v2.0.0a1

What's Changed

• [Cmake]Fix undefined symbol for std::filesystem under GCC8 + Linux by @Aurelius84 in #1333
• make libpaddle2onnx.so link libpaddle.so and include paddle_include direcotory by @risemeup1 in #1352
• support pir mode in paddle2onnx by @risemeup1 in #1354
• Support pir by @qzylalala in #1389
• Get input/output/attrvar interface by @risemeup1 in #1380
• Conversion of ResNet50 model under PIR by @0x3878f in #1382
• [PIR] Use paddlepaddle==3.0.0.dev20240904 in CI of test_pir by @0x3878f in #1395
• [PIR] Completion of unit testing in PIR mode by @0x3878f in #1394
• [OSPP][PIR] support mobilenet v2 by @qzylalala in #1397
• Automatic mapping of operator variable names to indices by @0x3878f in #1401
• [PIR] Adjust some interfaces in PIR && Support conversion of builtin.combine and builtin.split by @0x3878f in #1402
• 【P2O-PIR】Support op concat, split, split_with_num, transpose by @0x3878f in #1403
• [OSPP][PIR] support dropout and squeeze by @qzylalala in #1406
• [PIR]support if op by @risemeup1 in #1407
• support some ops in pir by @qzylalala in #1416
• Support some operations by @qzylalala in #1419
• 【PIR】Support while op in pir mode by @0x3878f in #1426
• Support some ops in PIR by @0x3878f in #1435
• Merge PR#1434 by @0x3878f in #1437
• support some ops by @qzylalala in #1434
• 【PIR】Improved the mechanism, added the conversion of some ops, and fixed some issues. by @0x3878f in #1444
• 【PIR】Improve some operations to support more scenarios by @0x3878f in #1450
• 【PIR】Fix issues with inference of LaTeX_OCR_rec model by @0x3878f in #1452
• 【PIR】Merge the develop branch into the test_pir branch by @0x3878f in #1455
• Fix the issue with multiclass_nms3 op by @0x3878f in #1456
• Support compilation and loading on macOS by @0x3878f in #1462
• Support compilation and loading on Windows by @0x3878f in #1465
• Add patch for compilaition on Windows by @0x3878f in #1470
• Update usage documentation by @0x3878f in #1473
• Enhance monitoring for macOS and Windows platforms using github action by @0x3878f in #1469
• Fix issues with inference of onnx models converted from paddlex by @0x3878f in #1484
• Fix the issue with determining whether operators in control flow are registered. by @0x3878f in #1485
• Support phi::DataType::UNDEFINED by @0x3878f in #1486
• Improve the mechanism by @0x3878f in #1487
• Update CI and README by @0x3878f in #1492
• Update release_linux_x86_64.yml by @risemeup1 in #1490
• Update release_linux_x86_64.yml by @risemeup1 in #1493
• Update release_linux_x86_64.yml by @risemeup1 in #1494
• Update version number by @0x3878f in #1496

New Contributors

• @qzylalala made their first contribution in #1389

Full Changelog: v1.2.6...v2.0.0a1

Paddle2ONNX v1.3.1

What's Changed

• Create clear_issues.yml by @Zheng-Bicheng in #1443
• Add MacRelease by @ccsuzzh in #1445

Full Changelog: v1.3.0...v1.3.1

Paddle2ONNX v1.3.0

What's Changed

• Fallback to old IR in paddlepaddle 3.0.0b2 by @SigureMo in #1421
• Make h1 title unique by @SigureMo in #1422
• Change LodTensorArray to DenseTensorArray by @co63oc in #1427
• Change LOD_TENSOR_ARRAY to DENSE_TENSOR_ARRAY by @co63oc in #1429
• Change LOD_TENSOR to DENSE_TENSOR by @co63oc in #1430
• 【Hackathon 7th No.48】Paddle2ONNX 添加对 Windows 平台自动发包机制的支持 -part by @ccsuzzh in #1433
• 【Hackathon 7th No.48】Paddle2ONNX 添加对 Windows 平台自动发包机制的支持 by @ccsuzzh in #1439

