MMDeploy Release V1.0.0rc2

What's Changed

🚀 Features

• [Feature] CodeCamp #101: Support MMDetection 3.x RTMDet model deployment on RV1126 by @Qingrenn in #1551
• [Feature] Support more MMOCR models: DBNet++, TextSnake, ABINet, MRCNN by @AllentDan in #1534
• [Feature] Support RTMDet-Ins. by @RangiLyu in #1662
• [Feature] Add coco whole-body skeleton (#1736) by @lzhangzz in #1742

💥 Improvements

• [Enhancement] [cherry-pick: #1688] remove MMDEPLOY_BUILD_SDK_CXX_API option by @lvhan028 in #1692
• [Enhancement] Add 320x320 static config for tensorrt by @hanrui1sensetime in #1689
• [Enhancement] Add mmyolo CI on mmdeploy by @hanrui1sensetime in #1650
• [Enhancement] enable TRT parse ONNX model from file by @AllentDan in #1734
• [Enhancement] check in tensorrt-fp16 deployment config for simcc by @lvhan028 in #1741

🐞 Bug fixes

• [Fix] Fix build error on cuda10.2 platform by @irexyc in #1597
• [Fix] fix log info typo of check env by @AllentDan in #1613
• [Fix] Fix typo in LetterResize transform by @lzhangzz in #1618
• [Fix] fix no test_step error in TorchWrapper by @AllentDan in #1600
• [Fix] Fixed calling miniconda script in Dockerfile by @nghiaho12 in #1629
• [Fix] fix numba numpy version not compatiable in circileci by @RunningLeon in #1611
• [Fix] Fix the performance test for RKNN by @AllentDan in #1583
• [Fix] Substitute SyncBN with BN for mmpose by @hanrui1sensetime in #1631
• [Fix] fix headless device visualize by @grimoire in #1630
• [Fix] Fix preprocess_model_config for CIFAR dataset by @hanrui1sensetime in #1659
• [Fix] fix rknn output index error in SDK by @AllentDan in #1682
• [Fix] fix lint by @triple-Mu in #1680
• [Fix] fix coreml for branch 1.x by @grimoire in #1669
• [Fix] fix mmpose regression codec sdk export by @irexyc in #1684
• [Fix] fix rknn quantization pipeline by @AllentDan in #1636
• [Fix] fix nms trt jetson 1.x by @grimoire in #1687
• [Fix] import torchvision in wrapper by @grimoire in #1702
• [Fix] fix mmaction2 visualizer by @irexyc in #1703
• [Fix] fix build_backend_model() error by @AllentDan in #1705
• [Fix] fix torch allocator resouce releasing by @AllentDan in #1711
• [Fix] fix mmocr create input from np.ndarray by @AllentDan in #1721
• [Fix] Fix double free 1.x by @grimoire in #1749
• [Fix] Fix WarpBbox and memory leak in TextRecognizer (#1745) by @lzhangzz in #1752
• [Fix] remove score filtering in rtmdet_head rewriter since it leads to error shape in batch inference by @lvhan028 in #1762
• [Fix] fix MRCNN visualization, add condition for mask resize by @AllentDan in #1767

📚 Documentations

• [Docs] update build doc for jetsons by @AllentDan in #1621
• [Docs] Correct document errors in build_from_source.md master -> 1.x by @linjie111 in #1700
• [Docs] Update docs by @Xiangxu-0103 in #1709
• [Docs] Add twitter discord medium youtube link by @vansin in #1763

🌐 Other

• [Update] Switch pip to mim in Docs and Dockerfile by @xin-li-67 in #1591
• [Refactor] Support batch inference with shape clustering (#1668) by @lzhangzz in #1733
• Cherry-pick #1439 to fix 'topk' on different devices for onnxruntime-gpu inference by @hanrui1sensetime in #1603
• cherry-pick 1608 by @RunningLeon in #1637
• Cherry-pick PR 1460 to dev-1.x by @hanrui1sensetime in #1617
• Cherry-pick PR 1366, 1370, 1460, 1577, 1598, 1601, 1612, 1626 to dev-1.x by @irexyc in #1635
• Cherry pick PR 1663, 1666, 1486 to dev-1.x by @lzhangzz in #1691
• Cherry pick PR 1625, 1715, 1725 to dev-1.x by @lzhangzz in #1726
• Cherry pick PR 1740 to dev-1.x by @irexyc in #1760
• bump version to 1.0.0rc2 by @grimoire in #1754

New Contributors

• @linjie111 made their first contribution in #1700
• @Xiangxu-0103 made their first contribution in #1709

Full Changelog: v1.0.0rc1...v1.0.0rc2