Paddle2ONNX v1.2.3

What's Changed

• [ONNX][Update] Update ONNX Version to 1.13.1 by @Zheng-Bicheng in #1250
• [CI] Add test for bitwise_and op by @chris-magic in #1253
• [ONNX][Update] Update ONNX Version to 1.16.0 by @Zheng-Bicheng in #1257
• [ONNX][Update] Update ONNX Version to 1.16.0 by @Zheng-Bicheng in #1258
• [Pybind][Update] Update ONNX Version to 2.12.0 by @Zheng-Bicheng in #1259
• [Pybind][Update] Update ONNX Version to 2.12.0 by @Zheng-Bicheng in #1260
• [ONNX][Version] Update IR Version by @Zheng-Bicheng in #1261
• [Bug][Build] Update find_package PythonInterp PythonLibs by @Zheng-Bicheng in #1263

New Contributors

• @chris-magic made their first contribution in #1253

Full Changelog: v1.2.2...v1.2.3

Paddle2ONNX v1.2.2

What's Changed

• [Docs] Update Paddle2ONNX_Development_Guide.md by @Zheng-Bicheng in #1235
• [CodeStyle][Python] Fix code style by @0x45f in #1232
• [Doc][Build] Update en docs by @Zheng-Bicheng in #1249

New Contributors

• @0x45f made their first contribution in #1232

Full Changelog: v1.2.1...v1.2.2

Paddle2ONNX v1.2.1

What's Changed

• [Operator][New] Update Roll by @Zheng-Bicheng in #1228

Full Changelog: v1.2.0...v1.2.1

Paddle2ONNX v1.2.0

What's Changed

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

New Contributors

• @chunyuwei made their first contribution in #1116
• @feifei-111 made their first contribution in #1138
• @2730gf made their first contribution in #1154
• @bryce-evans made their first contribution in #1133
• @jzhang533 made their first contribution in #1210

Full Changelog: v1.0.7...v1.2.0

Paddle2ONNX v1.0.7

What's Changed

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

New Contributors

• @rainyfly made their first contribution in #1060

Full Changelog: v1.0.6...v1.0.7

Paddle2ONNX v1.0.6

What's Changed

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

New Contributors

• @felixhjh made their first contribution in #997
• @dependabot made their first contribution in #1014
• @DefTruth made their first contribution in #1015
• @miniTsl made their first contribution in #1020

Full Changelog: v1.0.5...v1.0.6

Paddle2ONNX v1.0.5

What's Changed

• set paddle domin when custom is not empty by @yeliang2258 in #959
• support adaptive_X_pool2d export to custom OP by @yeliang2258 in #957
• Add max pool with index by @yeliang2258 in #964
• Fix the scale information loss bug when export quantize model by @yeliang2258 in #958
• Fix AdaptivePool2d custom by @yeliang2258 in #977
• update version to 1.0.4 by @yeliang2258 in #981
• Fix AdaptivePool2d by @yeliang2258 in #985

Full Changelog: v1.0.3...v1.0.5

Paddle2ONNX v1.0.3

What's Changed

• Fix bug of elementwise_add operator by @yeliang2258 in #952

Full Changelog: v1.0.2...v1.0.3

Paddle2ONNX v1.0.2

What's Changed

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

Full Changelog: v1.0.1...v1.0.2

Paddle2ONNX v1.0.1

What's Changed

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

Full Changelog: v1.0.0...v1.0.1