fix links and typos (#58)

* fix init

* fix test api

fix test api bug

* add metarcnn fsdetview config

* fix link and typos

README.md

@@ -9,17 +9,11 @@
 English | [简体中文](README_zh-CN.md)
 
 [![Documentation](https://readthedocs.org/projects/mmfewshot/badge/?version=latest)](https://mmfewshot.readthedocs.io/en/latest/?badge=latest)
-
 [![actions](https://github.com/open-mmlab/mmfewshot/workflows/build/badge.svg)](https://github.com/open-mmlab/mmfewshot/actions)
-
 [![codecov](https://codecov.io/gh/open-mmlab/mmfewshot/branch/master/graph/badge.svg)](https://codecov.io/gh/open-mmlab/mmfewshot)
-
 [![PyPI](https://badge.fury.io/py/mmedit.svg)](https://pypi.org/project/mmedit/)
-
 [![LICENSE](https://img.shields.io/github/license/open-mmlab/mmfewshot.svg)](https://github.com/open-mmlab/mmfewshot/blob/master/LICENSE)
-
 [![Average time to resolve an issue](https://isitmaintained.com/badge/resolution/open-mmlab/mmfewshot.svg)](https://github.com/open-mmlab/mmfewshot/issues)
-
 [![Percentage of issues still open](https://isitmaintained.com/badge/open/open-mmlab/mmfewshot.svg)](https://github.com/open-mmlab/mmfewshot/issues)
 
 
@@ -113,7 +107,7 @@ If you find this project useful in your research, please consider cite:
 
 ## Contributing
 
-We appreciate all contributions to improve mmfewshot. Please refer to [CONTRIBUTING.md in MMFewShot](https://github.com/open-mmlab/mmcv/blob/master/.github/CONTRIBUTING.md) for the contributing guideline.
+We appreciate all contributions to improve mmfewshot. Please refer to [CONTRIBUTING.md in MMFewShot](https://github.com/open-mmlab/mmfewshot/blob/main/.github/CONTRIBUTING.md) for the contributing guideline.
 
 ## Acknowledgement
 
@@ -130,6 +124,8 @@ mmfewshot is an open source project that is contributed by researchers and engin
 - [MMAction2](https://github.com/open-mmlab/mmaction2): OpenMMLab's next-generation action understanding toolbox and benchmark.
 - [MMTracking](https://github.com/open-mmlab/mmtracking): OpenMMLab video perception toolbox and benchmark.
 - [MMPose](https://github.com/open-mmlab/mmpose): OpenMMLab pose estimation toolbox and benchmark.
-- [MMEditing](https://github.com/open-mmlab/mmfewshot): OpenMMLab image and video editing toolbox.
+- [MMEditing](https://github.com/open-mmlab/mmediting): OpenMMLab image and video editing toolbox.
 - [MMOCR](https://github.com/open-mmlab/mmocr): A Comprehensive Toolbox for Text Detection, Recognition and Understanding.
-- [MMGeneration](https://github.com/open-mmlab/mmgeneration): A powerful toolkit for generative models.
+- [MMGeneration](https://github.com/open-mmlab/mmgeneration): OpenMMLab image and video generative models toolbox.
+- [MMFlow](https://github.com/open-mmlab/mmflow): OpenMMLab optical flow toolbox and benchmark.
+- [MMFewShot](https://github.com/open-mmlab/mmfewshot): OpenMMLab FewShot Learning Toolbox and Benchmark.

README_zh-CN.md

@@ -7,19 +7,12 @@
 ## Introduction
 
 [English](README.md) | 简体中文
-
 [![Documentation](https://readthedocs.org/projects/mmfewshot/badge/?version=latest)](https://mmfewshot.readthedocs.io/en/latest/?badge=latest)
-
 [![actions](https://github.com/open-mmlab/mmfewshot/workflows/build/badge.svg)](https://github.com/open-mmlab/mmfewshot/actions)
-
 [![codecov](https://codecov.io/gh/open-mmlab/mmfewshot/branch/master/graph/badge.svg)](https://codecov.io/gh/open-mmlab/mmfewshot)
-
 [![PyPI](https://badge.fury.io/py/mmedit.svg)](https://pypi.org/project/mmedit/)
-
 [![LICENSE](https://img.shields.io/github/license/open-mmlab/mmfewshot.svg)](https://github.com/open-mmlab/mmfewshot/blob/master/LICENSE)
-
 [![Average time to resolve an issue](https://isitmaintained.com/badge/resolution/open-mmlab/mmfewshot.svg)](https://github.com/open-mmlab/mmfewshot/issues)
-
 [![Percentage of issues still open](https://isitmaintained.com/badge/open/open-mmlab/mmfewshot.svg)](https://github.com/open-mmlab/mmfewshot/issues)
 
