提交 b75f4989 编写于 作者: qq_25193841's avatar qq_25193841 提交者: Tingquan Gao

Update README

Update README
上级 5c96d74d
......@@ -6,14 +6,20 @@
飞桨图像识别套件PaddleClas是飞桨为工业界和学术界所准备的一个图像识别和图像分类任务的工具集,助力使用者训练出更好的视觉模型和应用落地。
| PP-ShiTuV2图像识别系统效果展示 | PULC实用图像分类模型效果展示 |
| :----------------------------------------------------: | :---------------------------------------------------------: |
| <img src="./docs/images/shituv2.gif" width = "450" /> | <img src="./docs/images/class_simple.gif" width = "600" /> |
<div align="center">
<img src="https://user-images.githubusercontent.com/50011306/201870645-63319203-9730-44fc-8e2e-054aad164461.gif" width = "600" />
<p>PP-ShiTu图像识别系统应用范围</p>
</div>
<div align="center">
<img src="./docs/images/class_simple.gif" width = "600" />
<p>PULC实用图像分类模型效果展示</p>
</div>
## 📣 近期更新
- **💥 直播预告:11.1-11.3日每晚8点半**,PaddleClas研发团队详解PP-ShituV2优化策略与真实产业应用。微信扫描下方二维码,关注公众号并填写问卷后进入官方交流群,获取直播链接与20G重磅图像分类学习大礼包(内含20+数据集、4个垂类模型、70+前沿论文集合)
- **💥 直播回放**:PaddleClas研发团队详解PP-ShituV2优化策略与真实产业应用。微信扫描下方二维码,关注公众号并填写问卷后进入官方交流群,获取直播回放与20G重磅图像分类学习大礼包(内含20+数据集、4个垂类模型、70+前沿论文集合)
<div align="center">
<img src="https://user-images.githubusercontent.com/50011306/198980780-602c6eef-11da-4b4e-aa20-c2f6fd547ae5.jpg" width = "150" height = "150"/>
......@@ -24,7 +30,7 @@
- **🔥️ 2022.9.13 发布超轻量图像识别系统[PP-ShiTuV2](docs/zh_CN/models/PP-ShiTu/README.md):**
- recall1精度提升8个点,覆盖商品识别、垃圾分类、航拍场景等[20+识别场景](docs/zh_CN/deployment/PP-ShiTu/application_scenarios.md)
- 新增[库管理工具](./deploy/shitu_index_manager/)[Android Demo](./docs/zh_CN/quick_start/quick_start_recognition.md)全新体验。
- 2022.9.4 新增[生鲜产品自主结算范例库](./docs/zh_CN/samples/Fresh_Food_Recogniiton/README.md),具体内容可以在AI Studio上体验。
- 2022.6.15 发布[PULC超轻量图像分类实用方案](docs/zh_CN/training/PULC.md),CPU推理3ms,精度比肩SwinTransformer,覆盖人、车、OCR场景九大常见任务。
- 2022.5.23 新增[人员出入管理范例库](https://aistudio.baidu.com/aistudio/projectdetail/4094475),具体内容可以在 AI Studio 上体验。
......@@ -52,6 +58,7 @@ PaddleClas支持多种前沿图像分类、识别相关算法,发布产业级
<div align="center">
<img src="./docs/images/quick_start/android_demo/PPShiTu_qrcode.png" width = "170" height = "170" />
</div>
## 👫 开源社区
* **📑项目合作:** 如果您是企业开发者且有明确的图像分类应用需求,填写[问卷](https://paddle.wjx.cn/vm/hnGOjfn.aspx# )后可免费与官方团队展开不同层次的合作。
......@@ -222,7 +229,7 @@ PaddleClas提供了覆盖人、车、OCR场景九大常见任务的分类模型
<a name="贡献代码"></a>
## 贡献代码
我们非常欢迎你为PaddleClas贡献代码,也十分感谢你的反馈。
如果想为PaddleCLas贡献代码,可以参考[贡献指南](docs/zh_CN/community/how_to_contribute.md)
如果想为PaddleClas贡献代码,可以参考[贡献指南](docs/zh_CN/community/how_to_contribute.md)
- 非常感谢[nblib](https://github.com/nblib)修正了PaddleClas中RandErasing的数据增广配置文件。
- 非常感谢[chenpy228](https://github.com/chenpy228)修正了PaddleClas文档中的部分错别字。
......
