{"id":101697,"url":"https://github.com/fafa-dl/awesome-backbones","name":"awesome-backbones","description":"Integrate deep learning models for image classification | Backbone learning/comparison/magic modification project","projects_count":82,"last_synced_at":"2026-06-12T09:00:25.980Z","repository":{"id":37722130,"uuid":"444318559","full_name":"Fafa-DL/Awesome-Backbones","owner":"Fafa-DL","description":"Integrate deep learning models for image classification | Backbone learning/comparison/magic modification project","archived":false,"fork":false,"pushed_at":"2025-01-17T02:27:19.000Z","size":60666,"stargazers_count":1940,"open_issues_count":9,"forks_count":273,"subscribers_count":29,"default_branch":"main","last_synced_at":"2026-05-26T18:04:15.528Z","etag":null,"topics":["cnn","deep-learning","image-classification","pytorch","pytorch-classification","resnet","swin-transformer","transformer"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Fafa-DL.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2022-01-04T07:00:57.000Z","updated_at":"2026-05-26T13:02:14.000Z","dependencies_parsed_at":"2026-01-16T09:05:41.330Z","dependency_job_id":null,"html_url":"https://github.com/Fafa-DL/Awesome-Backbones","commit_stats":null,"previous_names":[],"tags_count":5,"template":false,"template_full_name":null,"purl":"pkg:github/Fafa-DL/Awesome-Backbones","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Fafa-DL%2FAwesome-Backbones","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Fafa-DL%2FAwesome-Backbones/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Fafa-DL%2FAwesome-Backbones/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Fafa-DL%2FAwesome-Backbones/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Fafa-DL","download_url":"https://codeload.github.com/Fafa-DL/Awesome-Backbones/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Fafa-DL%2FAwesome-Backbones/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34236552,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-12T02:00:06.859Z","response_time":109,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"created_at":"2025-12-29T22:05:00.131Z","updated_at":"2026-06-12T09:00:25.980Z","primary_language":null,"list_of_lists":false,"displayable":true,"categories":["模型","写在前面","更新日志","资料","快速开始","教程","预训练权重","我维护的其他项目"],"sub_categories":[],"readme":"Awesome backbones for image classification\n===========================\n\n\u003cdiv align=\"center\"\u003e\n\n[![BILIBILI](https://raw.githubusercontent.com/Fafa-DL/readme-data/main/Bilibili.png)](https://space.bilibili.com/46880349)\n\n![](https://img.shields.io/badge/Awesome%20Backbones-v0.6.3-brightgreen)\n![](https://img.shields.io/badge/PyTorch-%3E%3Dv1.7.1-green)\n![](https://img.shields.io/badge/Python-%3E%3Dv3.6-yellowgreen)\n[![GitHub forks](https://img.shields.io/github/forks/Fafa-DL/Awesome-Backbones)](https://github.com/Fafa-DL/Awesome-Backbones)\n[![GitHub stars](https://img.shields.io/github/stars/Fafa-DL/Awesome-Backbones)](https://github.com/Fafa-DL/Awesome-Backbones)\n\n\u003c/div\u003e\n\n## 写在前面\n- 若训练效果不佳，首先需要调整学习率和Batch size，这俩超参很大程度上影响收敛。其次，从关闭图像增强手段（尤其小数据集）开始，有的图像增强方法会污染数据，如\n\n![](https://raw.githubusercontent.com/Fafa-DL/readme-data/main/backbones/fail01.jpg) ![](https://raw.githubusercontent.com/Fafa-DL/readme-data/main/backbones/fail02.jpg) ![](https://raw.githubusercontent.com/Fafa-DL/readme-data/main/backbones/fail03.jpg)\n\n\u0026emsp;\u0026emsp;如何去除增强？如[efficientnetv2-b0](https://github.com/Fafa-DL/Awesome-Backbones/blob/main/models/efficientnetv2/efficientnetv2_b0.py)配置文件中train_pipeline可更改为如下\n```yaml\ntrain_pipeline = [\n    dict(type='LoadImageFromFile'),\n    dict(\n        type='RandomResizedCrop',\n        size=192,\n        efficientnet_style=True,\n        interpolation='bicubic'),\n    dict(type='Normalize', **img_norm_cfg),\n    dict(type='ImageToTensor', keys=['img']),\n    dict(type='ToTensor', keys=['gt_label']),\n    dict(type='Collect', keys=['img', 'gt_label'])\n]\n```\n\u0026emsp;\u0026emsp;若你的数据集提前已经将shape更改为网络要求的尺寸，那么`Resize`操作也可以去除。\n\n## 更新日志\n\n**`2025.01.17`** \n- 支持转ONNX[#136](https://github.com/Fafa-DL/Awesome-Backbones/pull/136) @PurpleSky-NS\n- 类别激活图相关脚本[#114](https://github.com/Fafa-DL/Awesome-Backbones/pull/114) @jackyjinjing\n\n**`2024.09.06`** \n- 修复高频反馈的**评估时结果浮动大**的问题\n\n**`2023.12.02`** \n- 新增Issue中多人提及的输出**Train Acc**与**Val loss**\n    - `metrics_outputs.csv`保存每周期`train_loss, train_acc, train_precision, train_recall, train_f1-score, val_loss, val_acc, val_precision, val_recall, val_f1-score`方便各位绘图\n    - 终端由原先仅输出**Val**相关metrics升级为Train与Val都输出\n\n    ![](https://raw.githubusercontent.com/Fafa-DL/readme-data/main/backbones/terminal.jpg)\n\n**`2023.08.05`** \n- 新增**TinyViT**(预训练权重不匹配)、**DeiT3**、**EdgeNeXt**、**RevVisionTransformer**\n\n**`2023.03.07`** \n- 新增**MobileViT**、**DaViT**、**RepLKNet**、**BEiT**、**EVA**、**MixMIM**、**EfficientNetV2**\n\n\n## 测试环境\n\n- Pytorch      1.7.1+\n- Python       3.6+\n\n## 资料\n|数据集|视频教程|人工智能技术探讨群|\n|---|---|---|\n|[`花卉数据集` 提取码：0zat](https://pan.baidu.com/s/1137y4l-J3AgyCiC_cXqIqw)|[点我跳转](https://www.bilibili.com/video/BV1SY411P7Nd)|[1群：78174903](https://jq.qq.com/?