MMDetection V2.17.0 Release

Highlights

• Support PVT and PVTv2
• Support SOLO
• Support large scale jittering and New Mask R-CNN baselines
• Speed up YOLOv3 inference

New Features

• Support PVT and PVTv2 (#5780)
• Support SOLO (#5832)
• Support large scale jittering and New Mask R-CNN baselines (#6132)
• Add a general data structrue for the results of models (#5508)
• Added a base class for one-stage instance segmentation (#5904)
• Speed up YOLOv3 inference (#5991)
• Release Swin Transformer pre-trained models (#6100)
• Support mixed precision training in YOLOX (#5983)
• Support val workflow in YOLACT (#5986)
• Add script to test torchserve (#5936)
• Support onnxsim with dynamic input shape (#6117)

Bug Fixes

• Fix the function naming errors in model_wrappers (#5975)
• Fix regression loss bug when the input is an empty tensor (#5976)
• Fix scores not contiguous error in centernet_head (#6016)
• Fix missing parameters bug in imshow_bboxes (#6034)
• Fix bug in aug_test of HTC when the length of det_bboxes is 0 (#6088)
• Fix empty proposal errors in the training of some two-stage models (#5941)
• Fix dynamic_axes parameter error in ONNX dynamic shape export (#6104)
• Fix dynamic_shape bug of SyncRandomSizeHook (#6144)
• Fix the Swin Transformer config link error in the configuration (#6172)

Improvements

• Add filter rules in Mosaic transform (#5897)
• Add size divisor in get flops to avoid some potential bugs (#6076)
• Add Chinese translation of docs_zh-CN/tutorials/customize_dataset.md (#5915)
• Add Chinese translation of conventions.md (#5825)
• Add description of the output of data pipeline (#5886)
• Add dataset information in the README file for PanopticFPN (#5996)
• Add extra_repr for DropBlock layer to get details in the model printing (#6140)
• Fix CI out of memory and add PyTorch1.9 Python3.9 unit tests (#5862)
• Fix download links error of some model (#6069)
• Improve the generalization of XML dataset (#5943)
• Polish assertion error messages (#6017)
• Remove opencv-python-headless dependency by albumentations (#5868)
• Check dtype in transform unit tests (#5969)
• Replace the default theme of documentation with PyTorch Sphinx Theme (#6146)
• Update the paper and code fields in the metafile (#6043)
• Support to customize padding value of segmentation map (#6152)
• Support to resize multiple segmentation maps (#5747)

Contributors

A total of 24 developers contributed to this release.
Thanks @morkovka1337, @HarborYuan, @guillaumefrd, @guigarfr, @www516717402, @gaotongxiao, @ypwhs, @MartaYang, @shinya7y, @justiceeem, @zhaojinjian0000, @VVsssssk, @aravind-anantha, @wangbo-zhao, @czczup, @whai362, @czczup, @marijnl, @AronLin, @BIGWangYuDong, @hhaAndroid, @jshilong, @RangiLyu, @ZwwWayne

New Contributors

• @www516717402 made their first contribution in #5975
• @gaotongxiao made their first contribution in #6017
• @MartaYang made their first contribution in #6034
• @justiceeem made their first contribution in #5915
• @zhaojinjian0000 made their first contribution in #5897
• @VVsssssk made their first contribution in #5936
• @aravind-anantha made their first contribution in #6104
• @czczup made their first contribution in #5780
• @marijnl made their first contribution in #5886
• @HarborYuan made their first contribution in #5747
• @morkovka1337 made their first contribution in #6172
• @guillaumefrd made their first contribution in #6140

Full Changelog: v2.16.0...v2.17.0

MMDetection V2.16.0 Release

Highlights

• Support Panoptic FPN and Swin Transformer

New Features

• Support Panoptic FPN and release models (#5577, #5902)
• Support Swin Transformer backbone (#5748)
• Release RetinaNet models pre-trained with multi-scale 3x schedule (#5636)
• Add script to convert unlabeled image list to coco format (#5643)
• Add hook to check whether the loss value is valid (#5674)
• Add YOLO anchor optimizing tool (#5644)
• Support export onnx models without post process. (#5851)
• Support classwise evaluation in CocoPanopticDataset (#5896)
• Adapt browse_dataset for concatenated datasets. (#5935)
• Add PatchEmbed and PatchMerging with AdaptivePadding (#5952)

