tensorflow-onnx | Keras Ecosystem Directory

Bot releases are hidden (Show)

tensorflow-onnx - v1.16.1 Latest Release

Published by fatcat-z 9 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

tensorflow-onnx - V1.16.0

Published by fatcat-z 10 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

tensorflow-onnx - v1.15.1

Published by fatcat-z about 1 year 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

tensorflow-onnx - v1.15.0

Published by fatcat-z about 1 year 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

tensorflow-onnx - tf2onnx-1.14.0

Published by fatcat-z over 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

tensorflow-onnx - tf2onnx-1.13.0

Published by fatcat-z almost 2 years 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

tensorflow-onnx - tf2onnx-1.12.1

Published by fatcat-z about 2 years 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

tensorflow-onnx - tf2onnx-1.12.0

Published by hwangdeyu about 2 years 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

tensorflow-onnx - tf2onnx-1.11.1

Published by hwangdeyu over 2 years 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

tensorflow-onnx - tf2onnx-1.10.1

Published by hwangdeyu over 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

tensorflow-onnx - tf2onnx-1.9.3

Published by guschmue almost 3 years ago

Summary

added support for opset-15
added support for tf-2.7
misc fixes

Changes since tf2onnx-1.9.2

remove 2.6rc0 override by @guschmue in https://github.com/onnx/tensorflow-onnx/pull/1683
Implement GRU rewriter for tf2 by @TomWildenhain-Microsoft in https://github.com/onnx/tensorflow-onnx/pull/1688
Fix bug in reverseV2 for 1D tensors by @TomWildenhain-Microsoft in https://github.com/onnx/tensorflow-onnx/pull/1691
Handle Abs in TransposeOptimizer by @mateusztabaka in https://github.com/onnx/tensorflow-onnx/pull/1699
Fix tf1 loop variable parsing for duplicated Enter nodes by @TomWildenhain-Microsoft in https://github.com/onnx/tensorflow-onnx/pull/1697
Tom/keras gru by @TomWildenhain-Microsoft in https://github.com/onnx/tensorflow-onnx/pull/1692
Implement symmetric padding mode by @TomWildenhain-Microsoft in https://github.com/onnx/tensorflow-onnx/pull/1698
Fix loop optimizer when scan output is also loop-carried-dependent by @TomWildenhain-Microsoft in https://github.com/onnx/tensorflow-onnx/pull/1701
Fix bug in reading hash tables in freeze_session by @TomWildenhain-Microsoft in https://github.com/onnx/tensorflow-onnx/pull/1709
Increase unit test timeout for windows job that often fails by @TomWildenhain-Microsoft in https://github.com/onnx/tensorflow-onnx/pull/1711
Fix RandomUniform/RandomNormal rewriters for non-const inputs by @TomWildenhain-Microsoft in https://github.com/onnx/tensorflow-onnx/pull/1710
Fix usage of custom_ops, custom_op_handlers, and custom_rewriter ags by @TomWildenhain-Microsoft in https://github.com/onnx/tensorflow-onnx/pull/1708
Fix nightly tests by @TomWildenhain-Microsoft in https://github.com/onnx/tensorflow-onnx/pull/1712
Fix nightly (explicit_pads not supported in old tf versions) by @TomWildenhain-Microsoft in https://github.com/onnx/tensorflow-onnx/pull/1717
Tom/tfjs bugfixes by @TomWildenhain-Microsoft in https://github.com/onnx/tensorflow-onnx/pull/1723
Pin onnxruntime-extensions until issue is fixed by @TomWildenhain-Microsoft in https://github.com/onnx/tensorflow-onnx/pull/1733
hardswish support for tflite by @guschmue in https://github.com/onnx/tensorflow-onnx/pull/1735
add opset-15 by @guschmue in https://github.com/onnx/tensorflow-onnx/pull/1731
Optimize einsum when node[1].is_const() by @xadupre in https://github.com/onnx/tensorflow-onnx/pull/1739
replace depreciated docker image by @guschmue in https://github.com/onnx/tensorflow-onnx/pull/1750
Add Keras LSTM support by @q-ycong-p in https://github.com/onnx/tensorflow-onnx/pull/1752
Bug-fix to skip keras LSTM test for TF2.1 by @q-ycong-p in https://github.com/onnx/tensorflow-onnx/pull/1754
tf-2.6.0 -> tf-2.6.1 to avoid build issues by @guschmue in https://github.com/onnx/tensorflow-onnx/pull/1759
Fix the Broken CI by @leimao in https://github.com/onnx/tensorflow-onnx/pull/1761
Fix TF1-Keras Dilated Conv ONNX Exported by @leimao in https://github.com/onnx/tensorflow-onnx/pull/1744
tf-2.7 by @guschmue in https://github.com/onnx/tensorflow-onnx/pull/1762
#1763: fix output shape of flatten rewriter by @guschmue in https://github.com/onnx/tensorflow-onnx/pull/1766
#1749: Fix fused_batch_norm 5d NDHWC input reshape convert by @hwangdeyu in https://github.com/onnx/tensorflow-onnx/pull/1769
[Test ONNX 1.10.2] Verify whether 1.10.2 from TestPyPI solve the crash issue by Shape-15 by @jcwchen in https://github.com/onnx/tensorflow-onnx/pull/1753

Full Changelog: https://github.com/onnx/tensorflow-onnx/compare/v1.9.2...v1.9.3

A huge thank you to our community for this release!

leimao,mateusztabaka,q-ycong-p

tensorflow-onnx - tf2onnx-1.9.2

Published by guschmue about 3 years ago

Summary

support for tf-2.6 (required some change for models >2GB and tflite)
experimental support for tensorflow.js
support for tf.signal.rfft
we added all unit tests from keras-onnx to prevent regressions when transitioning from keras-onnx to tf2onnx
misc fixes

