntime 1.10 into normaly run. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/1887
Change package author by @garymm in https://github.com/onnx/tensorflow-onnx/pull/1885
Create ado-sync-issue.yml by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/1892
Upgrade some keras jobs to use ort 1.11.0. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/1896
Fix nightly CI job failures caused by numpy version. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/1898
Add commit value to onnx file and clean up some code by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/1897
Fix keras bidirectional merge failures by @kota-row in https://github.com/onnx/tensorflow-onnx/pull/1869
Keras nightly CI jobs update. by @fatcat-z in https://github.com/onnx/tensorflow-onnx/pull/1904
Add the absolute path condition when loads the tf custom op library by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/1909
Change custom op example to new API and add the doc by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/1883
Fix split transpose optimize axes issue by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/1918
Replace the description exporting to conversion by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/1917
Allow passing optimizers to from_keras conversion function by @shelkesagar29 in https://github.com/onnx/tensorflow-onnx/pull/1907
Add split transpose optimizer tests by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/1923

Full Changelog: https://github.com/onnx/tensorflow-onnx/compare/v1.9.3...v1.10.1

A huge thank you to our community for this release!

LoicDagnas, jan-haug, mshr-h, peri044, kota-row, shelkesagar29