Bug Fixes

• Fix unit tests of YOLOX (#5859)
• Fix lose randomness in imshow_det_bboxes (#5845)
• Make output result of ImageToTensor contiguous (#5756)
• Fix inference bug when calling regress_by_class in RoIHead in some cases (#5884)
• Fix bug in CIoU loss where alpha should not have gradient. (#5835)
• Fix the bug that multiscale_output is defined but not used in HRNet (#5887)
• Set the priority of EvalHook to LOW. (#5882)
• Fix a YOLOX bug when applying bbox rescaling in test mode (#5899)
• Fix mosaic coordinate error (#5947)
• Fix dtype of bbox in RandomAffine. (#5930)

Improvements

• Add Chinese version of data_pipeline and (#5662)
• Support to remove state dicts of EMA when publishing models. (#5858)
• Refactor the loss function in HTC and SCNet (#5881)
• Use warnings instead of logger.warning (#5540)
• Use legacy coordinate in metric of VOC (#5627)
• Add Chinese version of customize_losses (#5826)
• Add Chinese version of model_zoo (#5827)

Contributors

A total of 19 developers contributed to this release.
Thanks @ypwhs, @zywvvd, @collinzrj, @OceanPang, @ddonatien, @@haotian-liu, @viibridges, @Muyun99, @guigarfr, @zhaojinjian0000, @jbwang1997,@wangbo-zhao, @xvjiarui, @RangiLyu, @jshilong, @AronLin, @BIGWangYuDong, @hhaAndroid, @ZwwWayne

New Contributors

• @zywvvd made their first contribution in #5756
• @ddonatien made their first contribution in #5926
• @viibridges made their first contribution in #5899
• @haotian-liu made their first contribution in #5882
• @Muyun99 made their first contribution in #5973
• @jbwang1997 made their first contribution in #5827

Full Changelog: v2.15.1...v2.16.0

MMDetection V2.15.1 Release

Highlights

• Support YOLOX

New Features

• Support YOLOX(#5756, #5758, #5760, #5767, #5770, #5774, #5777, #5808, #5828, #5848)

Bug Fixes

• Update correct SSD models. (#5789)
• Fix casting error in mask structure (#5820)
• Fix MMCV deployment documentation links. (#5790)

Improvements

• Use dynamic MMCV download link in TorchServe dockerfile (#5779)
• Rename the function upsample_like to interpolate_as for more general usage (#5788)

Contributors

A total of 14 developers contributed to this release.
Thanks @HAOCHENYE, @xiaohu2015, @HsLOL, @zhiqwang, @Adamdad, @shinya7y, @Johnson-Wang, @RangiLyu, @jshilong, @mmeendez8, @AronLin, @BIGWangYuDong, @hhaAndroid, @ZwwWayne

Full Changelog: v2.15.0...v2.15.1

MMDetection V2.15.0 Release

Highlights

• Support adding MIM dependencies during pip installation
• Support MobileNetV2 for SSD-Lite and YOLOv3
• Support Chinese Documentation

New Features

• Add function upsample_like (#5732)
• Support to output pdf and epub format documentation (#5738)
• Support and release Cascade Mask R-CNN 3x pre-trained models (#5645)
• Add ignore_index to CrossEntropyLoss (#5646)
• Support adding MIM dependencies during pip installation (#5676)
• Add MobileNetV2 config and models for YOLOv3 (#5510)
• Support COCO Panoptic Dataset (#5231)
• Support ONNX export of cascade models (#5486)
• Support DropBlock with RetinaNet (#5544)
• Support MobileNetV2 SSD-Lite (#5526)

