v1.0.2(15/08/2023)

New Features

- Add MFF ([open-mmlab#1725](open-mmlab#1725))
- Support training of BLIP2 ([open-mmlab#1700](open-mmlab#1700))

Improvements

- New Version of config Adapting MAE Algorithm ([open-mmlab#1750](open-mmlab#1750))
- New Version of config Adapting ConvNeXt Algorithm ([open-mmlab#1760](open-mmlab#1760))
- New version of config adapting BeitV2 Algorithm ([open-mmlab#1755](open-mmlab#1755))
- Update `dataset_prepare.md` ([open-mmlab#1732](open-mmlab#1732))
- New Version of `config` Adapting Vision Transformer Algorithm ([open-mmlab#1727](open-mmlab#1727))
- Support Infographic VQA dataset and ANLS metric. ([open-mmlab#1667](open-mmlab#1667))
- Support IconQA dataset. ([open-mmlab#1670](open-mmlab#1670))
- Fix typo MIMHIVIT to MAEHiViT ([open-mmlab#1749](open-mmlab#1749))

v1.0.1(31/07/2023)

Improvements

- Add init_cfg with type='pretrained' to downstream tasks ([open-mmlab#1717](open-mmlab#1717)
- Set 'is_init' in some multimodal methods ([open-mmlab#1718](open-mmlab#1718)
- Adapt test cases on Ascend NPU ([open-mmlab#1728](open-mmlab#1728)
- Add GPU Acceleration Apple silicon mac ([open-mmlab#1699](open-mmlab#1699)
- BEiT refactor ([open-mmlab#1705](open-mmlab#1705)

Bug Fixes

- Fix dict update in minigpt4. ([open-mmlab#1709](open-mmlab#1709)
- Fix nested predict for multi-task prediction ([open-mmlab#1716](open-mmlab#1716)
- Fix the issue open-mmlab#1711 "GaussianBlur doesn't work" ([open-mmlab#1722](open-mmlab#1722)
- Just to correct a typo of 'target' ([open-mmlab#1655](open-mmlab#1655)
- Fix freeze without cls_token in vit ([open-mmlab#1693](open-mmlab#1693)
- Fix RandomCrop bug ([open-mmlab#1706](open-mmlab#1706)

Docs Update

- Fix spelling ([open-mmlab#1689](open-mmlab#1689)

Bump version to 1.0.0 (open-mmlab#1686)

* bump version to 1.0.0

* update

* update

* fix lint

* update

* update

* update changelog

* update

v1.0.0rc8(22/05/2023)

Highlights

- Support multiple multi-modal algorithms and inferencers. You can explore these features by the [gradio demo](https://github.com/open-mmlab/mmpretrain/tree/main/projects/gradio_demo)!
- Add EVA-02, Dino-V2, ViT-SAM and GLIP backbones.
- Register torchvision transforms into MMPretrain, you can now easily integrate torchvision's data augmentations in MMPretrain.

New Features

- Support Chinese CLIP. ([open-mmlab#1576](open-mmlab#1576))
- Add ScienceQA Metrics ([open-mmlab#1577](open-mmlab#1577))
- Support multiple multi-modal algorithms and inferencers. ([open-mmlab#1561](open-mmlab#1561))
- add eva02 backbone ([open-mmlab#1450](open-mmlab#1450))
- Support dinov2 backbone ([open-mmlab#1522](open-mmlab#1522))
- Support some downstream classification datasets. ([open-mmlab#1467](open-mmlab#1467))
- Support GLIP ([open-mmlab#1308](open-mmlab#1308))
- Register torchvision transforms into mmpretrain ([open-mmlab#1265](open-mmlab#1265))
- Add ViT of SAM ([open-mmlab#1476](open-mmlab#1476))

Improvements

- [Refactor] Support to freeze channel reduction and add layer decay function ([open-mmlab#1490](open-mmlab#1490))
- [Refactor] Support resizing pos_embed while loading ckpt and format output ([open-mmlab#1488](open-mmlab#1488))