Changes since tf2onnx-1.9.1

tf-2.6 to ci, reflect tf-2.6 in readme 1680 (guschmue)
Fix issues with tflite on tf2.6 1681 (TomWildenhain-Microsoft)
Don't copy/split transpose unless further optimization is likely 1679 (TomWildenhain-Microsoft)
Implement RaggedTensorToTensor for tensors with dense (uniform) dims 1676 (TomWildenhain-Microsoft)
Fix conversion of OneHot for dtypes unsupported by ORT 1675 (TomWildenhain-Microsoft)
Fix bug in topk casts affecting other input consumers 1674 (TomWildenhain-Microsoft)
Fix Where/Select op for bool dtypes 1673 (TomWildenhain-Microsoft)
Fix freezing of ResourceGather op 1672 (TomWildenhain-Microsoft)
Fix script about benchmarking humpback_whale model 1671 (xadupre)
Implement VALUE_ROWIDS format for ragged to tensor 1664 (TomWildenhain-Microsoft)
Improve detection of NaN values in Select op 1663 (TomWildenhain-Microsoft)
tf-2.6.0rc2 1662 (guschmue)
Fix keras nightly applications 1661 (TomWildenhain-Microsoft)
Implement RandomShuffle op 1658 (TomWildenhain-Microsoft)
Implement reduce all/any for non-const axes 1657 (TomWildenhain-Microsoft)
Improve lookup table loading for from_keras conversion 1654 (TomWildenhain-Microsoft)
Fix implementation of skip_tf_versions 1653 (TomWildenhain-Microsoft)
Fix bug in einsum optimizer reading attributes 1652 (TomWildenhain-Microsoft)
Update RFFT2D to handle 3D arrays 1649 (xadupre)
support for AsString, StringToNumber 1648 (guschmue)
Handle missing tensorflowjs package in unit tests 1647 (TomWildenhain-Microsoft)
Update script to test tflite models from tfhub 1644 (xadupre)
add provider to run_pretrained_models 1642 (guschmue)
add inception_v4 1641 (guschmue)
Skip onnx checker for new onnx version for IR3 bug 1638 (TomWildenhain-Microsoft)
[WIP] Fix tfhub scripts (enformer, ...) 1637 (xadupre)
Skip onnx checker for new onnx version for IR3 bug 1636 (TomWildenhain-Microsoft)
Move check earlier to fix loop in transpose optimizer 1631 (TomWildenhain-Microsoft)
Add PRelu to Transpose optimizer 1630 (TomWildenhain-Microsoft)
Fix TFJS conversion for old TFJS models 1629 (TomWildenhain-Microsoft)
Add conversion of _FusedDepthwiseConv2dNative and Prelu for TFJS 1628 (TomWildenhain-Microsoft)
Add variable to make it possible to test weekly onnx package 1627 (TomWildenhain-Microsoft)
Fix tfhub scripts checking discrepencies on resnet 1626 (xadupre)
Fix tfjs quantized weight parsing for fp16 quant 1625 (TomWildenhain-Microsoft)
Tests for onnx 1.9.101 1624 (TomWildenhain-Microsoft)
Add pretrained model tests for tfjs 1622 (TomWildenhain-Microsoft)
RFFT2D for TFLite 1621 (TomWildenhain-Microsoft)
Implement fused tfjs ops 1620 (TomWildenhain-Microsoft)
Tom/fused tfjs ops 1619 (TomWildenhain-Microsoft)
Trim down regular keras2onnx tests 1618 (TomWildenhain-Microsoft)
Fix Roll op for negative shifts 1616 (TomWildenhain-Microsoft)
Add TFJS conversion 1614 (TomWildenhain-Microsoft)
Work on tfjs support [WIP] 1612 (TomWildenhain-Microsoft)
Fix nightly build by moving tf2.4.1 to Python3.7 1611 (TomWildenhain-Microsoft)
Make keras2onnx tests deterministic 1608 (TomWildenhain-Microsoft)
Make keras2onnx tests use templates 1605 (TomWildenhain-Microsoft)
fix state in azuredevops 1604 (guschmue)
Move unit tests from regular to nightly 1602 (TomWildenhain-Microsoft)
Refactor tflite/tf logic out of tfonnx into tf_utils and tflite_utils 1599 (TomWildenhain-Microsoft)
Add windows keras2onnx applications tests 1598 (TomWildenhain-Microsoft)
Fix converter for rfft when fft_length < shape[1], implements fft2d 1596 (xadupre)
Refactor tfonnx.py 1595 (TomWildenhain-Microsoft)
Add script to benchmark bert and mobilenet 1594 (xadupre)
Move keras2onnx unit tests inside tests dir 1591 (TomWildenhain-Microsoft)
Tom/keras2onnx application tests 1590 (TomWildenhain-Microsoft)

A huge thank you to our contributors for this release!

