Changelog¶
V0.24.1 (5/1/2022)¶
Bug Fixes
V0.24.0 (4/29/2022)¶
Highlights
Support MAE: Masked Autoencoders Are Scalable Vision Learners
Support Resnet strikes back
New Features
Support MAE: Masked Autoencoders Are Scalable Vision Learners (1307, 1523)
Support Resnet strikes back (1390)
Support extra dataloader settings in configs (1435)
Bug Fixes
Fix input previous results for the last cascade_decode_head (#1450)
Fix validation loss logging (#1494)
Fix the bug in binary_cross_entropy (1527)
Support single channel prediction for Binary Cross Entropy Loss (#1454)
Fix potential bugs in accuracy.py (1496)
Avoid converting label ids twice by label map during evaluation (1417)
Fix bug about label_map (1445)
Fix image save path bug in Windows (1423)
Migrate azure blob for beit checkpoints (1503)
Fix bug in
tools/analyse_logs.py
caused by wrong plot_iter in some cases (1428)
Improvements
Merge BEiT and ConvNext’s LR decay optimizer constructors (#1438)
Register optimizer constructor with mmseg (#1456)
Refactor transformer encode layer in ViT and BEiT backbone (#1481)
Add
build_pos_embed
andbuild_layers
for BEiT (1517)Add
with_cp
to mit and vit (1431)Fix inconsistent dtype of
seg_label
in stdc decode (1463)Delete random seed for training in
dist_train.sh
(1519)Revise high
workers_per_gpus
in config file (#1506)Add GPG keys and del mmcv version in Dockerfile (1534)
Update checkpoint for model in deeplabv3plus (#1487)
Add
DistSamplerSeedHook
to set epoch number to dataloader when runner isEpochBasedRunner
(1449)Provide URLs of Swin Transformer pretrained models (1389)
Updating Dockerfiles From Docker Directory and
get_started.md
to reach latest stable version of Python, PyTorch and MMCV (1446)
Documentation
Add more clearly statement of CPU training/inference (1518)
Contributors
@jiangyitong made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1431
@kahkeng made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1447
@Nourollah made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1446
@androbaza made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1452
@Yzichen made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1445
@whu-pzhang made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1423
@panfeng-hover made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1417
@Johnson-Wang made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1496
@jere357 made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1460
@mfernezir made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1494
@donglixp made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1503
@YuanLiuuuuuu made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1307
@Dawn-bin made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1527
V0.23.0 (4/1/2022)¶
Highlights
Support BEiT: BERT Pre-Training of Image Transformers
Support K-Net: Towards Unified Image Segmentation
Add
avg_non_ignore
of CELoss to support average loss over non-ignored elementsSupport dataset initialization with file client
New Features
Support BEiT: BERT Pre-Training of Image Transformers (#1404)
Support K-Net: Towards Unified Image Segmentation (#1289)
Support dataset initialization with file client (#1402)
Add class name function for STARE datasets (#1376)
Support different seeds on different ranks when distributed training (#1362)
Add
nlc2nchw2nlc
andnchw2nlc2nchw
to simplify tensor with different dimension operation (#1249)
Improvements
Synchronize random seed for distributed sampler (#1411)
Add script and documentation for multi-machine distributed training (#1383)
Bug Fixes
Add
avg_non_ignore
of CELoss to support average loss over non-ignored elements (#1409)Fix some wrong URLs of models or logs in
./configs
(#1336)Add title and color theme arguments to plot function in
tools/confusion_matrix.py
(#1401)Fix outdated link in Colab demo (#1392)
Documentation
Contributors
@kinglintianxia made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1371
@CCODING04 made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1376
@mob5566 made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1401
@xiongnemo made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1392
@Xiangxu-0103 made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1405
V0.22.1 (3/9/2022)¶
Bug Fixes
Fix the ZeroDivisionError that all pixels in one image is ignored. (#1336)
Improvements
Provide URLs of STDC, Segmenter and Twins pretrained models (#1272)
V0.22 (3/04/2022)¶
Highlights
Support ConvNeXt: A ConvNet for the 2020s. Please use the latest MMClassification (0.21.0) to try it out.
Support iSAID aerial Dataset.
Officially Support inference on Windows OS.