Bug Fixes

- Fix scienceqa ([open-mmlab#1581](open-mmlab#1581))
- Fix config of beit ([open-mmlab#1528](open-mmlab#1528))
- Incorrect stage freeze on RIFormer Model ([open-mmlab#1573](open-mmlab#1573))
- Fix ddp bugs caused by `out_type`. ([open-mmlab#1570](open-mmlab#1570))
- Fix multi-task-head loss potential bug ([open-mmlab#1530](open-mmlab#1530))
- Support bce loss without batch augmentations ([open-mmlab#1525](open-mmlab#1525))
- Fix clip generator init bug ([open-mmlab#1518](open-mmlab#1518))
- Fix the bug in binary cross entropy loss ([open-mmlab#1499](open-mmlab#1499))

Docs Update

- Update PoolFormer citation to CVPR version ([open-mmlab#1505](open-mmlab#1505))
- Refine Inference Doc ([open-mmlab#1489](open-mmlab#1489))
- Add doc for usage of confusion matrix ([open-mmlab#1513](open-mmlab#1513))
- Update MMagic link ([open-mmlab#1517](open-mmlab#1517))
- Fix example_project README ([open-mmlab#1575](open-mmlab#1575))
- Add NPU support page ([open-mmlab#1481](open-mmlab#1481))
- train cfg: Removed old description ([open-mmlab#1473](open-mmlab#1473))
- Fix typo in MultiLabelDataset docstring ([open-mmlab#1483](open-mmlab#1483))

Bump version to v1.0.0rc7 (open-mmlab#1465)

* update

* update info

* update changelog

* update

* update description

* change to v1.0.0rc7

v1.0.0rc6(06/04/2023)

Highlights

- Support OOD datasets.
- Support confusion matrix calculation and plot.
- Support LeViT, XCiT, ViG and ConvNeXt-V2 backbone.

New Features

- Support Out-of-Distribution datasets like ImageNet-A,R,S,C. ([open-mmlab#1342](open-mmlab#1342))
- Support XCiT Backbone. ([open-mmlab#1305](open-mmlab#1305))
- Support calculate confusion matrix and plot it. ([open-mmlab#1287](open-mmlab#1287))
- Support RetrieverRecall metric & Add ArcFace config ([open-mmlab#1316](open-mmlab#1316))
- Add `ImageClassificationInferencer`. ([open-mmlab#1261](open-mmlab#1261))
- Support InShop Dataset (Image Retrieval). ([open-mmlab#1019](open-mmlab#1019))
- Support LeViT backbone. ([open-mmlab#1238](open-mmlab#1238))
- Support VIG Backbone. ([open-mmlab#1304](open-mmlab#1304))
- Support ConvNeXt-V2 backbone. ([open-mmlab#1294](open-mmlab#1294))

Improvements

- [Enhance] Add stochastic depth decay rule in resnet. ([open-mmlab#1363](open-mmlab#1363))
- [Refactor] Update analysis tools and documentations. ([open-mmlab#1359](open-mmlab#1359))
- [Refactor] Unify the `--out` and `--dump` in `tools/test.py`. ([open-mmlab#1307](open-mmlab#1307))
- [Enhance] Enable to toggle whether Gem Pooling is trainable or not. ([open-mmlab#1246](open-mmlab#1246))
- [Improve] Update registries of mmcls. ([open-mmlab#1306](open-mmlab#1306))
- [Tool] Add metafile fill and validation tools. ([open-mmlab#1297](open-mmlab#1297))
- [Improve] Remove useless EfficientnetV2 config files. ([open-mmlab#1300](open-mmlab#1300))

Bug Fixes

- Fix precise bn hook ([open-mmlab#1386](open-mmlab#1386))
- Fix acc evalustion wait for long ([open-mmlab#1430](open-mmlab#1430))
- Fix retrieval multi gpu bug ([open-mmlab#1319](open-mmlab#1319))
- Fix error repvgg-deploy base config path. ([open-mmlab#1357](open-mmlab#1357))
- Fix bug in test tools. ([open-mmlab#1309](open-mmlab#1309))

Docs Update

- Update Readme ([open-mmlab#1442](open-mmlab#1442))
- Add NPU support page. ([open-mmlab#1437](open-mmlab#1437))
- Translate some tools tutorials to Chinese. ([open-mmlab#1321](open-mmlab#1321))
- Add Chinese translation for runtime.md.  ([open-mmlab#1313](open-mmlab#1313))

v1.0.0rc5(30/12/2022)

Highlights

- Support EVA, RevViT, EfficientnetV2, CLIP, TinyViT and MixMIM backbones.
- Reproduce the training accuracy of ConvNeXt and RepVGG.
- Support multi-task training and testing.
- Support Test-time Augmentation.