tensorflow-onnx - tf2onnx-1.9.1

Published by guschmue over 3 years ago

Summary

Fixes, support for opset-14, improved keras support

Changes since 1.8.5

Implement Round for lower opsets 1589 (TomWildenhain-Microsoft)
Fix bug in CropAndResize for empty tensors 1588 (TomWildenhain-Microsoft)
Add yamnet to the list of tfhub models tested 1587 (xadupre)
fix opset typo 1585 (guschmue)
Implement rewriter for LSTM nodes in tf2 1584 (TomWildenhain-Microsoft)
add opset-14, move ci pipeline to test opset-8 -> opset-14 1583 (guschmue)
Add pure keras unit tests for Windows 1582 (TomWildenhain-Microsoft)
Add target for converting to channels last format 1581 (TomWildenhain-Microsoft)
Adds scripts to benchmark tfhub models and check discrepencies 1580 (xadupre)
Removes uses of onnxruntime when optimizing einsum 1579 (xadupre)
Add Windows keras2onnx tests 1578 (TomWildenhain-Microsoft)
Fix issue with tf1 loops with tensor array read last pattern 1577 (TomWildenhain-Microsoft)
add pure keras tests from keras2onnx 1574 (TomWildenhain-Microsoft)
Fix timeout issues on nightly 1572 (TomWildenhain-Microsoft)
Make keras2onnx tests deterministic 1571 (TomWildenhain-Microsoft)
Add warning for non-cpp protobuf 1570 (TomWildenhain-Microsoft)
Const fold Ifs and remove keras_learning_phase inputs 1569 (TomWildenhain-Microsoft)
Fix nightly CI 1568 (TomWildenhain-Microsoft)
Misc fixes for adding keras2onnx tests 1567 (TomWildenhain-Microsoft)
Fix link to tutorials/keras-resnet50.ipynb in README.md 1566 (iizukak)
Fix nightly pipeline for tf1.13 1565 (TomWildenhain-Microsoft)
Fix nightly build for tf2.1 1564 (TomWildenhain-Microsoft)
Added tests from keras2onnx 1563 (TomWildenhain-Microsoft)
Prevent tf1 loop ops from const folding 1561 (TomWildenhain-Microsoft)
Hack to support > 2GB tensors 1558 (TomWildenhain-Microsoft)
Implement conversion of set intersection, union, difference 1556 (TomWildenhain-Microsoft)
Const fold Concat 1554 (TomWildenhain-Microsoft)
Add constant folding for Split op 1553 (TomWildenhain-Microsoft)
Fix Conv groups for unknown input dims 1552 (TomWildenhain-Microsoft)
Tom/ort 1.8 1551 (TomWildenhain-Microsoft)
ort -> 1.8 1550 (guschmue)
[DON'T MERGE] check pretrained models 1548 (xadupre)
Replace onnxruntime_customops by onnxruntime_extensions 1547 (xadupre)
Fix subtle bug in ConvTranspose 1542 (TomWildenhain-Microsoft)
better way to get kwargs 1541 (guschmue)
add script to run optimizer on onnx files 1538 (guschmue)
Use structured inputs by default from CLI 1534 (TomWildenhain-Microsoft)
Remove captured inputs when using CLI 1533 (TomWildenhain-Microsoft)
Implement conversion of CTCGreedyDecoder 1530 (TomWildenhain-Microsoft)
Made from_keras work for tf1 1529 (TomWildenhain-Microsoft)
Fixed bug in transpose optimizer for mul of conv with multiple consumers 1528 (TomWildenhain-Microsoft)
Add 1 more model and update script 1527 (TomWildenhain-Microsoft)
Make rewriters use get_tensor when needed to avoid subtle bugs 1526 (TomWildenhain-Microsoft)
Fix Conv for unknown input rank 1524 (TomWildenhain-Microsoft)
Fix dtype in SegmentSum 1523 (TomWildenhain-Microsoft)
Tom/more models 1522 (TomWildenhain-Microsoft)
Convert EnsureShape to Identity 1521 (TomWildenhain-Microsoft)
More group C models 1520 (TomWildenhain-Microsoft)
Remove from future import ..., only support python 3 1519 (xadupre)
Add support for register custom ops 1518 (zerollzeng)
Fix Gemm rewriter for bias node with multiple outputs 1517 (TomWildenhain-Microsoft)
more HF models 1516 (guschmue)
Added more group A and C tfhub models 1515 (TomWildenhain-Microsoft)
fix licence classifier 1514 (guschmue)
Explicit padding for const shape ConvTranspose 1513 (calvinmccarter-at-lightmatter)
Add hash table support and frozen graph repairing for from_keras 1512 (TomWildenhain-Microsoft)

A huge thank you to our contributors for this release!