Bug Fixes

• Fix the device of label in multiclass_nms (#5673)
• Fix error of backbone initialization from pre-trained checkpoint in config file (#5603, #5550)
• Fix download links of RegNet pretrained weights (#5655)
• Fix two-stage runtime error given empty proposal (#5559)
• Fix flops count error in DETR (#5654)
• Fix unittest for NumClassCheckHook when it is not used. (#5626)
• Fix description bug of using custom dataset (#5546)
• Fix bug of multiclass_nms that returns the global indices (#5592)
• Fix valid_mask logic error in RPNHead (#5562)
• Fix unit test error of pretrained configs (#5561)
• Fix typo error in anchor_head.py (#5555)
• Fix bug when using dataset wrappers (#5552)
• Fix a typo error in demo/MMDet_Tutorial.ipynb (#5511)
• Fixing crash in get_root_logger when cfg.log_level is not None (#5521)
• Fix docker version (#5502)
• Fix optimizer parameter error when using IterBasedRunner (#5490)

Improvements

• Add unit tests for MMTracking (#5620)
• Add Chinese translation of documentation (#5718, #5618, #5558, #5423, #5593, #5421, #5408. #5369, #5419, #5530, #5531)
• Update resource limit (#5697)
• Update docstring for InstaBoost (#5640)
• Support key reduction_override in all loss functions (#5515)
• Use repeatdataset to accelerate CenterNet training (#5509)
• Remove unnecessary code in autoassign (#5519)
• Add documentation about init_cfg (#5273)

Contributors

A total of 18 developers contributed to this release.
Thanks @OceanPang, @AronLin, @hellock, @Outsider565, @RangiLyu, @ElectronicElephant, @likyoo, @BIGWangYuDong, @hhaAndroid, @noobying, @yyz561, @likyoo,
@zeakey, @ZwwWayne, @ChenyangLiu, @johnson-magic, @qingswu, @BuxianChen

New Contributors

• @BuxianChen made their first contribution in #5511
• @qingswu made their first contribution in #5521
• @ChenyangLiu made their first contribution in #5555
• @zeakey made their first contribution in #5592
• @yyz561 made their first contribution in #5546
• @yingkaining made their first contribution in #5618
• @likyoo made their first contribution in #5640
• @Outsider565 made their first contribution in #5718

Full Changelog: v2.14.0...v2.15.0

MMDetection V2.14.0 Release

Highlights

• Upgrade to use MMCV-full 1.3.8 to use the fix in open-mmlab/mmcv#1120
• Add simple_test to dense heads to improve the consistency of single-stage and two-stage detectors
• Revert the test_mixins to single image test to improve efficiency and readability
• Add Faster R-CNN and Mask R-CNN config using multi-scale training with 3x schedule

New Features

• Support pretrained models from MoCo v2 and SwAV (#5286)
• Add Faster R-CNN and Mask R-CNN config using multi-scale training with 3x schedule (#5179, #5233)
• Add reduction_override in MSELoss (#5437)
• Stable support of exporting DETR to ONNX with dynamic shapes and batch inference (#5168)
• Stable support of exporting PointRend to ONNX with dynamic shapes and batch inference (#5440)

Bug Fixes

• Fix size mismatch bug in multiclass_nms (#4980)
• Fix the import path of MultiScaleDeformableAttention (#5338)
• Fix errors in config of GCNet ResNext101 models (#5360)
• Fix Grid-RCNN error when there is no bbox result (#5357)
• Fix errors in onnx_export of bbox_head when setting reg_class_agnostic (#5468)
• Fix type error of AutoAssign in the document (#5478)
• Fix web links ending with .md (#5315)

Improvements

• Add simple_test to dense heads to improve the consistency of single-stage and two-stage detectors (#5264)
• Add support for mask diagonal flip in TTA (#5403)
• Revert the test_mixins to single image test to improve efficiency and readability (#5249)
• Make YOLOv3 Neck more flexible (#5218)
• Refactor SSD to make it more general (#5291)
• Refactor anchor_generator and point_generator (#5349)
• Allow to configure out the mask_head of the HTC algorithm (#5389)
• Delete deprecated warning in FPN (#5311)
• Move model.pretrained to model.backbone.init_cfg (#5370)
• Make deployment tools more friendly to use (#5280)
• Clarify installation documentation (#5316)
• Add ImageNet Pretrained Models docs (#5268)
• Add FAQ about training loss=nan solution and COCO AP or AR =-1 (# 5312, #5313)
• Change all weight links of http to https (#5328)