New Features

- [Feature] Add EfficientnetV2 Backbone. ([open-mmlab#1253](open-mmlab#1253))
- [Feature] Support TTA and add `--tta` in `tools/test.py`. ([open-mmlab#1161](open-mmlab#1161))
- [Feature] Support Multi-task. ([open-mmlab#1229](open-mmlab#1229))
- [Feature] Add clip backbone. ([open-mmlab#1258](open-mmlab#1258))
- [Feature] Add mixmim backbone with checkpoints. ([open-mmlab#1224](open-mmlab#1224))
- [Feature] Add TinyViT for dev-1.x. ([open-mmlab#1042](open-mmlab#1042))
- [Feature] Add some scripts for development. ([open-mmlab#1257](open-mmlab#1257))
- [Feature] Support EVA. ([open-mmlab#1239](open-mmlab#1239))
- [Feature] Implementation of RevViT. ([open-mmlab#1127](open-mmlab#1127))

Improvements

- [Reproduce] Reproduce RepVGG  Training Accuracy. ([open-mmlab#1264](open-mmlab#1264))
- [Enhance] Support ConvNeXt More Weights. ([open-mmlab#1240](open-mmlab#1240))
- [Reproduce] Update ConvNeXt config files. ([open-mmlab#1256](open-mmlab#1256))
- [CI] Update CI to test PyTorch 1.13.0. ([open-mmlab#1260](open-mmlab#1260))
- [Project] Add ACCV workshop 1st Solution. ([open-mmlab#1245](open-mmlab#1245))
- [Project] Add Example project. ([open-mmlab#1254](open-mmlab#1254))

Bug Fixes

- [Fix] Fix imports in transforms. ([open-mmlab#1255](open-mmlab#1255))
- [Fix] Fix CAM visualization. ([open-mmlab#1248](open-mmlab#1248))
- [Fix] Fix the requirements and lazy register mmcls models. ([open-mmlab#1275](open-mmlab#1275))

v1.0.0rc4(06/12/2022)

Highlights

- Upgrade API to get pre-defined models of MMClassification. See [open-mmlab#1236](open-mmlab#1236) for more details.
- Refactor BEiT backbone and support v1/v2 inference. See [open-mmlab#1144](open-mmlab#1144).

New Features

- Support getting model from the name defined in the model-index file. ([open-mmlab#1236](open-mmlab#1236))

Improvements

- Support evaluate on both EMA and non-EMA models. ([open-mmlab#1204](open-mmlab#1204))
- Refactor BEiT backbone and support v1/v2 inference. ([open-mmlab#1144](open-mmlab#1144))

Bug Fixes

- Fix `reparameterize_model.py` doesn't save meta info. ([open-mmlab#1221](open-mmlab#1221))
- Fix dict update in BEiT. ([open-mmlab#1234](open-mmlab#1234))

Docs Update

- Update install tutorial. ([open-mmlab#1223](open-mmlab#1223))
- Update MobileNetv2 & MobileNetv3 readme. ([open-mmlab#1222](open-mmlab#1222))
- Add version selection in the banner. ([open-mmlab#1217](open-mmlab#1217))

v0.25.0(06/12/2022)

Highlights

- Support MLU backend.

New Features

- Support MLU backend. ([open-mmlab#1159](open-mmlab#1159))
- Support Activation Checkpointing for ConvNeXt. ([open-mmlab#1152](open-mmlab#1152))

Improvements

- Add `dist_train_arm.sh` for ARM device and update NPU results. ([open-mmlab#1218](open-mmlab#1218))

Bug Fixes

- Fix a bug caused `MMClsWandbHook` stuck. ([open-mmlab#1242](open-mmlab#1242))
- Fix the redundant `device_ids` in `tools/test.py`. ([open-mmlab#1215](open-mmlab#1215))

Docs Update

- Add version banner and version warning in master docs. ([open-mmlab#1216](open-mmlab#1216))
- Update NPU support doc. ([open-mmlab#1198](open-mmlab#1198))
- Fixed typo in `pytorch2torchscript.md`. ([open-mmlab#1173](open-mmlab#1173))
- Fix typo in `miscellaneous.md`. ([open-mmlab#1137](open-mmlab#1137))
- further detail for the doc for `ClassBalancedDataset`. ([open-mmlab#901](open-mmlab#901))

v1.0.0rc3(21/11/2022)