zerollzeng,calvinmccarter-at-lightmatter,iizukak

tensorflow-onnx - tf2onnx-1.8.5

Published by guschmue over 3 years ago

Summary

Fixes, support for tf-2.5, improved keras support

Changes since tf2onnx-1.8.4

Pin flatbuffers version 1511 (TomWildenhain-Microsoft)
Keep inputs of placeholder with default when removing unused nodes 1510 (TomWildenhain-Microsoft)
Add option to run_pretrained_models to save ort/tf profile 1509 (TomWildenhain-Microsoft)
add huggingface tutorial 1508 (guschmue)
Implement conversion of RaggedToVariant and RaggedFromVariant in loops 1503 (TomWildenhain-Microsoft)
Add getting started sample code 1502 (TomWildenhain-Microsoft)
Implement DivNoNan conversion 1499 (TomWildenhain-Microsoft)
Fix bug in conv rewriter if intermediate node outputs are used 1498 (TomWildenhain-Microsoft)
Add optimizer to push q and dq ops into place 1497 (TomWildenhain-Microsoft)
Fix bug in transpose optimizer where node is deleted twice 1496 (TomWildenhain-Microsoft)
Remove double reshape 1495 (TomWildenhain-Microsoft)
Unit test for from_function with non-tensor inputs in spec 1492 (TomWildenhain-Microsoft)
Filter structured inputs to only include TensorSpecs 1490 (TomWildenhain-Microsoft)
Improve keras output order detection 1489 (TomWildenhain-Microsoft)
Correct min opset of CombinedNMS to be opset 12 1488 (TomWildenhain-Microsoft)
Add hack for legacy keras 1486 (TomWildenhain-Microsoft)
Implement RandomStandardNormal conversion 1484 (TomWildenhain-Microsoft)
Fix bug with BatchMatMulV2 when it has the same input twice 1483 (TomWildenhain-Microsoft)
add huggingface/electra 1482 (guschmue)
Fix errors in tf freezing with AssignVariableOp 1481 (TomWildenhain-Microsoft)
Reorder keras outputs if possible 1480 (TomWildenhain-Microsoft)
Fix bug in while shapes 1479 (TomWildenhain-Microsoft)
Fix bug that renamed subgraph i/o twice 1478 (TomWildenhain-Microsoft)
Improve keras API 1477 (TomWildenhain-Microsoft)
Fix Slice that is Identity 1476 (TomWildenhain-Microsoft)
Fix Slice conversion for nodes with multiple outputs 1473 (TomWildenhain-Microsoft)
Make conv dilations rewriter work for dynamic pads 1470 (TomWildenhain-Microsoft)
add more huggingface models for testing 1469 (guschmue)
Match SpaceToBatch->Conv->BatchToSpace pattern more generally 1468 (TomWildenhain-Microsoft)
Skip unregistering optional inputs/outputs that are empty 1467 (TomWildenhain-Microsoft)
Handle DecodeError in tf_loader 1466 (calvinmccarter-at-lightmatter)
Add ReduceMean/ReduceMax -> GlobalAveragePool/GlobalMaxPool optimizer 1465 (TomWildenhain-Microsoft)
Improve perf of SegmentSum 1463 (TomWildenhain-Microsoft)
Tom/tf 2.5 1462 (TomWildenhain-Microsoft)
Optimize SpaceToBatchND sequence to DepthwiseConv2dNative dilations 1461 (TomWildenhain-Microsoft)
[WIP] add tf-2.5 to ci 1460 (guschmue)
Tom/batch to space crop 1459 (TomWildenhain-Microsoft)
Add support for Explicit padding 1458 (TomWildenhain-Microsoft)
Switch Einsum to Matmul when 2nd inp is constant 1457 (TomWildenhain-Microsoft)
Remove the OneHot from SparseSoftmaxCrossEntropyWithLogits for opset >= 11 1454 (TomWildenhain-Microsoft)
Tom/enable transpose any rank 1453 (TomWildenhain-Microsoft)
Check shapes and dtypes in optimizer tests 1452 (TomWildenhain-Microsoft)
Fix MaxpoolWithArgmax 1451 (TomWildenhain-Microsoft)
Enable string tests in CI pipeline 1450 (TomWildenhain-Microsoft)
Fix TensorListStack and Loop shapes 1448 (TomWildenhain-Microsoft)
Skip deepcopies for large models 1446 (TomWildenhain-Microsoft)
Fix bug in casting Log inputs 1445 (TomWildenhain-Microsoft)
respect target argument 1444 (guschmue)
Add support for range_given attr of QuantizeDequantizeV2 1442 (TomWildenhain-Microsoft)
Verify dtypes against onnx type inference 1441 (TomWildenhain-Microsoft)
Tests for onnx package 1440 (TomWildenhain-Microsoft)
Make transpose optimizer push through unsqueeze 1436 (TomWildenhain-Microsoft)
add onnx conv2d op group attr 1435 (BBuf)
Prepare to enable Transpose optimizer for transposes of any rank 1433 (TomWildenhain-Microsoft)
Fix bug in reshape_optimizer and disable silent error catching in opt… 1431 (TomWildenhain-Microsoft)
Fix random uniform rewriter for scalar shapes 1429 (TomWildenhain-Microsoft)
Make unit tests aggressively verify graph shape information 1427 (TomWildenhain-Microsoft)
Make unit tests verify graph shape information 1426 (TomWildenhain-Microsoft)
Add reshape optimizer 1425 (TomWildenhain-Microsoft)
Refactor transpose optimizer to prepare for doing transposes of any rank 1423 (TomWildenhain-Microsoft)
Completely clear raw_data field for external tensors 1422 (TomWildenhain-Microsoft)
update ssl certs 1421 (guschmue)
Add conversion for SampleDistortedBoundingBox op 1419 (TomWildenhain-Microsoft)
Conversion for AdjustHue op 1414 (TomWildenhain-Microsoft)
Make Transpose optimizer work for Tile op 1413 (TomWildenhain-Microsoft)
Remove useless Reshape ops 1411 (TomWildenhain-Microsoft)
Added more cobalt models 1410 (TomWildenhain-Microsoft)
Only load specified signatures when loading saved models in tf1 1409 (TomWildenhain-Microsoft)
Read hash tables for tf1 models 1408 (TomWildenhain-Microsoft)

A huge thank you to our contributors for this release!

BBuf, calvinmccarter-at-lightmatter

tensorflow-onnx - tf2onnx-1.8.4

Published by guschmue over 3 years ago

Summary

new, simplified python api (see here)
support for structured outputs so output names of keras model are the same as keras output names
examples for tflite and keras

