diff --git a/README.md b/README.md index 2ddbb254341a7a3b0f924bda682c058f0c58a10c..2575d95b7affb64b75edce3843ea59e8db34d47b 100644 --- a/README.md +++ b/README.md @@ -8,13 +8,10 @@ PaddleClas is a toolset for image classification tasks prepared for the industry **Recent update** -- 2021.05.14 Add `SwinTransformer` series pretrained models, whose Top-1 Acc on ImageNet-1k dataset reaches 87.19%. -- 2021.04.15 Add `MixNet` and `ReXNet` pretrained models, `MixNet_L`'s Top-1 Acc on ImageNet-1k reaches 78.6% and `ReXNet_3_0` reaches 82.09%. -- 2021.03.02 Add support for model quantization. -- 2021.02.01 Add `RepVGG` pretrained models, whose Top-1 Acc on ImageNet-1k dataset reaches 79.65%. -- 2021.01.27 Add `ViT` and `DeiT` pretrained models, `ViT`'s Top-1 Acc on ImageNet-1k dataset reaches 85.13%, and `DeiT` reaches 85.1%. -- 2021.01.08 Add support for whl package and its usage, Model inference can be done by simply install paddleclas using pip. -- 2020.12.16 Add support for TensorRT when using cpp inference to obain more obvious acceleration. +- 2021.06.16 PaddleClas release/2.2. + - Add metric learning and vector search module. + - Add product recognition, cartoon character recognition, car recognition and logo recognition. + - Add xxx models(todo @崔程) - [more](./docs/en/update_history_en.md) diff --git a/README_cn.md b/README_cn.md index 34bdc13df7ebbc05ad6809d8d630c21500cf5d00..5c76207c34af514e90b89f348c6fb616b4938c6e 100644 --- a/README_cn.md +++ b/README_cn.md @@ -8,7 +8,10 @@ **近期更新** -- 2021.06.16 PaddleClas v2.2版本升级，集成Metric learning，向量检索等组件，新增4个图像识别应用。 +- 2021.06.16 PaddleClas v2.2版本升级 + - 集成Metric learning，向量检索等组件。 + - 新增商品识别、动漫人物识别、车辆识别和logo识别等4个图像识别应用。 + - 新增xxx模型（todo @崔程） - [more](./docs/zh_CN/update_history.md) @@ -43,23 +46,22 @@ ## 文档教程 - [快速安装](./docs/zh_CN/tutorials/install.md) -- 图像识别快速体验(若愚) -- 图像分类快速体验(崔程，基于30分钟入门版修改) +- [图像识别快速体验](./docs/zh_CN/tutorials/quick_start_recognition.md) +- [图像分类快速体验](./docs/zh_CN/tutorials/quick_start_new_user.md) - 算法介绍 - - 图像识别系统] (胜禹) - - [模型库介绍和预训练模型](./docs/zh_CN/models/models_intro.md) - - [图像分类] - - ImageNet分类任务(崔程,基于30分钟进阶版修改) - - [多标签分类任务]() - - [特征学习] - - [商品识别]() - - [车辆识别]() - - [logo识别]() - - [动漫人物识别]() - - [向量检索]() + - [骨干网络模型库和预训练模型介绍](./docs/zh_CN/models/models_intro.md) + - [主体检测](./docs/zh_CN/application/object_detection.md) + - 图像分类 + - [ImageNet分类任务](./docs/zh_CN/tutorials/quick_start_professional.md) + - 特征学习 + - [商品识别](todo@崔程) + - [车辆识别](./docs/zh_CN/application/vehicle_fine_grained_classfication.md) + - [车辆ReID](./docs/zh_CN/application/vehicle_reid.md) + - [logo识别](./docs/zh_CN/application/logo_recognition.md) + - [向量检索](./deploy/vector_search/README.md) - 模型训练/评估 - - 图像分类任务(崔程，基于原有训练文档整理) - - 特征学习任务（陆彬） + - [图像分类任务](./docs/zh_CN/tutorials/getting_started.md) + - [特征学习任务](./docs/zh_CN/application/feature_learning.md) - 模型预测 - [基于训练引擎预测推理](./docs/zh_CN/tutorials/getting_started.md) - [基于Python预测引擎预测推理](./docs/zh_CN/tutorials/getting_started.md) @@ -74,7 +76,7 @@ - [数据增广](./docs/zh_CN/advanced_tutorials/image_augmentation/ImageAugment.md) - [代码解析与社区贡献指南](./docs/zh_CN/tutorials/quick_start_community.md) - FAQ(暂停更新) - - [图像分类任务FAQ] + - [图像分类任务FAQ](docs/zh_CN/faq.md) - [许可证书](#许可证书) - [贡献代码](#贡献代码) diff --git a/docs/en/update_history_en.md b/docs/en/update_history_en.md index cef5384e424f944ce146bcccdbb25294885949cd..601326979491fd17c31dec9cee7646d7b2a60b73 100644 --- a/docs/en/update_history_en.md +++ b/docs/en/update_history_en.md @@ -1,6 +1,7 @@ # Release Notes - +- 2021.05.14 + - Add `SwinTransformer` series pretrained models, whose Top-1 Acc on ImageNet-1k dataset reaches 87.19%. - 2021.04.15 - Add `MixNet` and `ReXNet` pretrained models, `MixNet_L`'s Top-1 Acc on ImageNet-1k reaches 78.6% and `ReXNet_3_0` reaches 82.09%. diff --git a/docs/zh_CN/update_history.md b/docs/zh_CN/update_history.md index 89f7b146dad555df0041994f41bcd1d9fed8131c..475760f2e5af031188838cf9b1b7a7b4a5f76f96 100644 --- a/docs/zh_CN/update_history.md +++ b/docs/zh_CN/update_history.md @@ -1,7 +1,8 @@ # 更新日志 - +- 2021.05.14 + - 添加`SwinTransformer` 系列模型，在ImageNet-1k上，Top1 Acc可达87.19% - 2021.04.15 - 添加`MixNet_L`和`ReXNet_3_0`系列模型，在ImageNet-1k上`MixNet` 模型Top1 Acc可达78.6%，`ReXNet`模型可达82.09% - 2021.01.27