 MMFewShot 是一款基于 PyTorch 的少样本学习代码库，是 [OpenMMLab](http://openmmlab.org/) 项目的成员之一。
@@ -113,7 +106,7 @@ MMFewShot 也提供了其他更详细的教程，包括：
 
 ## 贡献指南
 
-我们感谢所有的贡献者为改进和提升 MMFewShot 所作出的努力。请参考[贡献指南](https://github.com/open-mmlab/mmcv/blob/master/CONTRIBUTING.md)来了解参与项目贡献的相关指引。
+我们感谢所有的贡献者为改进和提升 MMFewShot 所作出的努力。请参考[贡献指南](https://github.com/open-mmlab/mmfewshot/blob/main/.github/CONTRIBUTING.md)来了解参与项目贡献的相关指引。
 
 
 ## 致谢
@@ -151,6 +144,7 @@ MMFewShot 是一款由不同学校和公司共同贡献的开源项目。我们
 - [MMOCR](https://github.com/open-mmlab/mmocr): OpenMMLab 全流程文字检测识别理解工具包
 - [MMGeneration](https://github.com/open-mmlab/mmgeneration): OpenMMLab 新一代生成模型工具箱
 - [MMFlow](https://github.com/open-mmlab/mmflow): OpenMMLab 光流估计工具箱与测试基准
+- [MMFewShot](https://github.com/open-mmlab/mmfewshot): OpenMMLab 少样本学习工具箱与测试基准
 
 ## 欢迎加入 OpenMMLab 社区
 

configs/classification/README.md

@@ -3,7 +3,7 @@
 
 ## Get Started
 If you're new of mmfewshot, you can check out [Get Started](https://mmfewshot.readthedocs.io/en/latest/index.html)
-and [Classification Tutorials]() to try out MMFewShot.
+and [Classification Tutorials](https://mmfewshot.readthedocs.io/en/latest/classification/index.html) to try out MMFewShot.
 
 ## Data Preparation
 Please follow [DATA Preparation](https://github.com/open-mmlab/mmfewshot/tree/master/tools/data/classification) to prepare data.

configs/detection/README.md

@@ -2,7 +2,7 @@
 
 ## Get Started
 If you're new of mmfewshot, you can check out [Get Started](https://mmfewshot.readthedocs.io/en/latest/index.html)
-and [Detection Tutorials](https://mmfewshot.readthedocs.io/en/latest) to try out MMFewShot.
+and [Detection Tutorials](https://mmfewshot.readthedocs.io/en/latest/detection/index.html) to try out MMFewShot.
 
 ## Data Preparation
 Please follow [DATA Preparation](https://github.com/open-mmlab/mmfewshot/tree/master/tools/data/detection) to prepare data.

docs/classification/customize_config.md

@@ -2,7 +2,7 @@
 
 We incorporate modular and inheritance design into our config system, which is convenient to conduct various experiments.
 If you wish to inspect the config file, you may run `python tools/misc/print_config.py /PATH/TO/CONFIG` to see the complete config.
-The classification part of mmfewshot is built upon the [mmcls](https://mmcv.readthedocs.io/en/latest/understand_mmcv/config.html),
+The classification part of mmfewshot is built upon the [mmcls](https://github.com/open-mmlab/mmclassification),
 thus it is highly recommended learning the basic of mmcls.
 
 
@@ -47,7 +47,6 @@ We follow the below style to name config files. Contributors are advised to foll
 - `{dataset}`: dataset like `cub`, `mini-imagenet` and `tiered-imagenet`.
 - `{meta test setting}`: n way k shot setting like `5way_1shot` or `5way_5shot`.
 