Changes since tf2onnx-1.8.3

raise error if signature is missing 1406 (guschmue)
Added conversion for DenseBincount 1401 (TomWildenhain-Microsoft)
fix broken link 1397 (guschmue)
Fix raw_data to no longer have __EXTERNAL when data stored externally 1392 (TomWildenhain-Microsoft)
[WIP] Support for WordpieceTokenizer (part of Bert) 1390 (xadupre)
Added debugging advice to GitHub issues template 1389 (TomWildenhain-Microsoft)
Added TensorRT as a target and fixed Resize op conversion for TensorRT 1388 (TomWildenhain-Microsoft)
Fixed bug in transpose optimizer for Mul when rank=5 1387 (TomWildenhain-Microsoft)
Enhance BatchToSpaceND and SpaceToBatchND handlers 1386 (mateusztabaka)
Fixed bug in depthwise conv when kernel is shared between two nodes 1384 (TomWildenhain-Microsoft)
Add argmax and reduction ops to transpose optimizer 1383 (TomWildenhain-Microsoft)
Fix bug where unknown shape overwrites loop iter and cond shapes 1382 (TomWildenhain-Microsoft)
Allow tflite to cut graph if inputs/outputs are provided 1381 (TomWildenhain-Microsoft)
Added rewriter for specific pattern in a 1P model 1380 (TomWildenhain-Microsoft)
Tom/combined non max suppression 1376 (TomWildenhain-Microsoft)
Tom/tflite flexops 1374 (TomWildenhain-Microsoft)
Bug with Dequantize with no quantization params 1373 (TomWildenhain-Microsoft)
Convert tflite PRelu op 1372 (TomWildenhain-Microsoft)
Add partial support for operator FFT 1371 (xadupre)
cleanup huggingface tests 1370 (guschmue)
Fix parsing of tflite string tensors and other tflite fixes 1369 (TomWildenhain-Microsoft)
fix nightly ci - large model support needs 2.1 or better 1368 (guschmue)
Improve reliability of reading tflite models 1366 (TomWildenhain-Microsoft)
add int support for pool ops 1365 (guschmue)
fix python api issue for large models 1363 (guschmue)
add unittest for --tflite command line 1362 (guschmue)
Tom/more co models 1361 (TomWildenhain-Microsoft)
fix --tflite command line 1360 (guschmue)
fix --tflite command line 1359 (guschmue)
Added more models for Co 1358 (TomWildenhain-Microsoft)
Tests to validate ORT release 1.7.0.dev202102184 1357 (TomWildenhain-Microsoft)
Add flags for cutting/renaming IO 1355 (TomWildenhain-Microsoft)
Fix RandomUniformInt for scalar values 1354 (TomWildenhain-Microsoft)
new api 1353 (guschmue)
First step to rename IO 1352 (TomWildenhain-Microsoft)
Handle Mul broadcastable const inputs other than (1,) or (N,) in Tran… 1351 (mateusztabaka)
Full conversion of MatrixBandPart 1350 (TomWildenhain-Microsoft)

A huge thank you to our contributors for this release!

mateusztabaka

tensorflow-onnx - tf2onnx-1.8.3

Published by guschmue over 3 years ago

Summary

Final touches for tflite support, support for more tf ops, fixes

Changes since 1.8.2

Convert RandomUniformInt 1347 (TomWildenhain-Microsoft)
Implement conversions for AdjustSaturation and AdjustContrastv2 1346 (TomWildenhain-Microsoft)
Fix typo in README.md 1345 (mrry)
onnx requires all inputs for bn to be the same T 1344 (guschmue)
Implement conversions of StringUpper and StringLower 1343 (TomWildenhain-Microsoft)
Handle ReduceSum in TransposeOptimizer 1342 (mateusztabaka)
Use simple_handler for Reciprocal,Sqrt in TransposeOptimizer 1340 (mateusztabaka)
Handle Mul as Square in TransposeOptimizer 1339 (mateusztabaka)
fix tf.roll with axes=-1 1338 (guschmue)
Add models for Co semester 1336 (TomWildenhain-Microsoft)
Fix make_const for strings 1335 (TomWildenhain-Microsoft)
Implement conversion of RaggedGather 1333 (TomWildenhain-Microsoft)
Implement RaggedTensorToTensor conversion 1332 (TomWildenhain-Microsoft)
Optimize Transpose->Pad when 'pads' input is not a constant 1331 (mateusztabaka)
Optimize Transpose->Slice regardless of Slice's axes 1330 (mateusztabaka)
Add support for GatherV2 batch_dims attr 1329 (TomWildenhain-Microsoft)
Fix bug in run_pretrained_models for large models 1327 (TomWildenhain-Microsoft)
Make merge optimizer faster 1326 (TomWildenhain-Microsoft)
Added more tflite models to pretrained tests 1325 (TomWildenhain-Microsoft)
Disambiguate a unit test method 1323 (xadupre)
Tom/tflite dequantize 1322 (TomWildenhain-Microsoft)
Implement const dequantize pushing for per-axis dequantization 1321 (TomWildenhain-Microsoft)
Fix bug in depthwise conv dilations with padding=same 1320 (TomWildenhain-Microsoft)
fix StridedSlice for ellipsis+newaxis 1319 (guschmue)
Implement non-standard nms for tflite 1318 (TomWildenhain-Microsoft)
Added optimization for dequantized constant folding 1316 (TomWildenhain-Microsoft)
Make TransposeOptimizer to optimize 5D transposes 1315 (mateusztabaka)
Extend transpose optimizer for quantize and dequantize 1314 (TomWildenhain-Microsoft)
Add tflite support to run_pretrained_models.py 1313 (TomWildenhain-Microsoft)
Fixed bug in shapes for tfltie postprocess 1312 (TomWildenhain-Microsoft)
Make tflite consider [] to designate unknown rank 1311 (TomWildenhain-Microsoft)
Tom/sentencetokenize 1309 (TomWildenhain-Microsoft)
Add conversion for SentencepieceTokenizeOp 1308 (TomWildenhain-Microsoft)
Fix common bug where node inputs are assumed to come from output[0] 1307 (TomWildenhain-Microsoft)
Fix bug in raggedToSparse and add casts to Unique for non-int64 ints 1306 (TomWildenhain-Microsoft)

A huge thank you to our contributors for this release!