......@@ -6,9 +6,14 @@
PaddleClas is an image classification and image recognition toolset for industry and academia, helping users train better computer vision models and apply them in real scenarios.
| PP-ShiTuV2 | PULC: **P**ractical **U**ltra **L**ight-weight image **C**lassification solutions |
| :----------------------------------------------------: | :----------------------------------------------------------: |
| <img src="./docs/images/shituv2.gif" width = "450" /> | <img src="./docs/images/class_simple_en.gif" width = "600" /> |
<div align="center">
<img src="https://user-images.githubusercontent.com/50011306/201870645-63319203-9730-44fc-8e2e-054aad164461.gif" width = "600" />
<p>PP-ShiTuV2</p>
</div>
<div align="center">
<img src="./docs/images/class_simple_en.gif" width = "600" />
<p>PULC: Practical Ultra Light-weight image Classification solutions</p>
</div>
## 📣 Recent updates
......
......@@ -2,11 +2,12 @@
该文档介绍了PP-ShiTu提供的各种应用场景库简介、下载链接以及使用简介。
------
## 目录
- [1. 应用场景介绍](#1-应用场景介绍)
- [1.1 场景库介绍](#11-场景库介绍)
- [1.2 场景库下载](#12-场景库下载)
- [2. 使用说明](#2-使用说明)
- [2.1 环境配置](#21-环境配置)
- [2.2 下载、解压场景库数据](#22-下载解压场景库数据)
......@@ -20,37 +21,45 @@
## 1. 应用场景介绍
<a name="1.1 场景库介绍"></a>
### 1.1 场景库介绍
PP-ShiTu对原数据集进行了`Gallery`库和`Query`库划分,并生成了对应的`Index`索引库,具体应用场景介绍和下载地址如下表所示。
| 场景 |示例图|场景简介|Recall@1|场景库下载地址|原数据集下载地址|
|:---:|:---:|:---:|:---:|:---:|:---:|
| 花 | <img src="../../../images/ppshitu_application_scenarios/104flowers.jpeg" height = "100"> |104种花细分类识别 | 0.9788 | [104flowers](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/data/PP-ShiTuV2_application_dataset/104flowers.tar) | [原数据下载地址](https://www.kaggle.com/datasets/msheriey/104-flowers-garden-of-eden) |
| 交通工具 | <img src="../../../images/ppshitu_application_scenarios/Vechicles.jpg" height = "100"> |车、船等交通工具粗分类识别 | 0.9307 | [Vechicles](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/data/PP-ShiTuV2_application_dataset/Vechicles.tar) | [原数据下载地址](https://www.kaggle.com/datasets/rishabkoul1/vechicle-dataset) |
| 动物 | <img src="../../../images/ppshitu_application_scenarios/AnimalImageDataset.jpg" height = "100"> |各种动物识别 | 0.9078 | [AnimalImageDataset](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/data/PP-ShiTuV2_application_dataset/AnimalImageDataset.tar) | [原数据下载地址](https://www.kaggle.com/datasets/iamsouravbanerjee/animal-image-dataset-90-different-animals) |
| 时装 | <img src="../../../images/ppshitu_application_scenarios/FashionProductsImage.jpg" height = "100"> |首饰、挎包、化妆品等时尚商品识别 | 0.9555 | [FashionProductImageSmall](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/data/PP-ShiTuV2_application_dataset/FashionProductImageSmall.tar) | [原数据下载地址](https://www.kaggle.com/datasets/paramaggarwal/fashion-product-images-small) |
| 球类 | <img src="../../../images/ppshitu_application_scenarios/Ball.jpg" height = "100"> |各种球类识别 | 0.9769 | [Balls](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/data/PP-ShiTuV2_application_dataset/Balls.tar) | [原数据下载地址](https://www.kaggle.com/datasets/gpiosenka/balls-image-classification) |