_wv=1027\u0026k=lY5KVICA)\u003cbr/\u003e[3群：584723646](https://jq.qq.com/?_wv=1027\u0026k=bakez5Yz)\n\n## 快速开始\n\n- 遵循[环境搭建](https://github.com/Fafa-DL/Awesome-Backbones/blob/main/datas/docs/Environment_setting.md)完成配置\n- 下载[MobileNetV3-Small](https://download.openmmlab.com/mmclassification/v0/mobilenet_v3/convert/mobilenet_v3_small-8427ecf0.pth)权重至**datas**下\n- **Awesome-Backbones**文件夹下终端输入\n```bash\npython tools/single_test.py datas/cat-dog.png models/mobilenet/mobilenet_v3_small.py --classes-map datas/imageNet1kAnnotation.txt\n```\n\n## 教程\n- [环境搭建](https://github.com/Fafa-DL/Awesome-Backbones/blob/main/datas/docs/Environment_setting.md)\n- [数据集准备](https://github.com/Fafa-DL/Awesome-Backbones/blob/main/datas/docs/Data_preparing.md)\n- [配置文件解释](https://github.com/Fafa-DL/Awesome-Backbones/blob/main/datas/docs/Configs_description.md)\n- [训练](https://github.com/Fafa-DL/Awesome-Backbones/blob/main/datas/docs/How_to_train.md)\n- [模型评估](https://github.com/Fafa-DL/Awesome-Backbones/blob/main/datas/docs/How_to_eval.md)\n- [计算Flops\u0026Params](https://github.com/Fafa-DL/Awesome-Backbones/blob/main/datas/docs/Calculate_Flops.md)\n- [添加新的模型组件](https://github.com/Fafa-DL/Awesome-Backbones/blob/main/datas/docs/Add_modules.md)\n- [类别激活图可视化](https://github.com/Fafa-DL/Awesome-Backbones/blob/main/datas/docs/CAM_visualization.md)\n- [学习率策略可视化](https://github.com/Fafa-DL/Awesome-Backbones/blob/main/datas/docs/Lr_visualization.md)\n- [数据增强策略可视化](https://github.com/Fafa-DL/Awesome-Backbones/blob/main/datas/docs/Pipeline_visualization.md)\n\n## 模型\n- [x] [LeNet5](https://ieeexplore.ieee.org/document/6795724)\n- [x] [AlexNet](https://blog.csdn.net/zzh516451964zzh/article/details/124461111)\n- [x] [VGG](https://blog.csdn.net/zzh516451964zzh/article/details/124477080)\n- [x] [DenseNet](https://blog.csdn.net/zzh516451964zzh/article/details/124630832)\n- [x] [ResNet](https://blog.csdn.net/zzh516451964zzh/article/details/124477575)\n- [x] [Wide-ResNet](https://blog.csdn.net/zzh516451964zzh/article/details/124754437)\n- [x] [ResNeXt](https://blog.csdn.net/zzh516451964zzh/article/details/124477919)\n- [x] [SEResNet](https://blog.csdn.net/zzh516451964zzh/article/details/124478157)\n- [x] [SEResNeXt](https://blog.csdn.net/zzh516451964zzh/article/details/124478347)\n- [x] [RegNet](https://blog.csdn.net/zzh516451964zzh/article/details/124478426)\n- [x] [MobileNetV2](https://blog.csdn.net/zzh516451964zzh/article/details/124478681)\n- [x] [MobileNetV3](https://blog.csdn.net/zzh516451964zzh/article/details/124478770)\n- [x] [ShuffleNetV1](https://blog.csdn.net/zzh516451964zzh/article/details/124479156)\n- [x] [ShuffleNetV2](https://blog.csdn.net/zzh516451964zzh/article/details/124479336)\n- [x] [EfficientNet](https://blog.csdn.net/zzh516451964zzh/article/details/124754493)\n- [x] [RepVGG](https://blog.csdn.net/zzh516451964zzh/article/details/124479644)\n- [x] [Res2Net](https://blog.csdn.net/zzh516451964zzh/article/details/124479467)\n- [x] [ConvNeXt](https://blog.csdn.net/zzh516451964zzh/article/details/124481466)\n- [x] [HRNet](https://blog.csdn.net/zzh516451964zzh/article/details/124481590)\n- [x] [ConvMixer](https://blog.csdn.net/zzh516451964zzh/article/details/124481766)\n- [x] [CSPNet](https://blog.csdn.net/zzh516451964zzh/article/details/124481930)\n- [x] [Swin-Transformer](https://blog.csdn.net/zzh516451964zzh/article/details/124538198)\n- [x] [Vision-Transformer](https://blog.csdn.net/zzh516451964zzh/article/details/124567953)\n- [x] [Transformer-in-Transformer](https://blog.csdn.net/zzh516451964zzh/article/details/124596023)\n- [x] [MLP-Mixer](https://blog.csdn.net/zzh516451964zzh/article/details/124596093)\n- [x] [DeiT](https://blog.csdn.net/zzh516451964zzh/article/details/124591888)\n- [x] [Conformer](https://blog.csdn.net/zzh516451964zzh/article/details/124596343)\n- [x] [T2T-ViT](https://blog.csdn.net/zzh516451964zzh/article/details/124596425)\n- [x] [Twins](https://blog.csdn.net/zzh516451964zzh/article/details/124596619)\n- [x] [PoolFormer](https://blog.csdn.net/zzh516451964zzh/article/details/124596740)\n- [x] [VAN](https://blog.csdn.net/zzh516451964zzh/article/details/124630541)\n- [x] [HorNet](https://arxiv.org/pdf/2207.14284v2.pdf)\n- [x] [EfficientFormer](https://arxiv.org/abs/2206.01191)\n- [x] [Swin Transformer V2](https://arxiv.org/abs/2111.09883.pdf)\n- [x] [MViT V2](http://openaccess.thecvf.com//content/CVPR2022/papers/Li_MViTv2_Improved_Multiscale_Vision_Transformers_for_Classification_and_Detection_CVPR_2022_paper.pdf)\n- [x] [MobileViT](https://arxiv.org/abs/2110.02178)\n- [x] [DaViT](https://arxiv.org/abs/2204.03645v1)\n- [x] [replknet](https://arxiv.org/abs/2203.06717)\n- [x] [BEiT](https://arxiv.org/abs/2106.08254)\n- [x] [EVA](https://arxiv.org/abs/2211.07636)\n- [x] [MixMIM](https://arxiv.org/abs/2205.13137)\n- [x] [EfficientNetV2](https://arxiv.org/abs/2104.00298)\n## 