mateusztabaka

tensorflow-onnx - tf2onnx-1.8.2

Published by guschmue over 3 years ago

Summary

Fixes, initial support for tflite->onnx conversion

Changes since 1.8.1

test_unsorted_segment_ops needs tf-2.3 or better 1305 (guschmue)
Tests for tflite postprocess 1302 (TomWildenhain-Microsoft)
Allow -1 to indicate unknown dimensions for shape override 1300 (TomWildenhain-Microsoft)
Support for bicubic resize 1299 (TomWildenhain-Microsoft)
Enabled tflite support and tests 1297 (TomWildenhain-Microsoft)
use test.pypi.org via ONNX_TEST env variable 1296 (guschmue)
Added conversion of TFLite_Detection_PostProcess 1293 (TomWildenhain-Microsoft)
Fix 2 bugs to avoid extranious warnings 1292 (TomWildenhain-Microsoft)
trim ci pipeline 1291 (guschmue)
Optimization for tflite loops 1289 (TomWildenhain-Microsoft)
transpose optimizer wrongly removes a transpose 1288 (guschmue)
Added support for mutable hash tables and fixed bug in making string … 1282 (TomWildenhain-Microsoft)
Added code for parsing tflite customops 1281 (TomWildenhain-Microsoft)
Fixed bug in tflite relu6 1280 (TomWildenhain-Microsoft)
Implemented conversion of RaggedToSparse 1276 (TomWildenhain-Microsoft)
Minor bugfixes to support tflite 1275 (TomWildenhain-Microsoft)
Moved tflite folder to tf2onnx 1273 ([TomWildenhain-Microsoft](ht
tps://github.com/TomWildenhain-Microsoft))
[LICENSE] remove leftover MIT licenses 1272 (szha)
[LICENSE] add ALv2 licenses 1271 (szha)
Added handlers for tflite 1270 (TomWildenhain-Microsoft)
updated supported ops doc 1269 (guschmue)
Added support for PlaceholderWithDefault ops with computed defaults 1268 (TomWildenhain-Microsoft)
Added @tfl_op decorator to handlers 1267 (TomWildenhain-Microsoft)

A huge thank you to our contributors for this release!