New Features
Support ConvNeXt: A ConvNet for the 2020s. (#1216)
Support iSAID aerial Dataset. (#1115
Generating and plotting confusion matrix. (#1301)
Improvements
Refactor 4 decoder heads (ASPP, FCN, PSP, UPer): Split forward function into
_forward_feature
andcls_seg
. (#1299)Add
min_size
arg inResize
to keep the shape after resize bigger than slide window. (#1318)Revise pre-commit-hooks. (#1315)
Add win-ci. (#1296)
Bug Fixes
Fix
mlp_ratio
type in Swin Transformer. (#1274)Fix path errors in
./demo
. (#1269)Fix bug in conversion of potsdam. (#1279)
Make accuracy take into account
ignore_index
. (#1259)Add Pytorch HardSwish assertion in unit test. (#1294)
Fix wrong palette value in vaihingen. (#1292)
Fix the bug that SETR cannot load pretrain. (#1293)
Update correct
In Collection
in metafile of each configs. (#1239)Upload completed STDC models. (#1332)
Fix
DNLHead
exports onnx inference difference type Cast error. (#1161)
Contributors
@JiaYanhao made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1269
@andife made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1281
@SBCV made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1279
@HJoonKwon made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1259
@Tsingularity made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1290
@Waterman0524 made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1115
@MeowZheng made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1315
@linfangjian01 made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1318
V0.21.1 (2/9/2022)¶
Bug Fixes
Fix typos in docs. (#1263)
Fix repeating log by
setup_multi_processes
. (#1267)Upgrade isort in pre-commit hook. (#1270)
Improvements
V0.21 (1/29/2022)¶
Highlights
Officially Support CPUs training and inference, please use the latest MMCV (1.4.4) to try it out.
Support Segmenter: Transformer for Semantic Segmentation (ICCV’2021).
Support ISPRS Potsdam and Vaihingen Dataset.
Add Mosaic transform and
MultiImageMixDataset
class indataset_wrappers
.
New Features
Support Segmenter: Transformer for Semantic Segmentation (ICCV’2021) (#955)
Add segformer‘s benchmark on cityscapes (#1155)
Add auto resume (#1172)
Add Mosaic transform and
MultiImageMixDataset
class indataset_wrappers
(#1093, #1105)Add log collector (#1175)
Improvements
New-style CPU training and inference (#1251)
Add UNet benchmark with multiple losses supervision (#1143)
Bug Fixes
Fix the model statistics in doc for readthedoc (#1153)
Set random seed for
palette
if not given (#1152)Add
COCOStuffDataset
inclass_names.py
(#1222)Fix bug in non-distributed multi-gpu training/testing (#1247)
Delete unnecessary lines of STDCHead (#1231)
Contributors
@jbwang1997 made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1152
@BeaverCC made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1206
@Echo-minn made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1214
@rstrudel made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/955
V0.20.2 (12/15/2021)¶
Bug Fixes
Revise –option to –options to avoid BC-breaking. (#1140)
V0.20.1 (12/14/2021)¶
Improvements
Change options to cfg-options (#1129)
Bug Fixes
V0.20 (12/10/2021)¶
Highlights
Support Twins (#989)
Support a real-time segmentation model STDC (#995)
Support a widely-used segmentation model in lane detection ERFNet (#960)
Support A Remote Sensing Land-Cover Dataset LoveDA (#1028)
Support focal loss (#1024)
New Features
Support Twins (#989)
Support a real-time segmentation model STDC (#995)
Support a widely-used segmentation model in lane detection ERFNet (#960)
Add SETR cityscapes benchmark (#1087)
Add BiSeNetV1 COCO-Stuff 164k benchmark (#1019)
Support focal loss (#1024)
Add Cutout transform (#1022)
Improvements
Set a random seed when the user does not set a seed (#1039)
Add CircleCI setup (#1086)
Skip CI on ignoring given paths (#1078)
Add abstract and image for every paper (#1060)
Create a symbolic link on windows (#1090)
Support video demo using trained model (#1014)
Bug Fixes
Fix incorrectly loading init_cfg or pretrained models of several transformer models (#999, #1069, #1102)
Fix EfficientMultiheadAttention in SegFormer (#1037)
Remove
fp16
folder inconfigs
(#1031)Fix several typos in .yml file (Dice Metric #1041, ADE20K dataset #1120, Training Memory (GB) #1083)
Fix test error when using
--show-dir
(#1091)Fix dist training infinite waiting issue (#1035)
Change the upper version of mmcv to 1.5.0 (#1096)
Fix symlink failure on Windows (#1038)
Cancel previous runs that are not completed (#1118)
Unified links of readthedocs in docs (#1119)
Contributors
@Junjue-Wang made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1028
@ddebby made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1066
@del-zhenwu made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1078
@KangBK0120 made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1106