-We follow the config structure of [mmdet](https://mmcv.readthedocs.io/en/latest/understand_mmcv/config.html)
 
 
 

docs/classification/customize_dataset.md

@@ -5,7 +5,7 @@
 ### Customize loading annotations
 
 You can write a new Dataset class inherited from `BaseFewShotDataset`, and overwrite `load_annotations(self)`,
-like [CUB](https://github.com/open-mmlab/mmfewshot/blob/master/mmfewshot/classification/datasets/cub.py) and [MiniImageNet](https://github.com/open-mmlab/mmfewshot/blob/master/mmfewshot/classification/datasets/mini_imagenet.py).
+like [CUB](https://github.com/open-mmlab/mmfewshot/blob/main/mmfewshot/classification/datasets/cub.py) and [MiniImageNet](https://github.com/open-mmlab/mmfewshot/blob/main/mmfewshot/classification/datasets/mini_imagenet.py).
 Typically, this function returns a list, where each sample is a dict, containing necessary data information, e.g., `img` and `gt_label`.
 
 Assume we are going to implement a `Filelist` dataset, which takes filelists for both training and testing. The format of annotation list is as follows:

docs/classification/customize_runtime.md

@@ -114,7 +114,7 @@ Tricks not implemented by the optimizer should be implemented through optimizer
 
 - __Use momentum schedule to accelerate model convergence__:
     We support momentum scheduler to modify model's momentum according to learning rate, which could make the model converge in a faster way.
-    Momentum scheduler is usually used with LR scheduler, for example, the following config is used in 3D classification to accelerate convergence.
+    Momentum scheduler is usually used with LR scheduler, for example, the following config is used in 3D detection to accelerate convergence.
     For more details, please refer to the implementation of [CyclicLrUpdater](https://github.com/open-mmlab/mmcv/blob/f48241a65aebfe07db122e9db320c31b685dc674/mmcv/runner/hooks/lr_updater.py#L327) and [CyclicMomentumUpdater](https://github.com/open-mmlab/mmcv/blob/f48241a65aebfe07db122e9db320c31b685dc674/mmcv/runner/hooks/momentum_updater.py#L130).
 
     ```python

docs/detection/customize_config.md

@@ -2,8 +2,8 @@
 
 We incorporate modular and inheritance design into our config system, which is convenient to conduct various experiments.
 If you wish to inspect the config file, you may run `python tools/misc/print_config.py /PATH/TO/CONFIG` to see the complete config.
-The detection part of mmfewshot is built upon the [mmdet](https://mmcv.readthedocs.io/en/latest/understand_mmcv/config.html),
+The detection part of mmfewshot is built upon the [mmdet](https://github.com/open-mmlab/mmdetection),
-thus it is highly recommended learning the basic of [mmdet](https://mmcv.readthedocs.io/en/latest/understand_mmcv/config.html).
+thus it is highly recommended learning the basic of [mmdet](https://mmdetection.readthedocs.io/en/latest/).
 
 
 ## Modify a config through script arguments

docs/detection/customize_dataset.md

@@ -32,7 +32,7 @@ Unlike few shot classification can test on thousands of tasks in a short time,
 it is hard to follow the same protocol in few shot detection because of the computation cost.
 Thus, we provide the predefined data split for reproducibility.
 These data splits directly use the files released from TFA [repo](https://github.com/ucbdrive/few-shot-object-detection).
-The details of data preparation can refer to [here](https://github.com/open-mmlab/mmfewshot/tree/master/tools/data/detection).
+The details of data preparation can refer to [here](https://github.com/open-mmlab/mmfewshot/tree/main/tools/data/detection).
 
 To load these predefined data splits, the type of dataset need to be set to
 `FewShotVOCDefaultDataset` or `FewShotCocoDefaultDataset`.

docs/install.md

@@ -165,16 +165,18 @@ conda install pytorch==1.7.0 torchvision==0.8.0 torchaudio==0.7.0 cudatoolkit=10
 pip install mmcv-full -f https://download.openmmlab.com/mmcv/dist/cu101/torch1.7.0/index.html
 
 # install mmcls
-git clone https://github.com/open-mmlab/mmdetection.git
+git clone https://github.com/open-mmlab/mmclassification.git
-cd mmdetection
+cd mmclassification
 pip install -r requirements/build.txt
 python setup.py install
+cd ..
 
