Ezra-Yu

**This is a PR for mmcls 1.x** ## Motivation upodate dataset tutorial(en/zh_CN). ## Checklist **Before PR**: - [ ] Pre-commit or other linting tools are used to fix the potential...

[Feature] Support EfficientFormer

1

## Motivation Support EfficientFormer, [Arxiv](https://arxiv.org/abs/2206.01191) | [Github](https://github.com/snap-research/EfficientFormer) ## Use cases (Optional) ``` Example: >>> from mmcls.models import EfficientFormer >>> import torch >>> inputs = torch.rand((1, 3, 224, 224)) >>> #...

improve multi label metric

1

**This is a PR for mmcls 1.x** ## Motivation Direct use of CP, CR, CF1, OR, OP, OF1 evaluation criteria ## Modification Add a average mode of 'both' in `MultiLabelMetric`....

### Describe the feature Support EdgeNeXt

This issue will participate in the [chinese GLCC activity](https://mp.weixin.qq.com/s/yBem9JTrPI5OKWqunUQWAQ). So I wrote it in Chinese: ## 题目名称 基于 MMCLS，实现 Google-landmark 数据集上的图像检索功能 ## 题目描述 ### 题目简介 MMClassification 是一款基于 PyTorch 的开源图像分类工具箱。 在...

[Doc] Using backbone giude

1

## Motivation Using backbone guides; ## Checklist **Before PR**: - [x] Pre-commit or other linting tools are used to fix the potential lint issues. - [x] Bug fixes are fully...

## Motivation Reproduce training results of ResNet in torchvision refer to [link](https://pytorch.org/blog/how-to-train-state-of-the-art-models-using-torchvision-latest-primitives) ## Checklist **Before PR**: - [ ] Pre-commit or other linting tools are used to fix the potential...

Hope to implement RMNet in MMClassification.

1

Hello, I am the developer of [MMClassification](https://github.com/open-mmlab/mmclassification). Some users find your great job and hope MMClassification to reproduce it in this [issue](https://github.com/open-mmlab/mmclassification/issues/517). Since we are relatively in a hurry in...

[Feature] Add MobileOne Backbone

2

## Motivation Add MobileOne backbone, [Paper](https://arxiv.org/abs/2206.04040) [Github](https://github.com/apple/ml-mobileone) ## Note *Because the [official repo.](https://github.com/apple/ml-mobileone) does not give a strategy for training and testing, the test data pipline of [RepVGG](https://github.com/open-mmlab/mmclassification/tree/master/configs/repvgg) is used...

精度如何

1

直接在ImageNet-1k数据集上训练，精度如何？