Paddle2ONNX Versions Save

ONNX Model Exporter for PaddlePaddle

v1.2.1

3 weeks ago

What's Changed

[Operator][New] Update Roll by @Zheng-Bicheng in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1228

Full Changelog: https://github.com/PaddlePaddle/Paddle2ONNX/compare/v1.2.0...v1.2.1

v1.2.0

1 month ago

What's Changed

[docs] update README.md by @chunyuwei in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1116
Use FP32 Pow when convert FP32 model to FP16 by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1122
fix dygraph2onnx bug by @feifei-111 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1138
layernorm support onnx export in opset17 by @2730gf in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1154
refresh paddle2onnx version number 1.1.0 by @Zeref996 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1155
[Bug][CI] Add support for PaddlePaddle2.6 by @Zheng-Bicheng in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1178
[Bug][CI] Remove legacy dependencies and Adapt to the latest numpy package by @Zheng-Bicheng in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1181
[Bug][CI] Fix the bug where elementwise floordiv only performs div without floor by @Zheng-Bicheng in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1188
[Docs] Fix docs and breaking var name typos by @bryce-evans in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1133
[Bug][CI] Fix the error caused by releu6 no longer having a threshold parameter by @Zheng-Bicheng in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1189
[Bug][CI] Fix the error caused by swish no longer having a beta parameter by @Zheng-Bicheng in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1190
[Bug][CI] Temporarily remove quantitative CI and Fixed bug in reduce_max by @Zheng-Bicheng in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1191
[Bug][CI] Rewrite useful tests and delete useless tests by @Zheng-Bicheng in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1192
[Bug][CI] Update ONNXRuntime version and Fixed bug in test_MaxPool2D by @Zheng-Bicheng in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1193
[Remove][legacy] Delete legacy by @Zheng-Bicheng in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1196
[Operator][Update] Update swish for paddlepaddle2.5 by @Zheng-Bicheng in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1197
[Operator][Update] Update relu6 for paddlepaddle2.5 by @Zheng-Bicheng in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1198
[Remove][Command] Remove enable_dev_version by @Zheng-Bicheng in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1199
[Remove][legacy] remove legacy by @Zheng-Bicheng in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1201
[Remove][Command] Remove output_names and input_shape_dict by @Zheng-Bicheng in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1200
[Bug][CI]Fixed nn upsample by @Zheng-Bicheng in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1202
[Utils] prune_paddle_model.py support input_names by @Zheng-Bicheng in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1209
[CI] Use github action to build paddle2onnx, will merge, so the workflow can be triggered by @jzhang533 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1210
[CI] debugging .github/workflows/build.yml by @jzhang533 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1211
[CI] build paddle2onnx in .github/workflows/build.yml by @jzhang533 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1212
[Utils] infer_paddle_model_shape.py support paddlepaddle2.6 by @Zheng-Bicheng in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1214
[Docs] Update README.md by @Zheng-Bicheng in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1215
[Docs] Fix typo by @jzhang533 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1216
[Build][Update] Update the project's build process to pyproject. by @Zheng-Bicheng in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1221
[Docs] Update compile.md by @Zheng-Bicheng in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1222
[Docs] Update docs by @Zheng-Bicheng in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1223
[Utils] Remove Unuseful Tools by @Zheng-Bicheng in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1226
[Utils] Remove Unuseful Tools by @Zheng-Bicheng in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1227
[CI][Update] Update CI Actions for releasing a brand new release package. by @Zheng-Bicheng in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1219

New Contributors

@chunyuwei made their first contribution in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1116
@feifei-111 made their first contribution in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1138
@2730gf made their first contribution in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1154
@bryce-evans made their first contribution in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1133
@jzhang533 made their first contribution in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1210

Full Changelog: https://github.com/PaddlePaddle/Paddle2ONNX/compare/v1.0.7...v1.2.0

v1.0.7

11 months ago

What's Changed

Add Paddle2ONNX for VisualDL by @rainyfly in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1060
Support export custom ops by user by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1058
Add atan2 op by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1057
Fix pool2d kernel size compute bug and 0D tensor support for argmin、argmax and size OPs by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1061
[0D tensor] Add 0D tensor input support for 52 element-wise unary ops by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1066
[Bug Fix] Fix RKNN backend when convert quantized model by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1071
[Quantize] Add MatMul OP support in RKNN backend by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1073
[0D Tensor] Add 0D tensor input for 43 elementwise-binary and other ops by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1067
[New operator] Add pad op by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1069
[0D tensor] Add 0D tensor output support for gaussian_random and fill_constant by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1068
[Quantize] Fix quantize model export bug by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1081
[Doc] update Paddle2ONNX_Development_Guide.md for CXX by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1082
[proto] update p2o_paddle.proto by @DefTruth in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1097