New Contributors

• @hasanirtiza made their first contribution in #5302
• @THU17cyz made their first contribution in #5315
• @hokmund made their first contribution in #5218
• @jiangwenj02 made their first contribution in #5357
• @Junjun2016 made their first contribution in #5415
• @shenyunhang made their first contribution in #5428
• @MaximilianOtten made their first contribution in #5389
• @Y-M-Y made their first contribution in #5479

Full Changelog: v2.13.0...v2.14.0

MMDetection V2.13.0 Release

Highlights

• Support new methods: CenterNet, Seesaw Loss, MobileNetV2

New Features

• Support paper Objects as Points (#4602)
• Support paper Seesaw Loss for Long-Tailed Instance Segmentation (CVPR 2021) (#5128)
• Support MobileNetV2 backbone and inverted residual block (#5122)
• Support MIM (#5143)
• ONNX exportation with dynamic shapes of CornerNet (#5136)
• Add mask_soft config option to allow non-binary masks (#4615)
• Add PWC metafile (#5135)

Bug Fixes

• Fix YOLOv3 FP16 training error (#5172)
• Fix Cascade R-CNN TTA test error when det_bboxes length is 0 (#5221)
• Fix iou_thr variable naming errors in VOC recall calculation function (#5195)
• Fix Faster R-CNN performance dropped in ONNX Runtime (#5197)
• Fix DETR dict changed error when using python 3.8 during iteration (#5226)

Improvements

• Refactor ONNX export of two-stage detector (#5205)
• Replace MMDetection's EvalHook with MMCV's EvalHook for consistency (#4806)
• Update RoI extractor for ONNX (#5194)
• Use better parameter initialization in YOLOv3 head for higher performance (#5181)
• Release new DCN models of Mask R-CNN by mixed-precision training (#5201)
• Update YOLOv3 model weights (#5229)
• Add DetectoRS ResNet-101 model weights (#4960)
• Discard boxes with sizes equals to min_bbox_size (#5011)
• Remove duplicated code in DETR head (#5129)
• Remove unnecessary object in the class definition (#5180)

New Contributors

• @namihagi made their first contribution in #5121
• @zlx-6 made their first contribution in #5129
• @haofanwang made their first contribution in #5147
• @ijjustinKim made their first contribution in #5163
• @liuhuiCNN made their first contribution in #5192
• @SemyonBevzuk made their first contribution in #5197

Full Changelog: v2.12.0...v2.13.0

MMDetection V2.12.0 Release

Highlights

• Support new methods: AutoAssign, YOLOF, and Deformable DETR
• Stable support of exporting models to ONNX with batched images and dynamic shape (#5039)

Backwards Incompatible Changes

MMDetection is going through big refactoring for more general and convenient usages during the releases from v2.12.0 to v2.15.0 (maybe longer).
In v2.12.0 MMDetection inevitably brings some BC-breakings including the MMCV dependency, model initialization, model registry, and mask AP evaluation.

• MMCV version. MMDetection v2.12.0 relies on the newest features in MMCV 1.3.3, including BaseModule for unified parameter initialization, model registry, and the CUDA operator MultiScaleDeformableAttn for Deformable DETR. Note that MMCV 1.3.2 already contains all the features used by MMDet but has known issues. Therefore, we recommend users to skip MMCV v1.3.2 and use v1.3.2, though v1.3.2 might work for most of the cases.
• Unified model initialization (#4750). To unify the parameter initialization in OpenMMLab projects, MMCV supports BaseModule that accepts init_cfg to allow the modules' parameters to be initialized in a flexible and unified manner. Now the users need to explicitly call model.init_weights() in the training script to initialize the model (as in here, previously this was handled by the detector. The models in MMDetection have been re-benchmarked to ensure accuracy in PR #4750. The downstream projects should update their code accordingly to use MMDetection v2.12.0.
• Unified model registry (#5059). To easily use backbones implemented in other OpenMMLab projects, MMDetection migrates to inherit the model registry created in MMCV (#760). In this way, as long as the backbone is supported in an OpenMMLab project and that project also uses the registry in MMCV, users can use that backbone in MMDetection by simply modifying the config without copying the code of that backbone into MMDetection.
• Mask AP evaluation (#4898). In the previous version, the areas of masks are calculated through the bounding boxes when calculating the mask AP of small, medium, and large instances. To really use the area of masks, we pop the key bbox during mask AP calculation. This change does not affect the overall mask AP evaluation and aligns the mask AP of similar models in other repos like Detectron2.