 # install mmdetection
 git clone https://github.com/open-mmlab/mmdetection.git
 cd mmdetection
 pip install -r requirements/build.txt
 python setup.py install
+cd ..
 
 # install mmfewshot
 git clone https://github.com/open-mmlab/mmfewshot.git
@@ -188,6 +190,6 @@ pip install -v -e .  # or "python setup.py develop"
 
 To verify whether MMFewShot is installed correctly, we can run the demo code and inference a demo image.
 
-Please refer to [few shot classification demo](https://github.com/open-mmlab/mmfewshot/demo/#Few-Shot-Classification-Demo)
+Please refer to [few shot classification demo](https://github.com/open-mmlab/mmfewshot/tree/main/demo#few-shot-classification-demo)
-or [few shot detection demo](https://github.com/open-mmlab/mmfewshot/demo/#Few-Shot-Detection-Demo)
+or [few shot detection demo](https://github.com/open-mmlab/mmfewshot/tree/main/demo#few-shot-detection-demo)
  for more details. The demo code is supposed to run successfully upon you finish the installation.

docs/model_zoo.md

@@ -6,35 +6,35 @@
 
 #### Baseline
 
-Please refer to [Baseline](https://github.com/open-mmlab/mmfewshot/tree/master/configs/classification/baseline) for details.
+Please refer to [Baseline](https://github.com/open-mmlab/mmfewshot/tree/main/configs/classification/baseline) for details.
 
 #### Baseline++
 
-Please refer to [Baseline++](https://github.com/open-mmlab/mmfewshot/tree/master/configs/classification/baseline_plus) for details.
+Please refer to [Baseline++](https://github.com/open-mmlab/mmfewshot/tree/main/configs/classification/baseline_plus) for details.
 
 #### ProtoNet
 
-Please refer to [ProtoNet](https://github.com/open-mmlab/mmfewshot/tree/master/configs/classification/proto_net) for details.
+Please refer to [ProtoNet](https://github.com/open-mmlab/mmfewshot/tree/main/configs/classification/proto_net) for details.
 
 #### RelationNet
 
-Please refer to [RelationNet](https://github.com/open-mmlab/mmfewshot/tree/master/configs/classification/relation_net) for details.
+Please refer to [RelationNet](https://github.com/open-mmlab/mmfewshot/tree/main/configs/classification/relation_net) for details.
 
 #### MatchingNet
 
-Please refer to [MatchingNet](https://github.com/open-mmlab/mmfewshot/tree/master/configs/classification/matching_net) for details.
+Please refer to [MatchingNet](https://github.com/open-mmlab/mmfewshot/tree/main/configs/classification/matching_net) for details.
 
 #### MAML
 
-Please refer to [MAML](https://github.com/open-mmlab/mmfewshot/tree/master/configs/classification/maml) for details.
+Please refer to [MAML](https://github.com/open-mmlab/mmfewshot/tree/main/configs/classification/maml) for details.
 
 #### NegMargin
 
-Please refer to [NegMargin](https://github.com/open-mmlab/mmfewshot/tree/master/configs/classification/neg_margin) for details.
+Please refer to [NegMargin](https://github.com/open-mmlab/mmfewshot/tree/main/configs/classification/neg_margin) for details.
 
 #### Meta Baseline
 
-Please refer to [Meta Baseline](https://github.com/open-mmlab/mmfewshot/tree/master/configs/classification/meta_baseline) for details.
+Please refer to [Meta Baseline](https://github.com/open-mmlab/mmfewshot/tree/main/configs/classification/meta_baseline) for details.
 
 
 
@@ -42,24 +42,24 @@ Please refer to [Meta Baseline](https://github.com/open-mmlab/mmfewshot/tree/mas
 
 #### TFA
 
-Please refer to [TFA](https://github.com/open-mmlab/mmfewshot/tree/master/configs/detection/tfa) for details.
+Please refer to [TFA](https://github.com/open-mmlab/mmfewshot/tree/main/configs/detection/tfa) for details.
 
 #### FSCE
 
-Please refer to [FSCE](https://github.com/open-mmlab/mmfewshot/tree/master/configs/detection/fsce) for details.
+Please refer to [FSCE](https://github.com/open-mmlab/mmfewshot/tree/main/configs/detection/fsce) for details.
 