New Contributors

• @SigureMo made their first contribution in #1421
• @co63oc made their first contribution in #1427
• @ccsuzzh made their first contribution in #1433

Full Changelog: v1.2.11...v1.3.0

Paddle2ONNX v1.2.11

What's Changed

• 修复 PaddlePaddle 3.0 转换 PaddleOCR 模型出现错误 by @Zheng-Bicheng in #1412

Full Changelog: v1.2.10...v1.2.11

Paddle2ONNX v1.2.10

What's Changed

• 【Hackathon 7th No.47】 Paddle2ONNX 添加对 While 算子的支持 by @brisaurora in #1408
• Fixed docs bugs by @Zheng-Bicheng in #1409

New Contributors

• @brisaurora made their first contribution in #1408

Full Changelog: v1.2.9...v1.2.10

Paddle2ONNX v1.2.9

What's Changed

• Support for customOp by @0x3878f in #1376
• expose get_all_supported_ops in python by @jzhang533 in #1374
• Fixed quantized add op for rknn by @Zheng-Bicheng in #1384
• Update for rknn by @Zheng-Bicheng in #1388
• Fixed MobileNetV3 Quantized Model for RKNN by @Zheng-Bicheng in #1390
• 【Hackathon 7th No.46】 添加对返回常量的 IfElse 算子的支持 by @Asthestarsfalll in #1383

New Contributors

• @Asthestarsfalll made their first contribution in #1383

Full Changelog: v1.2.8...v1.2.9

Paddle2ONNX v1.2.8

What's Changed

• [Docs] Add onnxslim reference by @inisis in #1344
• fix assign value op bug by @risemeup1 in #1350
• Fixed matmul bug when export to rknn by @Zheng-Bicheng in #1355

New Contributors

• @inisis made their first contribution in #1344

Full Changelog: v1.2.7...v1.2.8

Paddle2ONNX v1.2.7

What's Changed

• [Cmake]Fix undefined symbol for std::filesystem under GCC8 + Linux by @Aurelius84 in #1333
• Fixed RKNN Bug and Remove Unuseful by @Zheng-Bicheng in #1343

Full Changelog: v1.2.6...v1.2.7

Paddle2ONNX v1.2.6

What's Changed

• [Operator][Update] Split the mixed activation function into independent files by @Zheng-Bicheng in #1313
• [Operator][New] Add einsum by @Zheng-Bicheng in #1314
• [setuptools]Ignore all .h/.cc et.al unrelated files packed into wheel by @Aurelius84 in #1316
• [Remove][Unuseful] Remove unuseful by @Zheng-Bicheng in #1317
• [Remove][Update]Remove custom_ops by @Zheng-Bicheng in #1319
• [Operator][New] Add repeat_interleave op by @jiuyuedeyu156 in #1318
• [Operator][Update] Update export all graph by @Zheng-Bicheng in #1320
• [Operator][New] Add Bitwise Ops by @jiuyuedeyu156 in #1321
• [Build] Rename GetMinOpset by @Zheng-Bicheng in #1322
• [Build]Update Build CI by @Zheng-Bicheng in #1323
• [Operator][New] Add conditional_block select_input by @Zheng-Bicheng in #1324
• [Build]Update command by @Zheng-Bicheng in #1327
• [Operator][Update] Fix greater than op by @jiuyuedeyu156 in #1329
• [Operator][New] Add Unfold Op by @jiuyuedeyu156 in #1325

Full Changelog: v1.2.5...v1.2.6

Paddle2ONNX v1.2.5

What's Changed

• fix fill constant op by @jiuyuedeyu156 in #1291
• paddle2onnx tech walkthrough doc by @jzhang533 in #1298
• fix conv2trans op by @jiuyuedeyu156 in #1297
• support nearest_interp op with old version (v1) by @jiuyuedeyu156 in #1300
• 【Hackathon 6th No.58】support model convert from fp32 to fp16 by @xiaoyewww in #1268
• [API]Remove depreacate API and Expose convert.dygraph2onnx by @Aurelius84 in #1305
• Fix gather op by @jiuyuedeyu156 in #1304
• Remove useless dependencies by @Zheng-Bicheng in #1306

Full Changelog: v1.2.4...v1.2.5