New Contributors

@rainyfly made their first contribution in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1060

Full Changelog: https://github.com/PaddlePaddle/Paddle2ONNX/compare/v1.0.6...v1.0.7

v1.0.6

1 year ago

What's Changed

Fix assert in quantize helper by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1003
Add softmax_with_cross_entropy operator by @felixhjh in https://github.com/PaddlePaddle/Paddle2ONNX/pull/997
Remove Fluid APIs in tests to fix CI by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1004
Remove shape check for multiclass nms by @jiangjiajun in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1002
Bump onnx from 1.8.0 to 1.13.0 in /tests by @dependabot in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1014
[staticlib] support p2o staticlib in linux and osx by @DefTruth in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1015
Support softmax_with_cross_entropy operator with soft_label by @felixhjh in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1012
Update quantize.md by @miniTsl in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1020
Fix sampling_ratio attr type in roi_align op by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1025
Add index_sample OP by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1023
Fix bug in gather op by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1031
Add mv op by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1047
Add convert fp32 ONNX model to fp16 ONNX func by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1021
Fix tensorrt quantize bugs by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1054

New Contributors

@felixhjh made their first contribution in https://github.com/PaddlePaddle/Paddle2ONNX/pull/997
@dependabot made their first contribution in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1014
@DefTruth made their first contribution in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1015
@miniTsl made their first contribution in https://github.com/PaddlePaddle/Paddle2ONNX/pull/1020

Full Changelog: https://github.com/PaddlePaddle/Paddle2ONNX/compare/v1.0.5...v1.0.6

v1.0.5

1 year ago

What's Changed

set paddle domin when custom is not empty by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/959
support adaptive_X_pool2d export to custom OP by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/957
Add max pool with index by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/964
Fix the scale information loss bug when export quantize model by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/958
Fix AdaptivePool2d custom by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/977
update version to 1.0.4 by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/981
Fix AdaptivePool2d by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/985

Full Changelog: https://github.com/PaddlePaddle/Paddle2ONNX/compare/v1.0.3...v1.0.5

v1.0.3

1 year ago

What's Changed

Fix bug of elementwise_add operator by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/952

Full Changelog: https://github.com/PaddlePaddle/Paddle2ONNX/compare/v1.0.2...v1.0.3

v1.0.2

1 year ago

What's Changed

Add tensor attr for pool_adaptive_avg by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/915
Update doc and add tools for model modify by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/929
Fix bug in OnnxReader by @jiangjiajun in https://github.com/PaddlePaddle/Paddle2ONNX/pull/933
Export dynamic dimension with string by @jiangjiajun in https://github.com/PaddlePaddle/Paddle2ONNX/pull/931
Enable BatchedNMS Plugin in TensorRT by @jiangjiajun in https://github.com/PaddlePaddle/Paddle2ONNX/pull/934
Add merge_params tool for Paddle model by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/945
Fix bug for reshape operator by @jiangjiajun in https://github.com/PaddlePaddle/Paddle2ONNX/pull/948
External data support when model is bigger than 2G by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/942

Full Changelog: https://github.com/PaddlePaddle/Paddle2ONNX/compare/v1.0.1...v1.0.2

v1.0.1

1 year ago

What's Changed

Update paddle reader to support get information of inputs and outputs by @jiangjiajun in https://github.com/PaddlePaddle/Paddle2ONNX/pull/892
Add pixel_shuffle op support by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/895
Add unique op support by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/903
Add tensor attr support for Squeeze by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/910
Add tensor attr support for cumsum by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/913
Add tensor attr support for argmin and argmax by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/912
Support tensor attr for eye by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/908
Add tensor attr support for reduce ops by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/909
Add tensor attr support for dropout by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/911
Add test for conv2d_transpose by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/916
The quantization cache file read by TensorRT is returned by string by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/906

Full Changelog: https://github.com/PaddlePaddle/Paddle2ONNX/compare/v1.0.0...v1.0.1