 #### Meta RCNN
 
-Please refer to [Meta RCNN](https://github.com/open-mmlab/mmfewshot/tree/master/configs/detection/meta_rcnn) for details.
+Please refer to [Meta RCNN](https://github.com/open-mmlab/mmfewshot/tree/main/configs/detection/meta_rcnn) for details.
 
 #### FSDetView
 
-Please refer to [FSDetView](https://github.com/open-mmlab/mmfewshot/tree/master/configs/detection/fsdetview) for details.
+Please refer to [FSDetView](https://github.com/open-mmlab/mmfewshot/tree/main/configs/detection/fsdetview) for details.
 
 #### Attention RPN
 
-Please refer to [Attention RPN](https://github.com/open-mmlab/mmfewshot/tree/master/configs/detection/attention_rpn) for details.
+Please refer to [Attention RPN](https://github.com/open-mmlab/mmfewshot/tree/main/configs/detection/attention_rpn) for details.
 
 #### MPSR
 
-Please refer to [MPSR](https://github.com/open-mmlab/mmfewshot/tree/master/configs/detection/mpsr) for details.
+Please refer to [MPSR](https://github.com/open-mmlab/mmfewshot/tree/main/configs/detection/mpsr) for details.

docs_zh-CN/classification/customize_config.md

@@ -2,7 +2,7 @@
 
 We incorporate modular and inheritance design into our config system, which is convenient to conduct various experiments.
 If you wish to inspect the config file, you may run `python tools/misc/print_config.py /PATH/TO/CONFIG` to see the complete config.
-The classification part of mmfewshot is built upon the [mmcls](https://mmcv.readthedocs.io/en/latest/understand_mmcv/config.html),
+The classification part of mmfewshot is built upon the [mmcls](https://github.com/open-mmlab/mmclassification),
 thus it is highly recommended learning the basic of mmcls.
 
 
@@ -47,7 +47,6 @@ We follow the below style to name config files. Contributors are advised to foll
 - `{dataset}`: dataset like `cub`, `mini-imagenet` and `tiered-imagenet`.
 - `{meta test setting}`: n way k shot setting like `5way_1shot` or `5way_5shot`.
 
-We follow the config structure of [mmdet](https://mmcv.readthedocs.io/en/latest/understand_mmcv/config.html)
 
 
 

docs_zh-CN/classification/customize_dataset.md

@@ -5,7 +5,7 @@
 ### Customize loading annotations
 
 You can write a new Dataset class inherited from `BaseFewShotDataset`, and overwrite `load_annotations(self)`,
-like [CUB](https://github.com/open-mmlab/mmfewshot/blob/master/mmfewshot/classification/datasets/cub.py) and [MiniImageNet](https://github.com/open-mmlab/mmfewshot/blob/master/mmfewshot/classification/datasets/mini_imagenet.py).
+like [CUB](https://github.com/open-mmlab/mmfewshot/blob/main/mmfewshot/classification/datasets/cub.py) and [MiniImageNet](https://github.com/open-mmlab/mmfewshot/blob/main/mmfewshot/classification/datasets/mini_imagenet.py).
 Typically, this function returns a list, where each sample is a dict, containing necessary data information, e.g., `img` and `gt_label`.
 
 Assume we are going to implement a `Filelist` dataset, which takes filelists for both training and testing. The format of annotation list is as follows:

docs_zh-CN/classification/customize_runtime.md

@@ -114,7 +114,7 @@ Tricks not implemented by the optimizer should be implemented through optimizer
 
 - __Use momentum schedule to accelerate model convergence__:
     We support momentum scheduler to modify model's momentum according to learning rate, which could make the model converge in a faster way.
-    Momentum scheduler is usually used with LR scheduler, for example, the following config is used in 3D classification to accelerate convergence.
+    Momentum scheduler is usually used with LR scheduler, for example, the following config is used in 3D detection to accelerate convergence.
     For more details, please refer to the implementation of [CyclicLrUpdater](https://github.com/open-mmlab/mmcv/blob/f48241a65aebfe07db122e9db320c31b685dc674/mmcv/runner/hooks/lr_updater.py#L327) and [CyclicMomentumUpdater](https://github.com/open-mmlab/mmcv/blob/f48241a65aebfe07db122e9db320c31b685dc674/mmcv/runner/hooks/momentum_updater.py#L130).
 