| 狗识别 | <img src="../../../images/ppshitu_application_scenarios/DogBreeds.jpg" height = "100"> | 狗细分类识别,包括69种狗的图像 | 0.9606 | 添加技术交流群后即可获得 | [原数据下载地址](https://www.kaggle.com/datasets/gpiosenka/70-dog-breedsimage-data-set) |
| 宝石 | <img src="../../../images/ppshitu_application_scenarios/Gemstones.jpg" height = "100"> | 宝石种类识别 | 0.9653 | 添加技术交流群后即可获得 | [原数据下载地址](https://www.kaggle.com/datasets/lsind18/gemstones-images) |
| 鸟类 | <img src="../../../images/ppshitu_application_scenarios/Bird400.jpg" height = "100"> |鸟细分类识别,包括400种各种姿态的鸟类图像 | 0.9673 | 添加技术交流群后即可获得 | [原数据下载地址](https://www.kaggle.com/datasets/gpiosenka/100-bird-species) |
| 运动种类 | <img src="../../../images/ppshitu_application_scenarios/100sports.jpg" height = "100"> |100种运动图像识别 | 0.9413 | 添加技术交流群后即可获得 | [原数据下载地址](https://www.kaggle.com/datasets/gpiosenka/sports-classification) |
| 乐器 | <img src="../../../images/ppshitu_application_scenarios/MusicInstruments.jpg" height = "100"> |30种不同乐器种类识别 | 0.9467 | 添加技术交流群后即可获得 | [原数据下载地址](https://www.kaggle.com/datasets/gpiosenka/musical-instruments-image-classification) |
| 宝可梦 | <img src="../../../images/ppshitu_application_scenarios/Pokemon.png" height = "100"> |宝可梦神奇宝贝识别 | 0.9236 | 添加技术交流群后即可获得 | [原数据下载地址](https://www.kaggle.com/datasets/lantian773030/pokemonclassification) |
| 船 | <img src="../../../images/ppshitu_application_scenarios/Boat.jpg" height = "100"> |船种类识别 |0.9242 | 添加技术交流群后即可获得 | [原数据下载地址](https://www.kaggle.com/datasets/imsparsh/dockship-boat-type-classification) |
| 鞋子 | <img src="../../../images/ppshitu_application_scenarios/Shoes.jpeg" height = "100"> |鞋子种类识别,包括靴子、拖鞋等 | 0.9000 | 添加技术交流群后即可获得 | [原数据下载地址](https://www.kaggle.com/datasets/noobyogi0100/shoe-dataset) |
| 巴黎建筑 | <img src="../../../images/ppshitu_application_scenarios/Paris.jpg" height = "100"> |巴黎著名建筑景点识别,如:巴黎铁塔、圣母院等 | 1.000 | 添加技术交流群后即可获得 | [原数据下载地址](https://www.kaggle.com/datasets/skylord/oxbuildings) |
| 蝴蝶 | <img src="../../../images/ppshitu_application_scenarios/Butterfly.jpg" height = "100"> |75种蝴蝶细分类识别 | 0.9360 | 添加技术交流群后即可获得 | [原数据下载地址](https://www.kaggle.com/datasets/gpiosenka/butterfly-images40-species) |
| 野外植物 | <img src="../../../images/ppshitu_application_scenarios/WildEdiblePlants.jpg" height = "100"> |野外植物识别 | 0.9758 | 添加技术交流群后即可获得 | [原数据下载地址](https://www.kaggle.com/datasets/ryanpartridge01/wild-edible-plants) |
| 天气 | <img src="../../../images/ppshitu_application_scenarios/WeatherImageRecognition.jpg" height = "100"> |各种天气场景识别,如:雨天、打雷、下雪等 | 0.9924 | 添加技术交流群后即可获得 | [原数据下载地址](https://www.kaggle.com/datasets/jehanbhathena/weather-dataset) |
| 坚果 | <img src="../../../images/ppshitu_application_scenarios/TreeNuts.jpg" height = "100"> |各种坚果种类识别 | 0.9412 | 添加技术交流群后即可获得 | [原数据下载地址](https://www.kaggle.com/datasets/gpiosenka/tree-nuts-image-classification) |
| 垃圾 | <img src="../../../images/ppshitu_application_scenarios/Garbage12.jpg" height = "100"> |12种垃圾分类识别 | 0.9845 | 添加技术交流群后即可获得 | [原数据下载地址](https://www.kaggle.com/datasets/mostafaabla/garbage-classification) |
| 航拍场景 | <img src="../../../images/ppshitu_application_scenarios/AID.jpg" height = "100"> |各种航拍场景识别,如机场、火车站等 | 0.9797 | 添加技术交流群后即可获得 | [原数据下载地址](https://www.kaggle.com/datasets/jiayuanchengala/aid-scene-classification-datasets) |