New Features

• Support paper AutoAssign: Differentiable Label Assignment for Dense Object Detection (#4295)
• Support paper You Only Look One-level Feature (#4295)
• Support paper Deformable DETR: Deformable Transformers for End-to-End Object Detection (#4778)
• Support calculating IoU with FP16 tensor in bbox_overlaps to save memory and keep speed (#4889)
• Add __repr__ in custom dataset to count the number of instances (#4756)
• Add windows support by updating requirements.txt (#5052)
• Stable support of exporting models to ONNX with batched images and dynamic shape, including SSD, FSAF, FCOS, YOLOv3, RetinaNet, Faster R-CNN, and Mask R-CNN (#5039)

Improvements

• Use MMCV MODEL_REGISTRY (#5059)
• Unified parameter initialization for more flexible usage (#4750)
• Rename variable names and fix docstring in anchor head (#4883)
• Support training with empty GT in Cascade RPN (#4928)
• Add more details of usage of test_robustness in documentation (#4917)
• Changing to use pycocotools instead of mmpycocotools to fully support Detectron2 and MMDetection in one environment (#4939)
• Update torch serve dockerfile to support dockers of more versions (#4954)
• Add check for training with the single class dataset (#4973)
• Refactor transformer and DETR Head (#4763)
• Update FPG model zoo (#5079)
• More accurate mask AP of small/medium/large instances (#4898)

Bug Fixes

• Fix bug in mean_ap.py when calculating mAP by 11 points (#4875)
• Fix error when key meta is not in old checkpoints (#4936)
• Fix hanging bug when training with empty GT in VFNet, GFL, and FCOS by changing the place of reduce_mean (#4923, #4978, #5058)
• Fix asyncronized inference error and provide related demo (#4941)
• Fix IoU losses dimensionality unmatch error (#4982)
• Fix torch.randperm whtn using PyTorch 1.8 (#5014)
• Fix empty bbox error in mask_head when using CARAFE (#5062)
• Fix supplement_mask bug when there are zero-size RoIs (#5065)
• Fix testing with empty rois in RoI Heads (#5081)

New Contributors

• @ZephyrusKylin made their first contribution in #4875
• @agim-a made their first contribution in #4936
• @li-phone made their first contribution in #4889
• @Adamdad made their first contribution in #4756
• @hjin2902 made their first contribution in #4943
• @adursun made their first contribution in #5013
• @quincylin1 made their first contribution in #5031

Full Changelog: v2.11.0...v2.12.0

MMDetection V2.11.0 Release

Highlights

• Support new method: Localization Distillation for Object Detection
• Support Pytorch2ONNX with batch inference and dynamic shape

New Features

• Support localization distillation for object detection (#4758)
• Support Pytorch2ONNX with batch inference and dynamic shape for Faster-RCNN and mainstream one-stage detectors (#4796)

Improvements

• Support batch inference in head of RetinaNet (#4699)
• Add batch dimension in second stage of Faster-RCNN (#4785)
• Support batch inference in bbox coder (#4721)
• Add check for ann_ids in COCODataset to ensure it is unique (#4789)
• support for showing the RPN results (#4716)
• support dynamic shape for grid_anchor (#4684)
• Support automatic statistical evaluation results and export them to EXCEL (#4693)
• Move pycocotools version check to when it is used (#4880)

Bug Fixes

• Fix a bug of TridentNet when doing the batch inference (#4717)
• Fix a bug of Pytorch2ONNX in FASF (#4735)
• Fix a bug when show the image with float type (#4732)

New Contributors

• @tangyanf made their first contribution in #4685
• @freepoet made their first contribution in #4701
• @SeongjaeHong made their first contribution in #4770
• @ShoufaChen made their first contribution in #4805
• @tczhao made their first contribution in #4836
• @HikariTJU made their first contribution in #4758
• @ppwwyyxx made their first contribution in #4880
• @hcy226 made their first contribution in #4879

Full Changelog: v2.10.0...v2.11.0

MMDetection V2.10.0 Release

Highlights

• Support new methods: FPG
• Support ONNX2TensorRT for SSD, FSAF, FCOS, YOLOv3, and Faster R-CNN.