@zergzzlun made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1091
@fingertap made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1035
@irvingzhang0512 made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1014
@littleSunlxy made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/989
@lkm2835
@RockeyCoss
@MengzhangLI
@Junjun2016
@xiexinch
@xvjiarui
V0.19 (11/02/2021)¶
Highlights
Support TIMMBackbone wrapper (#998)
Support custom hook (#428)
Add codespell pre-commit hook (#920)
Add FastFCN benchmark on ADE20K (#972)
New Features
Support TIMMBackbone wrapper (#998)
Support custom hook (#428)
Add FastFCN benchmark on ADE20K (#972)
Add codespell pre-commit hook and fix typos (#920)
Improvements
Make inputs & channels smaller in unittests (#1004)
Change
self.loss_decode
back todict
in Single Loss situation (#1002)
Bug Fixes
Fix typo in usage example (#1003)
Add contiguous after permutation in ViT (#992)
Fix the invalid link (#985)
Fix bug in CI with python 3.9 (#994)
Fix bug when loading class name form file in custom dataset (#923)
Contributors
@ShoupingShan made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/923
@RockeyCoss made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/954
@HarborYuan made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/992
@lkm2835 made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/1003
@gszh made their first contribution in https://github.com/open-mmlab/mmsegmentation/pull/428
@VVsssssk
@MengzhangLI
@Junjun2016
V0.18 (10/07/2021)¶
Highlights
Support three real-time segmentation models (ICNet #884, BiSeNetV1 #851, and BiSeNetV2 #804)
Support one efficient segmentation model (FastFCN #885)
Support one efficient non-local/self-attention based segmentation model (ISANet #70)
Support COCO-Stuff 10k and 164k datasets (#625)
Support evaluate concated dataset separately (#833)
Support loading GT for evaluation from multi-file backend (#867)
New Features
Support three real-time segmentation models (ICNet #884, BiSeNetV1 #851, and BiSeNetV2 #804)
Support one efficient segmentation model (FastFCN #885)
Support one efficient non-local/self-attention based segmentation model (ISANet #70)
Support COCO-Stuff 10k and 164k datasets (#625)
Support evaluate concated dataset separately (#833)
Improvements
Support loading GT for evaluation from multi-file backend (#867)
Auto-convert SyncBN to BN when training on DP automatly(#772)
Refactor Swin-Transformer (#800)
Bug Fixes
V0.17 (09/01/2021)¶
Highlights
Support SegFormer
Support DPT
Support Dark Zurich and Nighttime Driving datasets
Support progressive evaluation
New Features
Support SegFormer (#599)
Support DPT (#605)
Support Dark Zurich and Nighttime Driving datasets (#815)
Support progressive evaluation (#709)
Improvements
Add multiscale_output interface and unittests for HRNet (#830)
Support inherit cityscapes dataset (#750)
Fix some typos in README.md (#824)
Delete convert function and add instruction to ViT/Swin README.md (#791)
Add vit/swin/mit convert weight scripts (#783)
Add copyright files (#796)
Bug Fixes
V0.16 (08/04/2021)¶
Highlights
Support PyTorch 1.9
Support SegFormer backbone MiT
Support md2yml pre-commit hook
Support frozen stage for HRNet
New Features
Support SegFormer backbone MiT (#594)
Support md2yml pre-commit hook (#732)
Support mim (#717)
Add mmseg2torchserve tool (#552)
Improvements
Support hrnet frozen stage (#743)
Add template of reimplementation questions (#741)
Output pdf and epub formats for readthedocs (#742)
Refine the docstring of ResNet (#723)
Replace interpolate with resize (#731)
Update resource limit (#700)
Update config.md (#678)
Bug Fixes
Fix ATTENTION registry (#729)
Fix analyze log script (#716)
Fix doc api display (#725)
Fix patch_embed and pos_embed mismatch error (#685)
Fix efficient test for multi-node (#707)
Fix init_cfg in resnet backbone (#697)
Fix efficient test bug (#702)
Fix url error in config docs (#680)
Fix mmcv installation (#676)
Fix torch version (#670)
Contributors
@sshuair @xiexinch @Junjun2016 @mmeendez8 @xvjiarui @sennnnn @puhsu @BIGWangYuDong @keke1u @daavoo
V0.15 (07/04/2021)¶
Highlights
Support ViT, SETR, and Swin-Transformer
Add Chinese documentation
Unified parameter initialization
Bug Fixes
Fix typo and links (#608)
Fix Dockerfile (#607)
Fix ViT init (#609)
Fix mmcv version compatible table (#658)
Fix model links of DMNEt (#660)
New Features
Support loading DeiT weights (#538)
Add config and models for ViT backbone with UperHead (#520, #635)
Support Swin-Transformer (#511)
Add higher accuracy FastSCNN (#606)
Add Chinese documentation (#666)
Improvements
V0.14 (06/02/2021)¶
Highlights
Support ONNX to TensorRT
Support MIM
Bug Fixes
New Features
Support loading DeiT weights (#538)
Support ONNX to TensorRT (#542)
Support output results for ADE20k (#544)
Support MIM (#549)
Improvements
V0.13 (05/05/2021)¶
Highlights
Support Pascal Context Class-59 dataset.