szha

tensorflow-onnx - tf2onnx-1.8.1

Published by guschmue almost 4 years ago

Summary

opset-13 support, bug fixes

Changes since tf2onnx-1.7.2

Created tflite utils for parsing tflite graphs 1265 (TomWildenhain-Microsoft)
Fix issue with LSTM state variables initialization 1264 (buddhapuneeth)
Fixed bug in reading table info from saved models 1263 (TomWildenhain-Microsoft)
Reenabled placeholderwithdefault tests 1262 (TomWildenhain-Microsoft)
Fixed bugs in squeeze/unsqueeze for string ops 1261 (TomWildenhain-Microsoft)
Added support for converting RaggedRange 1256 (TomWildenhain-Microsoft)
Fixed bug in Transpose optimizer mul handler for consts with multiple… 1255 (TomWildenhain-Microsoft)
Added a workaround for the TF bug that tensor.numpy() doesn't always … 1250 (TomWildenhain-Microsoft)
Fixed conversion of Batch Norm when training=true 1249 (TomWildenhain-Microsoft)
fix sparse_softmax_cross_entropy bug when logits is negative infinity 1248 (liangkaihuan)
Added flatbuffer parse code for tflite 1247 (TomWildenhain-Microsoft)
Simplified TA get item to avoid shape bug 1244 (TomWildenhain-Microsoft)
Set UT to test opset 13 1243 (TomWildenhain-Microsoft)
More bug fixes for opset 13 support 1241 (TomWildenhain-Microsoft)
add support dynamic max_iterations in loop 1240 (wangqiaoshi)
Add support for multiple scan outputs 1238 (TomWildenhain-Microsoft)
Bug fixes for opset 13 support 1237 (TomWildenhain-Microsoft)
Fixed resize op for opset 13 1236 (TomWildenhain-Microsoft)
Fix quant and dequant for opset 13 1235 (TomWildenhain-Microsoft)
Made unittests require optimizers to not fail 1234 (TomWildenhain-Microsoft)
Update split op for opset13 and add test cases 1233 (TomWildenhain-Microsoft)
fix for tf-2.4, ort does not support all topk dtypes 1232 (guschmue)
support for tf-2.4 1231 (guschmue)
Added recursive search for table info of saved models 1228 (TomWildenhain-Microsoft)
more complete nms support, fix efficientdet tutorial 1225 (guschmue)
Fix bug in reading hash table initializers for tables with names othe… 1223 (TomWildenhain-Microsoft)
[WIP] Support operators Squeeze/Unsqueeze for opset 13 (v2) 1221 (xadupre)
Updated ExpandDims handler for opset 13 unsqueeze 1218 (TomWildenhain-Microsoft)
[WIP] Support operators Squeeze/Unsqueeze for opset 13 1217 (xadupre)
Tom/squeeze unsqueeze 1216 (TomWildenhain-Microsoft)
Improve messaging for RandomUniform 1215 (TomWildenhain-Microsoft)
Created GraphBuilder method for ReduceSum to prepare for opset 13 1213 (TomWildenhain-Microsoft)
[WIP] Opset 13 support 1211 (TomWildenhain-Microsoft)
Added covid-twitter-bert to perf testing script 1209 (TomWildenhain-Microsoft)
Added universal-sentence-encoder-qa to perf testing script 1208 (TomWildenhain-Microsoft)
Allow specifying domain of custom ops 1206 (TomWildenhain-Microsoft)
Improved perf of SegmentSum 1205 (TomWildenhain-Microsoft)
Added conversion for SparseReshape 1204 (TomWildenhain-Microsoft)
Added conversion for Bincount op 1202 (TomWildenhain-Microsoft)
Don't fold constants if the result is way larger than inputs 1201 (TomWildenhain-Microsoft)
Avoid using Where op in Select and SelectV2 conversions 1199 (TomWildenhain-Microsoft)
Added two universal sentence encoder models to perf testing list 1198 (TomWildenhain-Microsoft)
Changed tf_utils pass1 to mostly use attribute type not name to determine how to convert. 1196 (TomWildenhain-Microsoft)
Added WikiWords models to perf testing yaml 1195 (TomWildenhain-Microsoft)
Added NNLM models to perf testing yaml 1194 (TomWildenhain-Microsoft)
Updated run_pretrained_models script to support hash tables and string ops 1193 (TomWildenhain-Microsoft)
Implemented conversion for StringEqual 1192 (TomWildenhain-Microsoft)
Implemented conversions for all segment ops 1191 (TomWildenhain-Microsoft)
Remove references to non-variable resources from graph before freezing 1190 (TomWildenhain-Microsoft)
Added optimization for TableLookup when key is const 1189 (TomWildenhain-Microsoft)
Allow Reduce ops to have negative axis if opset >= 11 1188 (TomWildenhain-Microsoft)
Added conversions for SparseSegment ops 1187 (TomWildenhain-Microsoft)
Added conversions for string ops using contrib ops 1185 (TomWildenhain-Microsoft)
Allow conversion of Select op when condition has rank 1 and input has… 1184 (TomWildenhain-Microsoft)
Added conversion for LookupTableSizeV2 1183 (TomWildenhain-Microsoft)
Added conversion for Roll op 1182 (TomWildenhain-Microsoft)
Implemented conversion of SparseFillEmptyRows 1180 (TomWildenhain-Microsoft)
Fixed string parsing and added tests 1179 (TomWildenhain-Microsoft)
dont look at fold_constant 1178 (guschmue)
Improved BatchNorm errors when training is true or shape is unknown 1176 (TomWildenhain-Microsoft)
Fixed 2nd output of Unique 1174 (TomWildenhain-Microsoft)
[WIP] test ci 1173 (guschmue)
Added fixes for newly failing test_segment_sum_unknown_rank and test_… 1172 (TomWildenhain-Microsoft)
modify annotation in process_tf_graph function 1171 (zzpmiracle)
Implemented SegmentSum for unknown rank 1170 (TomWildenhain-Microsoft)
Updated DynamicStitch to support tensors of higher rank 1169 (TomWildenhain-Microsoft)
Added conversion for SparseToDense 1168 (TomWildenhain-Microsoft)
[WIP] prep for tf-2.4 1167 (guschmue)
fix shape inference for onnx-1.8 1165 (guschmue)
Fix parsing of Sparse ops 1164 (TomWildenhain-Microsoft)
fixes for shape inference in onnx-1.8 1163 (guschmue)
Added conversions for Segment ops 1161 (TomWildenhain-Microsoft)
Implemented conversion of DynamicStitch 1160 (TomWildenhain-Microsoft)
Added support for DynamicPartition 1159 (TomWildenhain-Microsoft)
Improved HashTable support 1156 (TomWildenhain-Microsoft)
Update pipeline run_pretrained_models to use tf 2.3.0 1155 (TomWildenhain-Microsoft)
Fixed regression for SelectV2 when shape is unknown 1154 (TomWildenhain-Microsoft)
Added output_frozen_graph flag and marked --fold_const as deprecated 1151 (TomWildenhain-Microsoft)
Fixed bug with ConvTranspose 1150 (TomWildenhain-Microsoft)
Enabled test_hashtable_lookup for tf2 1149 (TomWildenhain-Microsoft)
Set aggressive inlining to true 1148 (TomWildenhain-Microsoft)
Improve ConvTranspose shape inference to work with unknown batch dim 1147 (TomWildenhain-Microsoft)
Fixed half_pixel_centers for resize_nearest_neighbor 1146 (TomWildenhain-Microsoft)
Added constant folding for Slice nodes following a shape node of know… 1145 (TomWildenhain-Microsoft)
Resize align corners attribute 1144 (NikolasMarkou)
Fixed bug in some rewriters where ops list aliased to g._nodes 1143 (TomWildenhain-Microsoft)
Added support for TensorScatterUpdate 1142 (TomWildenhain-Microsoft)
Improved detection of conversion errors due to large models 1141 (TomWildenhain-Microsoft)
Added more attributes to tf ignored list 1140 (TomWildenhain-Microsoft)
Fixed bug with order of args when make large models 1139 (TomWildenhain-Microsoft)
more tests 1138 (guschmue)
Remove special characters from model zip for large model format 1137 (TomWildenhain-Microsoft)
add more tests 1136 (guschmue)
Added pref test model yaml file 1133 (TomWildenhain-Microsoft)
Added new input_get functions to run_pretrained_models.py 1128 (TomWildenhain-Microsoft)

A huge thank you to our contributors for this release!