Highlights

- Add **Switch Recipe** Hook, Now we can modify training pipeline, mixup and loss settings during training, see [open-mmlab#1101](open-mmlab#1101).
- Add **TIMM and HuggingFace** wrappers. Now you can train/use models in TIMM/HuggingFace directly, see [open-mmlab#1102](open-mmlab#1102).
- Support **retrieval tasks**, see [open-mmlab#1055](open-mmlab#1055).
- Reproduce **mobileone** training accuracy. See [open-mmlab#1191](open-mmlab#1191)

New Features

- Add checkpoints from EfficientNets NoisyStudent & L2. ([open-mmlab#1122](open-mmlab#1122))
- Migrate CSRA head to 1.x. ([open-mmlab#1177](open-mmlab#1177))
- Support RepLKnet backbone. ([open-mmlab#1129](open-mmlab#1129))
- Add Switch Recipe Hook. ([open-mmlab#1101](open-mmlab#1101))
- Add adan optimizer. ([open-mmlab#1180](open-mmlab#1180))
- Support DaViT. ([open-mmlab#1105](open-mmlab#1105))
- Support Activation Checkpointing for ConvNeXt. ([open-mmlab#1153](open-mmlab#1153))
- Add TIMM and HuggingFace wrappers to build classifiers from them directly. ([open-mmlab#1102](open-mmlab#1102))
- Add reduction for neck ([open-mmlab#978](open-mmlab#978))
- Support HorNet Backbone for dev1.x. ([open-mmlab#1094](open-mmlab#1094))
- Add arcface head. ([open-mmlab#926](open-mmlab#926))
- Add Base Retriever and Image2Image Retriever for retrieval tasks. ([open-mmlab#1055](open-mmlab#1055))
- Support MobileViT backbone. ([open-mmlab#1068](open-mmlab#1068))

Improvements

- [Enhance] Enhance ArcFaceClsHead. ([open-mmlab#1181](open-mmlab#1181))
- [Refactor] Refactor to use new fileio API in MMEngine. ([open-mmlab#1176](open-mmlab#1176))
- [Enhance] Reproduce mobileone training accuracy. ([open-mmlab#1191](open-mmlab#1191))
- [Enhance] add deleting params info in swinv2. ([open-mmlab#1142](open-mmlab#1142))
- [Enhance] Add more mobilenetv3 pretrains. ([open-mmlab#1154](open-mmlab#1154))
- [Enhancement] RepVGG for YOLOX-PAI for dev-1.x. ([open-mmlab#1126](open-mmlab#1126))
- [Improve] Speed up data preprocessor. ([open-mmlab#1064](open-mmlab#1064))

Bug Fixes

- Fix the torchserve. ([open-mmlab#1143](open-mmlab#1143))
- Fix configs due to api refactor of `num_classes`. ([open-mmlab#1184](open-mmlab#1184))
- Update mmcls2torchserve. ([open-mmlab#1189](open-mmlab#1189))
- Fix for `inference_model` cannot get classes information in checkpoint. ([open-mmlab#1093](open-mmlab#1093))

Docs Update

- Add not-found page extension. ([open-mmlab#1207](open-mmlab#1207))
- update visualization doc. ([open-mmlab#1160](open-mmlab#1160))
- Support sort and search the Model Summary table. ([open-mmlab#1100](open-mmlab#1100))
- Improve the ResNet model page. ([open-mmlab#1118](open-mmlab#1118))
- update the readme of convnext. ([open-mmlab#1156](open-mmlab#1156))
- Fix the installation docs link in README. ([open-mmlab#1164](open-mmlab#1164))
- Improve ViT and MobileViT model pages. ([open-mmlab#1155](open-mmlab#1155))
- Improve Swin Doc and Add Tabs enxtation. ([open-mmlab#1145](open-mmlab#1145))
- Add MMEval projects link in README. ([open-mmlab#1162](open-mmlab#1162))
- Add runtime configuration docs. ([open-mmlab#1128](open-mmlab#1128))
- Add custom evaluation docs ([open-mmlab#1130](open-mmlab#1130))
- Add custom pipeline docs. ([open-mmlab#1124](open-mmlab#1124))
- Add MMYOLO projects link in MMCLS1.x. ([open-mmlab#1117](open-mmlab#1117))