     ```python

docs_zh-CN/detection/customize_config.md

@@ -2,8 +2,8 @@
 
 We incorporate modular and inheritance design into our config system, which is convenient to conduct various experiments.
 If you wish to inspect the config file, you may run `python tools/misc/print_config.py /PATH/TO/CONFIG` to see the complete config.
-The detection part of mmfewshot is built upon the [mmdet](https://mmcv.readthedocs.io/en/latest/understand_mmcv/config.html),
+The detection part of mmfewshot is built upon the [mmdet](https://github.com/open-mmlab/mmdetection),
-thus it is highly recommended learning the basic of [mmdet](https://mmcv.readthedocs.io/en/latest/understand_mmcv/config.html).
+thus it is highly recommended learning the basic of [mmdet](https://mmdetection.readthedocs.io/en/latest/).
 
 
 ## Modify a config through script arguments

docs_zh-CN/detection/customize_dataset.md

@@ -32,7 +32,7 @@ Unlike few shot classification can test on thousands of tasks in a short time,
 it is hard to follow the same protocol in few shot detection because of the computation cost.
 Thus, we provide the predefined data split for reproducibility.
 These data splits directly use the files released from TFA [repo](https://github.com/ucbdrive/few-shot-object-detection).
-The details of data preparation can refer to [here](https://github.com/open-mmlab/mmfewshot/tree/master/tools/data/detection).
+The details of data preparation can refer to [here](https://github.com/open-mmlab/mmfewshot/tree/main/tools/data/detection).
 
 To load these predefined data splits, the type of dataset need to be set to
 `FewShotVOCDefaultDataset` or `FewShotCocoDefaultDataset`.

docs_zh-CN/detection/overview.md

@@ -29,5 +29,3 @@ by `QuerySupportEvalHook`. More implementation details can refer to `mmfewshot.d
 ![](../_static/image/detection_data_flow.jpg)
 
 More usage details and customization can refer to [Tutorial 2: Adding New Dataset](https://mmfewshot.readthedocs.io/en/latest/detection/customize_dataset.html)
-
-## Design of data flow

docs_zh-CN/install.md

@@ -171,16 +171,18 @@ conda install pytorch==1.7.0 torchvision==0.8.0 torchaudio==0.7.0 cudatoolkit=10
 pip install mmcv-full -f https://download.openmmlab.com/mmcv/dist/cu101/torch1.7.0/index.html
 
 # 安装 mmcls
-git clone https://github.com/open-mmlab/mmdetection.git
+git clone https://github.com/open-mmlab/mmclassification.git
-cd mmdetection
+cd mmclassification
 pip install -r requirements/build.txt
 python setup.py install
+cd ..
 
 # 安装 mmdetection
 git clone https://github.com/open-mmlab/mmdetection.git
 cd mmdetection
 pip install -r requirements/build.txt
 python setup.py install
+cd ..
 
 # 安装 mmfewshot
 git clone https://github.com/open-mmlab/mmfewshot.git
@@ -194,6 +196,6 @@ pip install -v -e .  # or "python setup.py develop"
 
 为了验证是否正确安装了 MMFewShot 和所需的环境，我们可以运行示例的 Python 代码在示例图像进行推理：
 
-具体的细节可以参考 [few shot classification demo](https://github.com/open-mmlab/mmfewshot/demo/#Few-Shot-Classification-Demo)
+具体的细节可以参考 [few shot classification demo](https://github.com/open-mmlab/mmfewshot/tree/main/demo#few-shot-classification-demo)
-以及 [few shot detection demo](https://github.com/open-mmlab/mmfewshot/demo/#Few-Shot-Detection-Demo) 。
+以及 [few shot detection demo](https://github.com/open-mmlab/mmfewshot/tree/main/demo#few-shot-detection-demo) 。
 如果成功安装 MMFewShot，则上面的代码可以完整地运行。

docs_zh-CN/model_zoo.md

@@ -6,35 +6,35 @@
 
 #### Baseline
 
-Please refer to [Baseline](https://github.com/open-mmlab/mmfewshot/tree/master/configs/classification/baseline) for details.
+Please refer to [Baseline](https://github.com/open-mmlab/mmfewshot/tree/main/configs/classification/baseline) for details.
 