Support Visual Transformer Backbone.
Support mFscore metric.
Bug Fixes
Fixed Colaboratory tutorial (#451)
Fixed mIoU calculation range (#471)
Fixed sem_fpn, unet README.md (#492)
Fixed
num_classes
in FCN for Pascal Context 60-class dataset (#488)Fixed FP16 inference (#497)
New Features
Support dynamic export and visualize to pytorch2onnx (#463)
Support Pascal Context Class-59 dataset (#459)
Support Visual Transformer backbone (#465)
Support UpSample Neck (#512)
Support mFscore metric (#509)
Improvements
Add more CI for PyTorch (#460)
Add print model graph args for tools/print_config.py (#451)
Add cfg links in modelzoo README.md (#468)
Add BaseSegmentor import to segmentors/init.py (#495)
Add Chinese QR code (#506)
Use MMCV MODEL_REGISTRY (#515)
Add ONNX testing tools (#498)
Replace data_dict calling ‘img’ key to support MMDet3D (#514)
Support reading class_weight from file in loss function (#513)
Make tags as comment (#505)
Use MMCV EvalHook (#438)
V0.12 (04/03/2021)¶
Highlights
Support FCN-Dilate 6 model.
Support Dice Loss.
Bug Fixes
Fixed PhotoMetricDistortion Doc (#388)
Fixed install scripts (#399)
Fixed Dice Loss multi-class (#417)
New Features
Support Dice Loss (#396)
Add plot logs tool (#426)
Add opacity option to show_result (#425)
Speed up mIoU metric (#430)
Improvements
V0.11 (02/02/2021)¶
Highlights
Support memory efficient test, add more UNet models.
Bug Fixes
New Features
Improvements
Move train_cfg/test_cfg inside model (#341)
V0.10 (01/01/2021)¶
Highlights
Support MobileNetV3, DMNet, APCNet. Add models of ResNet18V1b, ResNet18V1c, ResNet50V1b.
Bug Fixes
New Features
Add ResNet18V1b, ResNet18V1c, ResNet50V1b, ResNet101V1b models (#316)
Support MobileNetV3 (#268)
Add 4 retinal vessel segmentation benchmark (#315)
Support DMNet (#313)
Support APCNet (#299)
Improvements
V0.9 (30/11/2020)¶
Highlights
Support 4 medical dataset, UNet and CGNet.
New Features
Support RGB2Gray transform (#227)
Support Rerange transform (#228)
Support ignore_index for BCE loss (#210)
Add modelzoo statistics (#263)
Support Dice evaluation metric (#225)
Support Adjust Gamma transform (#232)
Support CLAHE transform (#229)
Bug Fixes
Fixed detail API link (#267)
V0.8 (03/11/2020)¶
Highlights
Support 4 medical dataset, UNet and CGNet.
New Features
V0.7 (07/10/2020)¶
Highlights
Support Pascal Context dataset and customizing class dataset.
Bug Fixes
Fixed CPU inference (#153)
New Features
Add DeepLab OS16 models (#154)
Support Pascal Context dataset (#133)
Support customizing dataset classes (#71)
Support customizing dataset palette (#157)
Improvements
V0.6 (10/09/2020)¶
Highlights
Support new methods i.e. MobileNetV2, EMANet, DNL, PointRend, Semantic FPN, Fast-SCNN, ResNeSt.
Bug Fixes
Fixed sliding inference ONNX export (#90)
New Features
Support MobileNet v2 (#86)
Support EMANet (#34)
Support DNL (#37)
Support PointRend (#109)
Support Semantic FPN (#94)
Support Fast-SCNN (#58)
Support ResNeSt backbone (#47)
Support ONNX export (experimental) (#12)
Improvements
v0.5.1 (11/08/2020)¶
Highlights
Support FP16 and more generalized OHEM
Bug Fixes
Fixed Pascal VOC conversion script (#19)
Fixed OHEM weight assign bug (#54)
Fixed palette type when palette is not given (#27)
New Features
Support FP16 (#21)
Generalized OHEM (#54)
Improvements
Add load-from flag (#33)
Fixed training tricks doc about different learning rates of model (#26)