| 蔬菜 | <img src="../../../images/ppshitu_application_scenarios/Veg200.jpg" height = "100"> |各种蔬菜识别 | 0.8929 | 添加技术交流群后即可获得 | [原数据下载地址](https://www.kaggle.com/datasets/zhaoyj688/vegfru) |
| 类别 | 场景 |示例图|场景简介|Recall@1|场景库下载地址|原数据集下载地址|
|:---:|:---:|:---:|:---:|:---:|:---:|-----|
| 动植物 | 花 | <img src="../../../images/ppshitu_application_scenarios/104flowers.jpeg" height = "100"> |104种花细分类识别 | 0.9788 | [104flowers](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/data/PP-ShiTuV2_application_dataset/104flowers.tar) | [原数据下载地址](https://www.kaggle.com/datasets/msheriey/104-flowers-garden-of-eden) |
| 动植物 | 蝴蝶 | <img src="../../../images/ppshitu_application_scenarios/Butterfly.jpg" height = "100"> | 75种蝴蝶细分类识别 | 0.9360 | [下载地址](#12-场景库下载) | [原数据下载地址](https://www.kaggle.com/datasets/gpiosenka/butterfly-images40-species) |
| 动植物 | 野外植物 | <img src="../../../images/ppshitu_application_scenarios/WildEdiblePlants.jpg" height = "100"> | 32种野外植物识别,包括雏菊、蒲公英等 | 0.9758 | [下载地址](#12-场景库下载) | [原数据下载地址](https://www.kaggle.com/datasets/ryanpartridge01/wild-edible-plants) |
| 动植物 | 动物 | <img src="../../../images/ppshitu_application_scenarios/AnimalImageDataset.jpg" height = "100"> |90种动物识别,包括斑马、羚羊等 | 0.9078 | [AnimalImageDataset](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/data/PP-ShiTuV2_application_dataset/AnimalImageDataset.tar) | [原数据下载地址](https://www.kaggle.com/datasets/iamsouravbanerjee/animal-image-dataset-90-different-animals) |
| 动植物 | 狗识别 | <img src="../../../images/ppshitu_application_scenarios/DogBreeds.jpg" height = "100"> |69种狗细分类识别,包括柴犬等 | 0.9606 | [下载地址](#12-场景库下载) | [原数据下载地址](https://www.kaggle.com/datasets/gpiosenka/70-dog-breedsimage-data-set) |
| 动植物 | 鸟类 | <img src="../../../images/ppshitu_application_scenarios/Bird400.jpg" height = "100"> |400种各种姿态的鸟细分类识别 | 0.9673 | [下载地址](#12-场景库下载) | [原数据下载地址](https://www.kaggle.com/datasets/gpiosenka/100-bird-species) |
| 商品 | 坚果 | <img src="../../../images/ppshitu_application_scenarios/TreeNuts.jpg" height = "100"> | 10种坚果种类识别,包括开心果、核桃、腰果等 | 0.9412 | [下载地址](#12-场景库下载) | [原数据下载地址](https://www.kaggle.com/datasets/gpiosenka/tree-nuts-image-classification) |
| 商品 | 蔬菜 | <img src="../../../images/ppshitu_application_scenarios/Veg200.jpg" height = "100"> | 116种蔬菜识别,包括菠菜、胡萝卜、玉米等 | 0.8929 | [下载地址](#12-场景库下载) | [原数据下载地址](https://www.kaggle.com/datasets/zhaoyj688/vegfru) |
| 商品 | 时装 | <img src="../../../images/ppshitu_application_scenarios/FashionProductsImage.jpg" height = "100"> | 23种时尚商品识别,包括首饰、挎包、化妆品等 | 0.9555 | [FashionProductImageSmall](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/data/PP-ShiTuV2_application_dataset/FashionProductImageSmall.tar) | [原数据下载地址](https://www.kaggle.com/datasets/paramaggarwal/fashion-product-images-small) |
| 商品 | 鞋子 | <img src="../../../images/ppshitu_application_scenarios/Shoes.jpeg" height = "100"> | 6种鞋子识别,包括靴子、足球鞋等 | 0.9000 | [下载地址](#12-场景库下载) | [原数据下载地址](https://www.kaggle.com/datasets/noobyogi0100/shoe-dataset) |
| 商品 | 乐器 | <img src="../../../images/ppshitu_application_scenarios/MusicInstruments.jpg" height = "100"> | 30种不同乐器种类识别 | 0.9467 | [下载地址](#12-场景库下载) | [原数据下载地址](https://www.kaggle.com/datasets/gpiosenka/musical-instruments-image-classification) |