v1.0.0

1 year ago

What's Changed

Fix quantize OP Matmul and Relu by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/788
Add partial_sum and partial_concat support by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/791
Add temporal_shift support by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/792
Fix multiclass_nms by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/794
Keep input/output same order with paddle by @jiangjiajun in https://github.com/PaddlePaddle/Paddle2ONNX/pull/789
Fix gather aixs bug of nms by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/795
Add leaky_relu support in quantize model by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/797
Add scatter_nd_add op support by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/800
Add conv3d and pool3d support, fix a bug in tile by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/798
Add quantize model related doc by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/801
Add ONNX util function by @jiangjiajun in https://github.com/PaddlePaddle/Paddle2ONNX/pull/806
Add Paddle2Caffe under Contrib by @ltcs11 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/799
Add Paddle model util function by @jiangjiajun in https://github.com/PaddlePaddle/Paddle2ONNX/pull/808
Support operator export as custom op by @jiangjiajun in https://github.com/PaddlePaddle/Paddle2ONNX/pull/814
Enhance OnnxReader by @jiangjiajun in https://github.com/PaddlePaddle/Paddle2ONNX/pull/816
Fix bug in PaddleReader by @jiangjiajun in https://github.com/PaddlePaddle/Paddle2ONNX/pull/817
Support remove multiclass_nms by @jiangjiajun in https://github.com/PaddlePaddle/Paddle2ONNX/pull/821
Add deploy backend option and TRT backend support for quantize model by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/819
Add bilinear_interp OP by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/829
Fix quantize model export for TRT backend by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/830
Add take_along _axis OP support by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/831
Support read parameters of nms operator by @jiangjiajun in https://github.com/PaddlePaddle/Paddle2ONNX/pull/834
Modify install directory on windows by @jiangjiajun in https://github.com/PaddlePaddle/Paddle2ONNX/pull/835
Add clip extra in test by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/822
Set enable_dev_version to True by default by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/836
Fix windows build bug by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/839
Fix ONNX reader while initializer exists by @jiangjiajun in https://github.com/PaddlePaddle/Paddle2ONNX/pull/845
[OpAttr]Support to parse Attribute with type(Variable) in 2ONNX by @Aurelius84 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/854
Update document by @jiangjiajun in https://github.com/PaddlePaddle/Paddle2ONNX/pull/842
separate setup for Paddle2Caffe by @ltcs11 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/843
Add linspace support by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/860
Add group_norm support by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/863
Add top_k OP support by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/861
Support new ir of paddle while by @jiangjiajun in https://github.com/PaddlePaddle/Paddle2ONNX/pull/865
Make roi of interploate be empty by @jiangjiajun in https://github.com/PaddlePaddle/Paddle2ONNX/pull/867
Replace Explicit Quantization to Implicit Quantization for TensorRT backend by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/856
Update compile.md to support previous version ONNXRuntime by @jiangjiajun in https://github.com/PaddlePaddle/Paddle2ONNX/pull/873
Update compile.md by @jiangjiajun in https://github.com/PaddlePaddle/Paddle2ONNX/pull/874
Add index_select support by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/876
Rename paddle2caffe by @jiangjiajun in https://github.com/PaddlePaddle/Paddle2ONNX/pull/886
Enhance ONNX reader to get input/output information from ONNX model by @jiangjiajun in https://github.com/PaddlePaddle/Paddle2ONNX/pull/885
Add RKNN deploy backend support for quantized model by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/887
Add grid_sampler op convert support by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/889

New Contributors

@ltcs11 made their first contribution in https://github.com/PaddlePaddle/Paddle2ONNX/pull/799
@Aurelius84 made their first contribution in https://github.com/PaddlePaddle/Paddle2ONNX/pull/854

Full Changelog: https://github.com/PaddlePaddle/Paddle2ONNX/compare/v0.9.9...v1.0.0

v1.0.0rc4

1 year ago

What's Changed

Support read parameters of nms operator by @jiangjiajun in https://github.com/PaddlePaddle/Paddle2ONNX/pull/834
Modify install directory on windows by @jiangjiajun in https://github.com/PaddlePaddle/Paddle2ONNX/pull/835
Add clip extra in test by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/822
Set enable_dev_version to True by default by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/836
Fix windows build bug by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/839
Fix onnx reader while initializer exists by @jiangjiajun in https://github.com/PaddlePaddle/Paddle2ONNX/pull/845
[OpAttr]Support to parse Attribute with type(Variable) in 2ONNX by @Aurelius84 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/854
Update document by @jiangjiajun in https://github.com/PaddlePaddle/Paddle2ONNX/pull/842
Separate setup for Paddle2Caffe by @ltcs11 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/843
Fix test by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/864
Add linspace support by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/860
Add group_norm support by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/863
Add top_k OP support by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/861
Support new ir of paddle while by @jiangjiajun in https://github.com/PaddlePaddle/Paddle2ONNX/pull/865
Make roi of interploate be empty by @jiangjiajun in https://github.com/PaddlePaddle/Paddle2ONNX/pull/867
Replace Explicit Quantization to Implicit Quantization for TensorRT backend by @yeliang2258 in https://github.com/PaddlePaddle/Paddle2ONNX/pull/856

New Contributors

@Aurelius84 made their first contribution in https://github.com/PaddlePaddle/Paddle2ONNX/pull/854

Full Changelog: https://github.com/PaddlePaddle/Paddle2ONNX/compare/v1.0.0rc2...v1.0.0rc4