zzc98

Add arcface head

2

## Motivation Support [ArcFace loss](https://arxiv.org/abs/1801.07698). ## Checklist **Before PR**: - [ ] Pre-commit or other linting tools are used to fix the potential lint issues. - [ ] Bug fixes...

Support Stanford Car dataset

2

## Motivation Support [Stanford Car dataset](https://ai.stanford.edu/~jkrause/cars/car_dataset.html) . ## Checklist **Before PR**: - [ ] Pre-commit or other linting tools are used to fix the potential lint issues. - [ ]...

## Motivation Support [InShop dataset](https://mmlab.ie.cuhk.edu.hk/projects/DeepFashion/InShopRetrieval.html) . ### Example ``` >>> from mmcls.data import InShop >>> data_root = 'data/stanfordcars' >>> inshop_train_cfg = dict(data_root='data/inshop', mode='train') >>> inshop_train = InShop(**inshop_train_cfg) >>> len(inshop_train) 25882...

[Feature] add reduction for neck

2

## Motivation In some cases, it is necessary to reduce the dimension of extracted feature, so ``Reduction`` is implemented in necks. ## Use cases ```python model = dict( type='ImageClassifier', backbone=dict(...

update metric mAP@k for image retrieval

1

## Motivation Support mAP@k in image retrieval ## Use cases ```python from mmcls.evaluation.metrics import RetrievalAveragePrecision index = torch.Tensor([idx for idx in range(100)]) target = torch.Tensor([0, 3, 6, 8, 35, 101,...

## Experimental results of image retrieval on Google-Lanmark-V2 dataset | set | optim | init lr | epochs | schedule | batch | image size | private | public |...

[Feature] Add Google Landmark v2 retrieval dataset

1

## Motivation Support [Google Landmark v2 retrieval dataset](https://www.kaggle.com/competitions/landmark-retrieval-2019) in 2019. ## Use cases ```python train_pipeline = [ dict(type='LoadImageFromFile'), dict(type='Resize', scale=384), dict(type='RandomCrop', crop_size=336), dict(type='RandomFlip', prob=0.5, direction='horizontal'), dict(type='PackClsInputs'), ] test_pipeline = [...