| 商品 | 宝石 | <img src="../../../images/ppshitu_application_scenarios/Gemstones.jpg" height = "100"> | 27种宝石识别,包括萤石、翡翠等 | 0.9653 | [下载地址](#12-场景库下载) | [原数据下载地址](https://www.kaggle.com/datasets/lsind18/gemstones-images) |
| 商品 | 球类 | <img src="../../../images/ppshitu_application_scenarios/Ball.jpg" height = "100"> | 26种球型物体识别,包括弹珠、足球等 | 0.9769 | [Balls](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/data/PP-ShiTuV2_application_dataset/Balls.tar) | [原数据下载地址](https://www.kaggle.com/datasets/gpiosenka/balls-image-classification) |
| 交通 | 交通工具 | <img src="../../../images/ppshitu_application_scenarios/Vechicles.jpg" height = "100"> | 9种交通工具粗分类识别,包括车、船等 | 0.9307 | [Vechicles](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/data/PP-ShiTuV2_application_dataset/Vechicles.tar) | [原数据下载地址](https://www.kaggle.com/datasets/rishabkoul1/vechicle-dataset) |
| 交通 | 船 | <img src="../../../images/ppshitu_application_scenarios/Boat.jpg" height = "100"> |6种船种类识别,包括游轮、帆船等 |0.9242 | [下载地址](#12-场景库下载) | [原数据下载地址](https://www.kaggle.com/datasets/imsparsh/dockship-boat-type-classification) |
| 交通 | 航拍场景 | <img src="../../../images/ppshitu_application_scenarios/AID.jpg" height = "100"> | 30种航拍场景识别,如机场、火车站等 | 0.9797 | [下载地址](#12-场景库下载) | [原数据下载地址](https://www.kaggle.com/datasets/jiayuanchengala/aid-scene-classification-datasets) |
| 其他 | 巴黎建筑 | <img src="../../../images/ppshitu_application_scenarios/Paris.jpg" height = "100"> |11个巴黎建筑识别,如:巴黎铁塔、圣母院等 | 1.000 | [下载地址](#12-场景库下载) | [原数据下载地址](https://www.kaggle.com/datasets/skylord/oxbuildings) |
| 其他 | 天气 | <img src="../../../images/ppshitu_application_scenarios/WeatherImageRecognition.jpg" height = "100"> |10种天气场景识别,如:雨天、打雷、下雪等 | 0.9924 | [下载地址](#12-场景库下载) | [原数据下载地址](https://www.kaggle.com/datasets/jehanbhathena/weather-dataset) |
| 其他 | 垃圾 | <img src="../../../images/ppshitu_application_scenarios/Garbage12.jpg" height = "100"> |12种垃圾分类识别 | 0.9845 | [下载地址](#12-场景库下载) | [原数据下载地址](https://www.kaggle.com/datasets/mostafaabla/garbage-classification) |
| 其他 | 运动种类 | <img src="../../../images/ppshitu_application_scenarios/100sports.jpg" height = "100"> |100种运动图像识别 | 0.9413 | [下载地址](#12-场景库下载) | [原数据下载地址](https://www.kaggle.com/datasets/gpiosenka/sports-classification) |
| 其他 | 宝可梦 | <img src="../../../images/ppshitu_application_scenarios/Pokemon.png" height = "100"> | 150种宝可梦神奇宝贝识别,包括皮卡丘、喷火龙等 | 0.9236 | [下载地址](#12-场景库下载) | [原数据下载地址](https://www.kaggle.com/datasets/lantian773030/pokemonclassification) |
<a name="1.2 场景库下载"></a>
### 1.2 场景库下载
如需下载已经整理后的场景库数据集,可以扫描下方二维码,关注公众号填写问卷后,加入PaddleClas官方交流群获取**20G重磅图像分类学习大礼包****内含上述所有场景库数据集****垂类模型集合**(包括人员出入管理、生鲜品识别、商品识别等)、70+前沿图像分类与识别论文、历次发版课程视频与优质社区项目等
<div align="center">
<img src="https://user-images.githubusercontent.com/11568925/189877049-d17ddcea-22d2-44ab-91fe-36d12af3add8.png" width = "200" height = "200"/>
<p>添加二维码获取相关场景库及大礼包</p>
<img src="https://user-images.githubusercontent.com/11568925/189877049-d17ddcea-22d2-44ab-91fe-36d12af3add8.png" width = "150" height = "150"/>
</div>
<a name="2. 使用说明"></a>
## 2. 使用说明
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册