预训练权重\n\n| 名称 | 权重 | 名称 | 权重 | 名称 | 权重 |\n| :-----: | :-----: | :------: | :------: | :------: | :-----: |\n| **LeNet5** | None | **AlexNet** | None | **VGG** | [VGG-11](https://download.openmmlab.com/mmclassification/v0/vgg/vgg11_batch256_imagenet_20210208-4271cd6c.pth)\u003cbr/\u003e[VGG-13](https://download.openmmlab.com/mmclassification/v0/vgg/vgg13_batch256_imagenet_20210208-4d1d6080.pth)\u003cbr/\u003e[VGG-16](https://download.openmmlab.com/mmclassification/v0/vgg/vgg16_batch256_imagenet_20210208-db26f1a5.pth)\u003cbr/\u003e[VGG-19](https://download.openmmlab.com/mmclassification/v0/vgg/vgg19_batch256_imagenet_20210208-e6920e4a.pth)\u003cbr/\u003e[VGG-11-BN](https://download.openmmlab.com/mmclassification/v0/vgg/vgg11_bn_batch256_imagenet_20210207-f244902c.pth)\u003cbr/\u003e[VGG-13-BN](https://download.openmmlab.com/mmclassification/v0/vgg/vgg13_bn_batch256_imagenet_20210207-1a8b7864.pth)\u003cbr/\u003e[VGG-16-BN](https://download.openmmlab.com/mmclassification/v0/vgg/vgg16_bn_batch256_imagenet_20210208-7e55cd29.pth)\u003cbr/\u003e[VGG-19-BN](https://download.openmmlab.com/mmclassification/v0/vgg/vgg19_bn_batch256_imagenet_20210208-da620c4f.pth)|\n| **ResNet** |[ResNet-18](https://download.openmmlab.com/mmclassification/v0/resnet/resnet18_8xb32_in1k_20210831-fbbb1da6.pth)\u003cbr/\u003e[ResNet-34](https://download.openmmlab.com/mmclassification/v0/resnet/resnet34_8xb32_in1k_20210831-f257d4e6.pth)\u003cbr/\u003e[ResNet-50](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_8xb32_in1k_20210831-ea4938fc.pth)\u003cbr/\u003e[ResNet-101](https://download.openmmlab.com/mmclassification/v0/resnet/resnet101_8xb32_in1k_20210831-539c63f8.pth)\u003cbr/\u003e[ResNet-152](https://download.openmmlab.com/mmclassification/v0/resnet/resnet152_8xb32_in1k_20210901-4d7582fa.pth) | **ResNetV1C** | [ResNetV1C-50](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1c50_8xb32_in1k_20220214-3343eccd.pth)\u003cbr/\u003e[ResNetV1C-101](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1c101_8xb32_in1k_20220214-434fe45f.pth)\u003cbr/\u003e[ResNetV1C-152](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1c152_8xb32_in1k_20220214-c013291f.pth) |**ResNetV1D** | [ResNetV1D-50](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d50_b32x8_imagenet_20210531-db14775a.pth)\u003cbr/\u003e[ResNetV1D-101](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d101_b32x8_imagenet_20210531-6e13bcd3.pth)\u003cbr/\u003e[ResNetV1D-152](https://download.openmmlab.com/mmclassification/v0/resnet/resnetv1d152_b32x8_imagenet_20210531-278cf22a.pth) |\n| **ResNeXt** | [ResNeXt-50](https://download.openmmlab.com/mmclassification/v0/resnext/resnext50_32x4d_b32x8_imagenet_20210429-56066e27.pth)\u003cbr/\u003e[ResNeXt-101](https://download.openmmlab.com/mmclassification/v0/resnext/resnext101_32x4d_b32x8_imagenet_20210506-e0fa3dd5.pth)\u003cbr/\u003e[ResNeXt-152](https://download.openmmlab.com/mmclassification/v0/resnext/resnext152_32x4d_b32x8_imagenet_20210524-927787be.pth) | **SEResNet** | [SEResNet-50](https://download.openmmlab.com/mmclassification/v0/se-resnet/se-resnet50_batch256_imagenet_20200804-ae206104.pth)\u003cbr/\u003e[SEResNet-101](https://download.openmmlab.com/mmclassification/v0/se-resnet/se-resnet101_batch256_imagenet_20200804-ba5b51d4.pth)| **SEResNeXt**| None|\n| **RegNet** |[RegNetX-400MF](https://download.openmmlab.com/mmclassification/v0/regnet/regnetx-400mf_8xb128_in1k_20211213-89bfc226.pth)\u003cbr/\u003e[RegNetX-800MF](https://download.openmmlab.com/mmclassification/v0/regnet/regnetx-800mf_8xb128_in1k_20211213-222b0f11.pth)\u003cbr/\u003e[RegNetX-1.6GF](https://download.openmmlab.com/mmclassification/v0/regnet/regnetx-1.6gf_8xb128_in1k_20211213-d1b89758.pth)\u003cbr/\u003e[RegNetX-3.2GF](https://download.openmmlab.com/mmclassification/v0/regnet/regnetx-3.2gf_8xb64_in1k_20211213-1fdd82ae.pth)\u003cbr/\u003e[RegNetX-4.0GF](https://download.openmmlab.com/mmclassification/v0/regnet/regnetx-4.0gf_8xb64_in1k_20211213-efed675c.pth)\u003cbr/\u003e[RegNetX-6.4GF](https://download.openmmlab.com/mmclassification/v0/regnet/regnetx-6.4gf_8xb64_in1k_20211215-5c6089da.pth)\u003cbr/\u003e[RegNetX-8.0GF](https://download.openmmlab.com/mmclassification/v0/regnet/regnetx-8.0gf_8xb64_in1k_20211213-9a9fcc76.pth)\u003cbr/\u003e[RegNetX-12GF](https://download.openmmlab.com/mmclassification/v0/regnet/regnetx-12gf_8xb64_in1k_20211213-5df8c2f8.pth) | **MobileNetV2** | [MobileNetV2](https://download.openmmlab.com/mmclassification/v0/mobilenet_v2/mobilenet_v2_batch256_imagenet_20200708-3b2dc3af.pth) |**MobileNetV3** | [MobileNetV3-Small](https://download.openmmlab.com/mmclassification/v0/mobilenet_v3/convert/mobilenet_v3_small-8427ecf0.pth)\u003cbr/\u003e[MobileNetV3-Large](https://download.openmmlab.com/mmclassification/v0/mobilenet_v3/convert/mobilenet_v3_large-3ea3c186.pth) |\n| **ShuffleNetV1** |[ShuffleNetV1](https://download.openmmlab.com/mmclassification/v0/shufflenet_v1/shufflenet_v1_batch1024_imagenet_20200804-5d6cec73.pth) | **ShuffleNetV2** | [ShuffleNetV2](https://download.openmmlab.com/mmclassification/v0/shufflenet_v2/shufflenet_v2_batch1024_imagenet_20200812-5bf4721e.pth) |**EfficientNet** | [EfficientNet-B0](https://download.openmmlab.com/mmclassification/v0/efficientnet/efficientnet-b0_3rdparty_8xb32_in1k_20220119-a7e2a0b1.pth)\u003cbr/\u003e[EfficientNet-B1](https://download.openmmlab.com/mmclassification/v0/efficientnet/efficientnet-b1_3rdparty_8xb32_in1k_20220119-002556d9.pth)\u003cbr/\u003e[EfficientNet-B2](https://download.openmmlab.com/mmclassification/v0/efficientnet/efficientnet-b2_3rdparty_8xb32_in1k_20220119-ea374a30.pth)\u003cbr/\u003e[EfficientNet-B3](https://download.openmmlab.com/mmclassification/v0/efficientnet/efficientnet-b3_3rdparty_8xb32_in1k_20220119-4b4d7487.pth)\u003cbr/\u003e[EfficientNet-B4](https://download.openmmlab.com/mmclassification/v0/efficientnet/efficientnet-b4_3rdparty_8xb32_in1k_20220119-81fd4077.pth)\u003cbr/\u003e[EfficientNet-B5](https://download.openmmlab.com/mmclassification/v0/efficientnet/efficientnet-b5_3rdparty_8xb32_in1k_20220119-e9814430.pth)\u003cbr/\u003e[EfficientNet-B6](https://download.openmmlab.com/mmclassification/v0/efficientnet/efficientnet-b6_3rdparty_8xb32-aa_in1k_20220119-45b03310.pth)\u003cbr/\u003e[EfficientNet-B7](https://download.openmmlab.com/mmclassification/v0/efficientnet/efficientnet-b7_3rdparty_8xb32-aa_in1k_20220119-bf03951c.pth)\u003cbr/\u003e[EfficientNet-B8](https://download.openmmlab.com/mmclassification/v0/efficientnet/efficientnet-b8_3rdparty_8xb32-aa-advprop_in1k_20220119-297ce1b7.pth) |\n| **RepVGG** |[RepVGG-A0](https://download.openmmlab.com/mmclassification/v0/repvgg/repvgg-A0_3rdparty_4xb64-coslr-120e_in1k_20210909-883ab98c.pth)\u003cbr/\u003e[RepVGG-A1](https://download.openmmlab.com/mmclassification/v0/repvgg/repvgg-A1_3rdparty_4xb64-coslr-120e_in1k_20210909-24003a24.pth) \u003cbr/\u003e[RepVGG-A2](https://download.openmmlab.com/mmclassification/v0/repvgg/repvgg-A2_3rdparty_4xb64-coslr-120e_in1k_20210909-97d7695a.pth)\u003cbr/\u003e[RepVGG-B0](https://download.openmmlab.com/mmclassification/v0/repvgg/repvgg-B0_3rdparty_4xb64-coslr-120e_in1k_20210909-446375f4.pth)\u003cbr/\u003e[RepVGG-B1](https://download.openmmlab.com/mmclassification/v0/repvgg/repvgg-B1_3rdparty_4xb64-coslr-120e_in1k_20210909-750cdf67.pth)\u003cbr/\u003e[RepVGG-A1](https://download.openmmlab.com/mmclassification/v0/repvgg/repvgg-A1_3rdparty_4xb64-coslr-120e_in1k_20210909-24003a24.pth)\u003cbr/\u003e[RepVGG-B1g2](https://download.openmmlab.com/mmclassification/v0/repvgg/repvgg-B1g2_3rdparty_4xb64-coslr-120e_in1k_20210909-344f6422.pth)\u003cbr/\u003e[RepVGG-B1g4](https://download.openmmlab.com/mmclassification/v0/repvgg/repvgg-B1g4_3rdparty_4xb64-coslr-120e_in1k_20210909-d4c1a642.pth)\u003cbr/\u003e[RepVGG-B2](https://download.openmmlab.com/mmclassification/v0/repvgg/repvgg-B2_3rdparty_4xb64-coslr-120e_in1k_20210909-bd6b937c.pth)\u003cbr/\u003e[RepVGG-B2g4](https://download.openmmlab.com/mmclassification/v0/repvgg/repvgg-B2g4_3rdparty_4xb64-autoaug-lbs-mixup-coslr-200e_in1k_20210909-7b7955f0.pth)\u003cbr/\u003e[RepVGG-B2g4](https://download.openmmlab.com/mmclassification/v0/repvgg/repvgg-B2g4_3rdparty_4xb64-autoaug-lbs-mixup-coslr-200e_in1k_20210909-7b7955f0.pth)\u003cbr/\u003e[RepVGG-B3](https://download.openmmlab.com/mmclassification/v0/repvgg/repvgg-B3_3rdparty_4xb64-autoaug-lbs-mixup-coslr-200e_in1k_20210909-dda968bf.pth)\u003cbr/\u003e[RepVGG-B3g4](https://download.openmmlab.com/mmclassification/v0/repvgg/repvgg-B3g4_3rdparty_4xb64-autoaug-lbs-mixup-coslr-200e_in1k_20210909-4e54846a.pth)\u003cbr/\u003e[RepVGG-D2se](https://download.openmmlab.com/mmclassification/v0/repvgg/repvgg-D2se_3rdparty_4xb64-autoaug-lbs-mixup-coslr-200e_in1k_20210909-cf3139b7.pth)| **Res2Net** | [Res2Net-50-14w-8s](https://download.openmmlab.com/mmclassification/v0/res2net/res2net50-w14-s8_3rdparty_8xb32_in1k_20210927-bc967bf1.pth)\u003cbr/\u003e[Res2Net-50-26w-8s](https://download.openmmlab.com/mmclassification/v0/res2net/res2net50-w26-s8_3rdparty_8xb32_in1k_20210927-f547a94b.pth)\u003cbr/\u003e[Res2Net-101-26w-4s](https://download.openmmlab.com/mmclassification/v0/res2net/res2net101-w26-s4_3rdparty_8xb32_in1k_20210927-870b6c36.pth)\u003cbr/\u003e |**ConvNeXt** | [ConvNeXt-Tiny](https://download.openmmlab.com/mmclassification/v0/convnext/convnext-tiny_3rdparty_32xb128_in1k_20220124-18abde00.pth)\u003cbr/\u003e[ConvNeXt-Small](https://download.openmmlab.com/mmclassification/v0/convnext/convnext-small_3rdparty_32xb128_in1k_20220124-d39b5192.pth)\u003cbr/\u003e[ConvNeXt-Base](https://download.openmmlab.com/mmclassification/v0/convnext/convnext-base_in21k-pre-3rdparty_32xb128_in1k_20220124-eb2d6ada.pth)\u003cbr/\u003e[ConvNeXt-Large](https://download.openmmlab.com/mmclassification/v0/convnext/convnext-large_in21k-pre-3rdparty_64xb64_in1k_20220124-2412403d.pth)\u003cbr/\u003e[ConvNeXt-XLarge](https://download.openmmlab.com/mmclassification/v0/convnext/convnext-xlarge_in21k-pre-3rdparty_64xb64_in1k_20220124