 #### Baseline++
 
-Please refer to [Baseline++](https://github.com/open-mmlab/mmfewshot/tree/master/configs/classification/baseline_plus) for details.
+Please refer to [Baseline++](https://github.com/open-mmlab/mmfewshot/tree/main/configs/classification/baseline_plus) for details.
 
 #### ProtoNet
 
-Please refer to [ProtoNet](https://github.com/open-mmlab/mmfewshot/tree/master/configs/classification/proto_net) for details.
+Please refer to [ProtoNet](https://github.com/open-mmlab/mmfewshot/tree/main/configs/classification/proto_net) for details.
 
 #### RelationNet
 
-Please refer to [RelationNet](https://github.com/open-mmlab/mmfewshot/tree/master/configs/classification/relation_net) for details.
+Please refer to [RelationNet](https://github.com/open-mmlab/mmfewshot/tree/main/configs/classification/relation_net) for details.
 
 #### MatchingNet
 
-Please refer to [MatchingNet](https://github.com/open-mmlab/mmfewshot/tree/master/configs/classification/matching_net) for details.
+Please refer to [MatchingNet](https://github.com/open-mmlab/mmfewshot/tree/main/configs/classification/matching_net) for details.
 
 #### MAML
 
-Please refer to [MAML](https://github.com/open-mmlab/mmfewshot/tree/master/configs/classification/maml) for details.
+Please refer to [MAML](https://github.com/open-mmlab/mmfewshot/tree/main/configs/classification/maml) for details.
 
 #### NegMargin
 
-Please refer to [NegMargin](https://github.com/open-mmlab/mmfewshot/tree/master/configs/classification/neg_margin) for details.
+Please refer to [NegMargin](https://github.com/open-mmlab/mmfewshot/tree/main/configs/classification/neg_margin) for details.
 
 #### Meta Baseline
 
-Please refer to [Meta Baseline](https://github.com/open-mmlab/mmfewshot/tree/master/configs/classification/meta_baseline) for details.
+Please refer to [Meta Baseline](https://github.com/open-mmlab/mmfewshot/tree/main/configs/classification/meta_baseline) for details.
 
 
 
@@ -42,24 +42,24 @@ Please refer to [Meta Baseline](https://github.com/open-mmlab/mmfewshot/tree/mas
 
 #### TFA
 
-Please refer to [TFA](https://github.com/open-mmlab/mmfewshot/tree/master/configs/detection/tfa) for details.
+Please refer to [TFA](https://github.com/open-mmlab/mmfewshot/tree/main/configs/detection/tfa) for details.
 
 #### FSCE
 
-Please refer to [FSCE](https://github.com/open-mmlab/mmfewshot/tree/master/configs/detection/fsce) for details.
+Please refer to [FSCE](https://github.com/open-mmlab/mmfewshot/tree/main/configs/detection/fsce) for details.
 
 #### Meta RCNN
 
-Please refer to [Meta RCNN](https://github.com/open-mmlab/mmfewshot/tree/master/configs/detection/meta_rcnn) for details.
+Please refer to [Meta RCNN](https://github.com/open-mmlab/mmfewshot/tree/main/configs/detection/meta_rcnn) for details.
 
 #### FSDetView
 
-Please refer to [FSDetView](https://github.com/open-mmlab/mmfewshot/tree/master/configs/detection/fsdetview) for details.
+Please refer to [FSDetView](https://github.com/open-mmlab/mmfewshot/tree/main/configs/detection/fsdetview) for details.
 
 #### Attention RPN
 
-Please refer to [Attention RPN](https://github.com/open-mmlab/mmfewshot/tree/master/configs/detection/attention_rpn) for details.
+Please refer to [Attention RPN](https://github.com/open-mmlab/mmfewshot/tree/main/configs/detection/attention_rpn) for details.
 
 #### MPSR
 
-Please refer to [MPSR](https://github.com/open-mmlab/mmfewshot/tree/master/configs/detection/mpsr) for details.
+Please refer to [MPSR](https://github.com/open-mmlab/mmfewshot/tree/main/configs/detection/mpsr) for details.