liangkaihuan, zzpmiracle, NikolasMarkou, buddhapuneeth, wangqiaoshi

tensorflow-onnx - tf2onnx-1.7.2

Published by guschmue almost 4 years ago

Summary

Fixes and changes to how we use onnx shape inference needed for onnx-1.8

Changes since v1.7.1

fix shape inference for onnx-1.8 1165 (guschmue)
Fix parsing of Sparse ops 1164 (TomWildenhain-Microsoft)
Added conversions for Segment ops 1161 (TomWildenhain-Microsoft)
Implemented conversion of DynamicStitch 1160 (TomWildenhain-Microsoft)
Added support for DynamicPartition 1159 (TomWildenhain-Microsoft)
Update pipeline run_pretrained_models to use tf 2.3.0 1155 (TomWildenhain-Microsoft)
Fixed regression for SelectV2 when shape is unknown 1154 (TomWildenhain-Microsoft)
Added output_frozen_graph flag and marked --fold_const as deprecated 1151 (TomWildenhain-Microsoft)
Fixed bug with ConvTranspose 1150 (TomWildenhain-Microsoft)
Enabled test_hashtable_lookup for tf2 1149 (TomWildenhain-Microsoft)
Set aggressive inlining to true 1148 (TomWildenhain-Microsoft)
Improve ConvTranspose shape inference to work with unknown batch dim 1147 (TomWildenhain-Microsoft)
Fixed half_pixel_centers for resize_nearest_neighbor 1146 (TomWildenhain-Microsoft)
Added constant folding for Slice nodes following a shape node of know… 1145 (TomWildenhain-Microsoft)
Resize align corners attribute 1144 (NikolasMarkou)
Fixed bug in some rewriters where ops list aliased to g._nodes 1143 (TomWildenhain-Microsoft)
Added support for TensorScatterUpdate 1142 (TomWildenhain-Microsoft)
Improved detection of conversion errors due to large models 1141 (TomWildenhain-Microsoft)
Added more attributes to tf ignored list 1140 (TomWildenhain-Microsoft)
Fixed bug with order of args when make large models 1139 (TomWildenhain-Microsoft)
more tests 1138 (guschmue)
Remove special characters from model zip for large model format 1137 (TomWildenhain-Microsoft)
add more tests 1136 (guschmue)
Added perf test model yaml file 1133 (TomWildenhain-Microsoft)
Added new input_get functions to run_pretrained_models.py 1128 (TomWildenhain-Microsoft)
Don't add identity before output if output is also a graph input 1127 (TomWildenhain-Microsoft)

A huge thank you to our contributors for this release!

NikolasMarkou

tensorflow-onnx - tf2onnx-1.7.1

Published by guschmue about 4 years ago

Summary

large model support, conversion performance improvements and fixes.

Changes since v1.6.3

Fixed error in computing shape of unpack op 1125 (TomWildenhain-Microsoft)
Moves unused class attribute to function local variable. 1124 (xadupre)
Added cast to float before log 1123 (TomWildenhain-Microsoft)
cast log to float 1122 (TomWildenhain-Microsoft)
Add cast after Size if expected type is not int64 1119 (TomWildenhain-Microsoft)
Fixed bug in run_pretrained_models.py for models with subgraphs 1118 (TomWildenhain-Microsoft)
Fixes #595, support operator InvertPermutation 1117 (xadupre)
Better error message when it fails due to RFFT 1116 (xadupre)
Add support for operators RFFT, ComplexAbs 1114 (xadupre)
Rescaled get_beach and added get_zeros_int32 and get_zeros_int64 1113 (TomWildenhain-Microsoft)
Fix --concrete_func for multiple inputs in signature 1110 (TomWildenhain-Microsoft)
Added support for converting NonMaxSuppression in opset 10 with dynam… 1109 (TomWildenhain-Microsoft)
Update run_pretrained_models.py to support large models 1107 (TomWildenhain-Microsoft)
fix bn fuse for fp16 1106 (guschmue)
Added constant folding using TF for large models 1105 (TomWildenhain-Microsoft)
Add an end2end example with tf.keras 1103 (xadupre)
Hash tensor tensor values in merge_duplicated_nodes to increase conversion speed 1102 (TomWildenhain-Microsoft)
Made einsum op convert equation string to lower case 1099 (TomWildenhain-Microsoft)
Fix issue with model esrgan-tf2_1 1098 (xadupre)
reflect support for python 3.8, tf-2.3 1097 (guschmue)
Added f to the list of TF function attributes 1094 (TomWildenhain-Microsoft)
Added support for converting large models 1090 (TomWildenhain-Microsoft)
Add cast to same type before equal operator 1089 (bedapisl)
Added graph methods for saving using the external data storage format 1088 (TomWildenhain-Microsoft)
Created compress_graph_def function 1087 (TomWildenhain-Microsoft)
Rename coverter into converter 1086 (xadupre)
Fix the missing axis when LogSoftmax is in graph 1084 (peterjc123)
Add functionality for QDQ per channel 1081 (peri044)
Add a script to profile the conversion of a model 1077 (xadupre)
Feature: Added optimization step to remove upsample layers with all ones in scale 1074 (NikolasMarkou)
#1070 replacing Reshape and Transpose operators to the kernel that are invalid in tensorrt with just a reshaped tensor 1071 (NikolasMarkou)
Fix/gemm rewriter bias add 1069 (phager90)
fix a NCHW pb converting bug in pad_rewriter 1063 (charlieguo0307)
Faster insertion of operator cast, missing replacement in #1059 1061 (xadupre)
Faster insertion of operator cast 1059 (xadupre)
Changes type instead of name in operator clip 1058 (xadupre)
Replace sys.maxsize by np.iinfo(np.int64).max 1057 (xadupre)
Use the same syntax to replace an node input 1056 (xadupre)
Removes unnecessary print 1055 (xadupre)
Perf gain in tf_utils.py, more efficient error messages, faster comparisons 1054 (xadupre)
Minor perf gain in graph_matcher.py 1053 (xadupre)- Added brackets to fix error in QueueDequeueUpToV2 1050 (TomWildenhain-Microsoft)
[WIP] Improve performance by adding forward indexes, second version. 1049 (xadupre)
Implemented QueueDequeueUpToV2 1047 (TomWildenhain-Microsoft)
Fixed bug in padding calculation for padding='SAME' when dilations>1 1046 (TomWildenhain-Microsoft)
Conv3DBackpropInputV2 1045 (ralovich)
Adding Constant Folding for Reshape Nodes to Optimizer 1042 (phager90)
Added support for Conv3DBackpropInputV2 1041 (TomWildenhain-Microsoft)
[WIP] Improve performance by adding forward indexes. 1035 (xadupre)
fix label offset in tutorial 1026 (guschmue)
[WIP] Improve performance by adding identity nodes 1023 (xadupre)
enable tf-2.3 in ci pipeline 1022 (guschmue)