-76b6863d.pth) |\n| **HRNet** |[HRNet-W18](https://download.openmmlab.com/mmclassification/v0/hrnet/hrnet-w18_3rdparty_8xb32_in1k_20220120-0c10b180.pth)\u003cbr/\u003e[HRNet-W30](https://download.openmmlab.com/mmclassification/v0/hrnet/hrnet-w30_3rdparty_8xb32_in1k_20220120-8aa3832f.pth) \u003cbr/\u003e[HRNet-W32](https://download.openmmlab.com/mmclassification/v0/hrnet/hrnet-w32_3rdparty_8xb32_in1k_20220120-c394f1ab.pth)\u003cbr/\u003e[HRNet-W40](https://download.openmmlab.com/mmclassification/v0/hrnet/hrnet-w40_3rdparty_8xb32_in1k_20220120-9a2dbfc5.pth)\u003cbr/\u003e[HRNet-W44](https://download.openmmlab.com/mmclassification/v0/hrnet/hrnet-w44_3rdparty_8xb32_in1k_20220120-35d07f73.pth)\u003cbr/\u003e[HRNet-W48](https://download.openmmlab.com/mmclassification/v0/hrnet/hrnet-w48_3rdparty_8xb32_in1k_20220120-e555ef50.pth)\u003cbr/\u003e[HRNet-W64](https://download.openmmlab.com/mmclassification/v0/hrnet/hrnet-w64_3rdparty_8xb32_in1k_20220120-19126642.pth) | **ConvMixer** | [ConvMixer-768/32](https://download.openmmlab.com/mmclassification/v0/convmixer/convmixer-768-32_3rdparty_10xb64_in1k_20220323-bca1f7b8.pth)\u003cbr/\u003e[ConvMixer-1024/20](https://download.openmmlab.com/mmclassification/v0/convmixer/convmixer-1024-20_3rdparty_10xb64_in1k_20220323-48f8aeba.pth)\u003cbr/\u003e[ConvMixer-1536/20](https://download.openmmlab.com/mmclassification/v0/convmixer/convmixer-1536_20_3rdparty_10xb64_in1k_20220323-ea5786f3.pth) |**CSPNet** | [CSPDarkNet50](https://download.openmmlab.com/mmclassification/v0/cspnet/cspdarknet50_3rdparty_8xb32_in1k_20220329-bd275287.pth)\u003cbr/\u003e[CSPResNet50](https://download.openmmlab.com/mmclassification/v0/cspnet/cspresnet50_3rdparty_8xb32_in1k_20220329-dd6dddfb.pth)\u003cbr/\u003e[CSPResNeXt50](https://download.openmmlab.com/mmclassification/v0/cspnet/cspresnext50_3rdparty_8xb32_in1k_20220329-2cc84d21.pth) |\n|**Swin Transformer**|[tiny-224](https://download.openmmlab.com/mmclassification/v0/swin-transformer/swin_tiny_224_b16x64_300e_imagenet_20210616_090925-66df6be6.pth)\u003cbr/\u003e[small-224](https://download.openmmlab.com/mmclassification/v0/swin-transformer/swin_small_224_b16x64_300e_imagenet_20210615_110219-7f9d988b.pth)\u003cbr/\u003e[base-224](https://download.openmmlab.com/mmclassification/v0/swin-transformer/swin_base_224_b16x64_300e_imagenet_20210616_190742-93230b0d.pth)\u003cbr/\u003e[large-224](https://download.openmmlab.com/mmclassification/v0/swin-transformer/convert/swin_large_patch4_window7_224_22kto1k-5f0996db.pth)\u003cbr/\u003e[base-384](https://download.openmmlab.com/mmclassification/v0/swin-transformer/convert/swin_base_patch4_window12_384_22kto1k-d59b0d1d.pth)\u003cbr/\u003e[large-384](https://download.openmmlab.com/mmclassification/v0/swin-transformer/convert/swin_large_patch4_window12_384_22kto1k-0a40944b.pth)|**Vision Transformer**|[vit_base_p16_224](https://download.openmmlab.com/mmclassification/v0/vit/pretrain/vit-base-p16_3rdparty_pt-64xb64_in1k-224_20210928-02284250.pth)\u003cbr/\u003e[vit_base_p32_224](https://download.openmmlab.com/mmclassification/v0/vit/pretrain/vit-base-p32_3rdparty_pt-64xb64_in1k-224_20210928-eee25dd4.pth)\u003cbr/\u003e[vit_large_p16_224](https://download.openmmlab.com/mmclassification/v0/vit/pretrain/vit-large-p16_3rdparty_pt-64xb64_in1k-224_20210928-0001f9a1.pth)\u003cbr/\u003e[vit_base_p16_384](https://download.openmmlab.com/mmclassification/v0/vit/finetune/vit-base-p16_in21k-pre-3rdparty_ft-64xb64_in1k-384_20210928-98e8652b.pth)\u003cbr/\u003e[vit_base_p32_384](https://download.openmmlab.com/mmclassification/v0/vit/finetune/vit-base-p32_in21k-pre-3rdparty_ft-64xb64_in1k-384_20210928-9cea8599.pth)\u003cbr/\u003e[vit_large_p16_384](https://download.openmmlab.com/mmclassification/v0/vit/finetune/vit-large-p16_in21k-pre-3rdparty_ft-64xb64_in1k-384_20210928-b20ba619.pth)|**Transformer in Transformer**|[TNT-small](https://download.openmmlab.com/mmclassification/v0/tnt/tnt-small-p16_3rdparty_in1k_20210903-c56ee7df.pth)|\n|**MLP Mixer**|[base_p16](https://download.openmmlab.com/mmclassification/v0/mlp-mixer/mixer-base-p16_3rdparty_64xb64_in1k_20211124-1377e3e0.pth)\u003cbr/\u003e[large_p16](https://download.openmmlab.com/mmclassification/v0/mlp-mixer/mixer-large-p16_3rdparty_64xb64_in1k_20211124-5a2519d2.pth)|**Deit**|[DeiT-tiny](https://download.openmmlab.com/mmclassification/v0/deit/deit-tiny_pt-4xb256_in1k_20220218-13b382a0.pth)\u003cbr/\u003e[DeiT-tiny distilled](https://download.openmmlab.com/mmclassification/v0/deit/deit-tiny-distilled_3rdparty_pt-4xb256_in1k_20211216-c429839a.pth)\u003cbr/\u003e[DeiT-small](https://download.openmmlab.com/mmclassification/v0/deit/deit-small_pt-4xb256_in1k_20220218-9425b9bb.pth)\u003cbr/\u003e[DeiT-small distilled](https://download.openmmlab.com/mmclassification/v0/deit/deit-small-distilled_3rdparty_pt-4xb256_in1k_20211216-4de1d725.pth)\u003cbr/\u003e[DeiT-base](https://download.openmmlab.com/mmclassification/v0/deit/deit-base_pt-16xb64_in1k_20220216-db63c16c.pth)\u003cbr/\u003e[DeiT-base