New Features

• Support ONNX2TensorRT for SSD, FSAF, FCOS, YOLOv3, and Faster R-CNN (#4569)
• Support Feature Pyramid Grids (FPG) (#4645)
• Support video demo (#4420)
• Add seed option for sampler (#4665)
• Support to customize type of runner (#4570, #4669)
• Support synchronizing BN buffer in EvalHook (#4582)
• Add script for GIF demo (#4573)

Bug Fixes

• Fix ConfigDict AttributeError and add Colab link (#4643)
• Avoid crash in empty gt training of GFL head (#4631)
• Fix iou_thrs bug in RPN evaluation (#4581)
• Fix syntax error of config when upgrading model version (#4584)

Improvements

• Refactor unit test file structures (#4600)
• Refactor nms config (#4636)
• Get loading pipeline by checking the class directly rather than through config strings (#4619)
• Add doctests for mask target generation and mask structures (#4614)
• Use deep copy when copying pipeline arguments (#4621)
• Update documentations (#4642, #4650, #4620, #4630)
• Remove redundant code calling import_modules_from_strings (#4601)
• Clean deprecated FP16 API (#4571)
• Check whether CLASSES is correctly initialized in the intialization of XMLDataset (#4555)
• Support batch inference in the inference API (#4462, #4526)
• Clean deprecated warning and fix 'meta' error (#4695)

New Contributors

• @CescMessi made their first contribution in #4584
• @dave-andersen made their first contribution in #4462
• @sleepfin made their first contribution in #4581
• @YimianDai made their first contribution in #4620
• @lml131 made their first contribution in #4192
• @steven0129 made their first contribution in #4420

Full Changelog: v2.9.0...v2.10.0

MMDetection V2.9.0 Release

Highlights

• Support new methods: SCNet, Sparse R-CNN
• Move train_cfg and test_cfg into model in configs
• Support to visualize results based on prediction quality

New Features

• Support SCNet (#4356)
• Support Sparse R-CNN (#4219)
• Support evaluate mAP by multiple IoUs (#4398)
• Support concatenate dataset for testing (#4452)
• Support to visualize results based on prediction quality (#4441)
• Add ONNX simplify option to Pytorch2ONNX script (#4468)
• Add hook for checking compatibility of class numbers in heads and datasets (#4508)

Bug Fixes

• Fix CPU inference bug of Cascade RPN (#4410)
• Fix NMS error of CornerNet when there is no prediction box (#4409)
• Fix TypeError in CornerNet inference (#4411)
• Fix bug of PAA when training with background images (#4391)
• Fix the error that the window data is not destroyed when out_file is not None and show==False (#4442)
• Fix order of NMS score_factor that will decrease the performance of YOLOv3 (#4473)
• Fix bug in HTC TTA when the number of detection boxes is 0 (#4516)
• Fix resize error in mask data structures (#4520)

Improvements

• Allow to customize classes in LVIS dataset (#4382)
• Add tutorials for building new models with existing datasets (#4396)
• Add CPU compatibility information in documentation (#4405)
• Add documentation of deprecated ImageToTensor for batch inference (#4408)
• Add more details in documentation for customizing dataset (#4430)
• Switch imshow_det_bboxes visualization backend from OpenCV to Matplotlib (#4389)
• Deprecate ImageToTensor in image_demo.py (#4400)
• Move train_cfg/test_cfg into model (#4347, #4489)
• Update docstring for reg_decoded_bbox option in bbox heads (#4467)
• Update dataset information in documentation (#4525)
• Release pre-trained R50 and R101 PAA detectors with multi-scale 3x training schedules (#4495)
• Add guidance for speed benchmark (#4537)

New Contributors

• @kazet made their first contribution in #4429
• @LutingWang made their first contribution in #4474
• @digantamisra98 made their first contribution in #4510

Full Changelog: v2.8.0...v2.9.0