distilled](https://download.openmmlab.com/mmclassification/v0/deit/deit-base-distilled_3rdparty_pt-16xb64_in1k_20211216-42891296.pth)\u003cbr/\u003e[DeiT-base 384px](https://download.openmmlab.com/mmclassification/v0/deit/deit-base_3rdparty_ft-16xb32_in1k-384px_20211124-822d02f2.pth)\u003cbr/\u003e[DeiT-base distilled 384px](https://download.openmmlab.com/mmclassification/v0/deit/deit-base-distilled_3rdparty_ft-16xb32_in1k-384px_20211216-e48d6000.pth)|**Conformer**|[Conformer-tiny-p16](https://download.openmmlab.com/mmclassification/v0/conformer/conformer-tiny-p16_3rdparty_8xb128_in1k_20211206-f6860372.pth)\u003cbr/\u003e[Conformer-small-p32](https://download.openmmlab.com/mmclassification/v0/conformer/conformer-small-p32_8xb128_in1k_20211206-947a0816.pth)\u003cbr/\u003e[Conformer-small-p16](https://download.openmmlab.com/mmclassification/v0/conformer/conformer-small-p16_3rdparty_8xb128_in1k_20211206-3065dcf5.pth)\u003cbr/\u003e[Conformer-base-p16](https://download.openmmlab.com/mmclassification/v0/conformer/conformer-base-p16_3rdparty_8xb128_in1k_20211206-bfdf8637.pth)|\n|**T2T-ViT**|[T2T-ViT_t-14](https://download.openmmlab.com/mmclassification/v0/t2t-vit/t2t-vit-t-14_8xb64_in1k_20211220-f7378dd5.pth)\u003cbr/\u003e[T2T-ViT_t-19](https://download.openmmlab.com/mmclassification/v0/t2t-vit/t2t-vit-t-19_8xb64_in1k_20211214-7f5e3aaf.pth)\u003cbr/\u003e[T2T-ViT_t-24](https://download.openmmlab.com/mmclassification/v0/t2t-vit/t2t-vit-t-24_8xb64_in1k_20211214-b2a68ae3.pth)|**Twins**|[PCPVT-small](https://download.openmmlab.com/mmclassification/v0/twins/twins-pcpvt-small_3rdparty_8xb128_in1k_20220126-ef23c132.pth)\u003cbr/\u003e[PCPVT-base](https://download.openmmlab.com/mmclassification/v0/twins/twins-pcpvt-base_3rdparty_8xb128_in1k_20220126-f8c4b0d5.pth)\u003cbr/\u003e[PCPVT-large](https://download.openmmlab.com/mmclassification/v0/twins/twins-pcpvt-large_3rdparty_16xb64_in1k_20220126-c1ef8d80.pth)\u003cbr/\u003e[SVT-small](https://download.openmmlab.com/mmclassification/v0/twins/twins-svt-small_3rdparty_8xb128_in1k_20220126-8fe5205b.pth)\u003cbr/\u003e[SVT-base](https://download.openmmlab.com/mmclassification/v0/twins/twins-svt-base_3rdparty_8xb128_in1k_20220126-e31cc8e9.pth)\u003cbr/\u003e[SVT-large](https://download.openmmlab.com/mmclassification/v0/twins/twins-svt-large_3rdparty_16xb64_in1k_20220126-4817645f.pth)|**PoolFormer**|[PoolFormer-S12](https://download.openmmlab.com/mmclassification/v0/poolformer/poolformer-s12_3rdparty_32xb128_in1k_20220414-f8d83051.pth)\u003cbr/\u003e[PoolFormer-S24](https://download.openmmlab.com/mmclassification/v0/poolformer/poolformer-s24_3rdparty_32xb128_in1k_20220414-d7055904.pth)\u003cbr/\u003e[PoolFormer-S36](https://download.openmmlab.com/mmclassification/v0/poolformer/poolformer-s36_3rdparty_32xb128_in1k_20220414-d78ff3e8.pth)\u003cbr/\u003e[PoolFormer-M36](https://download.openmmlab.com/mmclassification/v0/poolformer/poolformer-m36_3rdparty_32xb128_in1k_20220414-c55e0949.pth)\u003cbr/\u003e[PoolFormer-M48](https://download.openmmlab.com/mmclassification/v0/poolformer/poolformer-m48_3rdparty_32xb128_in1k_20220414-9378f3eb.pth)|\n|**DenseNet**|[DenseNet121](https://download.openmmlab.com/mmclassification/v0/densenet/densenet121_4xb256_in1k_20220426-07450f99.pth)\u003cbr/\u003e[DenseNet161](https://download.openmmlab.com/mmclassification/v0/densenet/densenet161_4xb256_in1k_20220426-ee6a80a9.pth)\u003cbr/\u003e[DenseNet169](https://download.openmmlab.com/mmclassification/v0/densenet/densenet169_4xb256_in1k_20220426-a2889902.pth)\u003cbr/\u003e[DenseNet201](https://download.openmmlab.com/mmclassification/v0/densenet/densenet201_4xb256_in1k_20220426-05cae4ef.pth)|**Visual Attention Network(VAN)**|[VAN-Tiny](https://download.openmmlab.com/mmclassification/v0/van/van-tiny_8xb128_in1k_20220501-385941af.pth)\u003cbr/\u003e[VAN-Small](https://download.openmmlab.com/mmclassification/v0/van/van-small_8xb128_in1k_20220501-17bc91aa.pth)\u003cbr/\u003e[VAN-Base](https://download.openmmlab.com/mmclassification/v0/van/van-base_8xb128_in1k_20220501-6a4cc31b.pth)\u003cbr/\u003e[VAN-Large](https://download.openmmlab.com/mmclassification/v0/van/van-large_8xb128_in1k_20220501-f212ba21.pth)|**Wide-ResNet**|[WRN-50](https://download.openmmlab.com/mmclassification/v0/wrn/wide-resnet50_3rdparty-timm_8xb32_in1k_20220304-83ae4399.pth)\u003cbr/\u003e[WRN-101](https://download.openmmlab.com/mmclassification/v0/wrn/wide-resnet101_3rdparty_8xb32_in1k_20220304-8d5f9d61.pth)|\n|**HorNet**|[HorNet-Tiny](https://download.openmmlab.com/mmclassification/v0/hornet/hornet-tiny_3rdparty_in1k_20220915-0e8eedff.pth)\u003cbr/\u003e[HorNet-Tiny-GF](https://download.openmmlab.com/mmclassification/v0/hornet/hornet-tiny-gf_3rdparty_in1k_20220915-4c35a66b.pth)\u003cbr/\u003e[HorNet-Small](https://download.openmmlab.com/mmclassification/v0/hornet/hornet-small_3rdparty_in1k_20220915-5935f60f.pth)\u003cbr/\u003e[HorNet-Small-GF](https://download.openmmlab.com/mmclassification/v0/hornet/hornet-small-gf_3rdparty_in1k_20220915-649ca492.pth)\u003cbr/\u003e[HorNet-Base](https://download.openmmlab.com/mmclassification/v0/hornet/hornet-base_3rdparty_in1k_20220915-a06176bb.pth)\u003cbr/\u003e[HorNet-Base-GF](https://download.openmmlab.com/mmclassification/v0/hornet/hornet-base-gf_3rdparty_in1k_20220915-82c06fa7.pth)\u003cbr/\u003e[HorNet-Large](https://download.openmmlab.com/mmclassification/v0/hornet/hornet-large_3rdparty_in21k_20220909-9ccef421.pth)\u003cbr/\u003e[HorNet-Large-GF](https://download.openmmlab.com/mmclassification/v0/hornet/hornet-large-gf_3rdparty_in21k_20220909-3aea3b61.pth)\u003cbr/\u003e[HorNet-Large-GF384](https://download.openmmlab.com/mmclassification/v0/hornet/hornet-base-gf_3rdparty_in1k_20220915-82c06fa7.pth)|**EfficientFormer**|[efficientformer-l1](https://download.openmmlab.com/mmclassification/v0/efficientformer/efficientformer-l1_3rdparty_in1k_20220803-d66e61df.pth)\u003cbr/\u003e[efficientformer-l3](https://download.openmmlab.com/mmclassification/v0/efficientformer/efficientformer-l3_3rdparty_in1k_20220803-dde1c8c5.pth)\u003cbr/\u003e[efficientformer-l7](https://download.openmmlab.com/mmclassification/v0/efficientformer/efficientformer-l7_3rdparty_in1k_20220803-41a552bb.pth)|**Swin Transformer v2**|[tiny-256 window 8](https://download.openmmlab.com/mmclassification/v0/swin-v2/swinv2-tiny-w8_3rdparty_in1k-256px_20220803-e318968f.pth)\u003cbr/\u003e[tiny-256 window 16](https://download.openmmlab.com/mmclassification/v0/swin-v2/swinv2-tiny-w16_3rdparty_in1k-256px_20220803-9651cdd7.pth)\u003cbr/\u003e[small-256 window 8](https://download.openmmlab.com/mmclassification/v0/swin-v2/swinv2-small-w8_3rdparty_in1k-256px_20220803-b01a4332.pth)\u003cbr/\u003e[small-256 window 16](https://download.openmmlab.com/mmclassification/v0/swin-v2/swinv2-small-w16_3rdparty_in1k-256px_20220803-b707d206.pth)\u003cbr/\u003e[base-256 window 8](https://download.openmmlab.com/mmclassification/v0/swin-v2/swinv2-base-w8_3rdparty_in1k-256px_20220803-8ff28f2b.pth)\u003cbr/\u003e[base-256 window 16](https://download.openmmlab.com/mmclassification/v0/swin-v2/swinv2-base-w16_3rdparty_in1k-256px_20220803-5a1886b7.pth)\u003cbr/\u003e[large-256 window 16](https://download.openmmlab.com/mmclassification/v0/swin-v2/swinv2-large-w16_in21k-pre_3rdparty_in1k-256px_20220803-c40cbed7.pth)\u003cbr/\u003e[large-384 window 24](https://download.openmmlab.com/mmclassification/v0/swin-v2/swinv2-large-w24_in21k-pre_3rdparty_in1k-384px_20220803-3b36c165.pth)|\n|**MViTv2**|[MViTv2-Tiny](https://download.openmmlab.com/mmclassification/v0/mvit/mvitv2-tiny_3rdparty_in1k_20220722-db7beeef.pth)\u003cbr/\u003e[MViTv2-Small](https://download.openmmlab.com/mmclassification/v0/mvit/mvitv2-small_3rdparty_in1k_20220722-986bd741.pth)\u003cbr/\u003e[MViTv2-Base](https://download.openmmlab.com/mmclassification/v0/mvit/mvitv2-base_3rdparty_in1k_20220722-9c4f0a17.pth)\u003cbr/\u003e[MViTv2-Large](https://download.openmmlab.com/mmclassification/v0/mvit/mvitv2-large_3rdparty_in1k_20220722-2b57b983.pth)|**MobileVit**|[MobileViT-XXSmall](https://download.openmmlab.com/mmclassification/v0/mobilevit/mobilevit-xxsmall_3rdparty_in1k_20221018-77835605.pth)\u003cbr\u003e[MobileViT-XSmall](https://download.openmmlab.com/mmclassification/v0/mobilevit/mobilevit-xsmall_3rdparty_in1k_20221018-be39a6e7.pth)\u003cbr\u003e[MobileViT-Small](https://download.openmmlab.com/mmclassification/v0/mobilevit/mobilevit-small_3rdparty_in1k_20221018-cb4f741c.pth)|**DaViT**|[DaViT-T](https://download.openmmlab.com/mmclassification/v0/davit/davit-tiny_3rdparty_in1k_20221116-700fdf7d.pth)\u003cbr\u003e[DaViT-S](https://download.openmmlab.com/mmclassification/v0/davit/davit-small_3rdparty_in1k_20221116-51a849a6.pth)\u003cbr\u003e[DaViT-B](https://download.openmmlab.com/mmclassification/v0/davit/davit-base_3rdparty_in1k_20221116-19e0d956.pth)|\n|**RepLKNet**|[RepLKNet-31B-224](https://download.openmmlab.com/mmclassification/v0/replknet/replknet-31B_in21k-pre_3rdparty_in1k_20221118-54ed5c46.pth)\u003cbr\u003e[RepLKNet-31B-384](https://download.openmmlab.com/mmclassification/v0/replknet/replknet-31B_in21k-pre_3rdparty_in1k-384px_20221118-76c92b24.pth)\u003cbr\u003e[RepLKNet-31L-384](https://download.openmmlab.com/mmclassification/v0/replknet/replknet-31L_in21k-pre_3rdparty_in1k-384px_20221118-dc3fc07c.pth)\u003cbr\u003e[RepLKNet-XL](https://download.openmmlab.com/mmclassification/v0/replknet/replknet-XL_meg73m-pre_3rdparty_in1k-320px_20221118-88259b1d.pth)|**BEiT**|[BEiT-base](https://download.openmmlab.com/mmclassification/v0/beit/beit-base_3rdparty_in1k_20221114-c0a4df23.pth)|**EVA**|[EVA-G-p14-224](https://download.openmmlab.com/mmclassification/v0/eva/eva-g-p14_30m-pre_3rdparty_in21k_20221213-d72285b7.pth)\u003cbr\u003e[EVA-G-p14-336](https://download.openmmlab.com/mmclassification/v0/eva/eva-g-p14_30m-in21k-pre_3rdparty_in1k-336px_20221213-210f9071.pth)\u003cbr\u003e[EVA-G-p14-560](https://download.openmmlab.com/mmclassification/v0/eva/eva-g-p14_30m-in21k-pre_3rdparty_in1k-560px_20221213-fa1c3652.pth)\u003cbr\u003e[EVA-G-p16-224](https://download.openmmlab.com/mmclassification/v0/eva/eva-g-p16_3rdparty_30m_20221213-7bed23ee.pth)\u003cbr\u003e[EVA-L-p14-224](https://download.openmmlab.com/mmclassification/v0/eva/eva-l-p14_mim-pre_3rdparty_in21k_20221213-8f194fa2.pth)\u003cbr\u003e[EVA-L-p14-196](https://download.openmmlab.com/mmclassification/v0/eva/eva-l-p14_mim-in21k-pre_3rdparty_in1k-196px_20221213-b730c7e7.pth)\u003cbr\u003e[EVA-L-p14-336](https://download.openmmlab.com/mmclassification/v0/eva/eva-l-p14_mim-in21k-pre_3rdparty_in1k-336px_20221213-f25b7634.pth)\n|**MixMIM**|[mixmim-base](https://download.openmmlab.com/mmclassification/v0/mixmim/mixmim-base_3rdparty_in1k_20221206-e40e2c8c.pth)|**EfficientNetV2**|[EfficientNetV2-b0](https://download.openmmlab.com/mmclassification/v0/efficientnetv2/efficientnetv2-b0_3rdparty_in1k_20221221-9ef6e736.pth)\u003cbr\u003e[EfficientNetV2-b1](https://download.openmmlab.com/mmclassification/v0/efficientnetv2/efficientnetv2-b1_3rdparty_in1k_20221221-6955d9ce.pth)\u003cbr\u003e[EfficientNetV2-b2](https://download.openmmlab.com/mmclassification/v0/efficientnetv2/efficientnetv2-b2_3rdparty_in1k_20221221-74f7d493.pth)\u003cbr\u003e[EfficientNetV2-b3](https://download.openmmlab.com/mmclassification/v0/efficientnetv2/efficientnetv2-b3_3rdparty_in1k_20221221-b6f07a36.pth)\u003cbr\u003e[EfficientNetV2-s](https://download.openmmlab.com/mmclassification/v0/efficientnetv2/efficientnetv2-s_in21k-pre-3rdparty_in1k_20221220-7a7c8475.pth)\u003cbr\u003e[EfficientNetV2-m](https://download.openmmlab.com/mmclassification/v0/efficientnetv2/efficientnetv2-m_in21k-pre-3rdparty_in1k_20221220-a1013a04.pth)\u003cbr\u003e[EfficientNetV2-l](https://download.openmmlab.com/mmclassification/v0/efficientnetv2/efficientnetv2-l_in21k-pre-3rdparty_in1k_20221220-63df0efd.pth)\u003cbr\u003e[EfficientNetV2-xl](https://download.openmmlab.com/mmclassification/v0/efficientnetv2/efficientnetv2-xl_in21k-pre-3rdparty_in1k_20221220-583ac18b.pth)|**DeiT3**|[deit3_small_p16](https://download.openmmlab.com/mmclassification/v0/deit3/deit3-small-p16_3rdparty_in1k_20221008-0f7c70cf.pth)\u003cbr/\u003e[deit3_small_p16_384](https://download.openmmlab.com/mmclassification/v0/deit3/deit3-small-p16_3rdparty_in1k-384px_20221008-a2c1a0c7.pth)\u003cbr/\u003e[deit3_base_p16](https://download.openmmlab.com/mmclassification/v0/deit3/deit3-base-p16_3rdparty_in1k_20221008-60b8c8bf.pth)\u003cbr/\u003e[deit3_base_p16_384](https://download.openmmlab.com/mmclassification/v0/deit3/deit3-base-p16_3rdparty_in1k-384px_20221009-e19e36d4.pth)\u003cbr/\u003e[deit3_medium_p16](https://download.openmmlab.com/mmclassification/v0/deit3/deit3-medium-p16_3rdparty_in1k_20221008-3b21284d.pth)\u003cbr/\u003e[deit3_large_p16](https://download.openmmlab.com/mmclassification/v0/deit3/deit3-large-p16_3rdparty_in1k_20221009-03b427ea.pth)\u003cbr/\u003e[deit3_large_p16_384](https://download.openmmlab.com/mmclassification/v0/deit3/deit3-large-p16_3rdparty_in1k-384px_20221009-4317ce62.pth)\u003cbr/\u003e[deit3_huge_p16](https://download.openmmlab.com/mmclassification/v0/deit3/deit3-huge-p14_3rdparty_in1k_20221009-e107bcb7.pth)|\n|**EdgeNeXt**|[edgenext-base](https://download.openmmlab.com/mmclassification/v0/edgenext/edgenext-base_3rdparty_in1k_20220801-9ade408b.pth)\u003cbr\u003e[edgenext-small](https://download.openmmlab.com/mmclassification/v0/edgenext/edgenext-small_3rdparty_in1k_20220801-d00db5f8.pth)\u003cbr\u003e[edgenext-X-small](https://download.openmmlab.com/mmclassification/v0/edgenext/edgenext-xsmall_3rdparty_in1k_20220801-974f9fe7.pth)\u003cbr\u003e[edgenext-XX-small](https://download.openmmlab.com/mmclassification/v0/edgenext/edgenext-xxsmall_3rdparty_in1k_20220801-7ca8a81d.pth)|**RevVisionTransformer**|[revvit-small](https://download.openmmlab.com/mmclassification/v0/revvit/revvit-base_3rdparty_in1k_20221213-87a7b0a5.pth)\u003cbr\u003e[revvit-base](https://download.openmmlab.com/mmclassification/v0/revvit/revvit-small_3rdparty_in1k_20221213-a3a34f5c.pth)\n\n## 我维护的其他项目\n- [**图片数据不够？我做了一款图像增强软件**](https://github.com/Fafa-DL/Image-Augmentation)\n[![GitHub stars](https://img.shields.io/github/stars/Fafa-DL/Image-Augmentation)](https://github.com/Fafa-DL/Image-Augmentation)\n[![GitHub forks](https://img.shields.io/github/forks/Fafa-DL/Image-Augmentation)](https://github.com/Fafa-DL/Image-Augmentation)\n- [**一键转换与编辑图像标注文件软件，极大提高效率**](https://github.com/Fafa-DL/LabelConvert)\n[![GitHub stars](https://img.shields.io/github/stars/Fafa-DL/LabelConvert)](https://github.com/Fafa-DL/LabelConvert)\n[![GitHub forks](https://img.shields.io/github/forks/Fafa-DL/LabelConvert)](https://github.com/Fafa-DL/LabelConvert)\n\n## 参考\n```\n@repo{2020mmclassification,\n    title={OpenMMLab's Image Classification Toolbox and Benchmark},\n    author={MMClassification Contributors},\n    howpublished = {\\url{https://github.com/open-mmlab/mmclassification}},\n    year={2020}\n}\n```\n","projects_url":"https://awesome.ecosyste.ms/api/v1/lists/fafa-dl%2Fawesome-backbones/projects"}