## Plant Disease Detector
<br>
<img src="app/static/SS.png">
<br>
<p align="center">
<sub>
Created by
<a href="https://github.com/imskr">
<strong>Shubham Kumar </strong>
</a>
<strong>and</strong>
<a href="https://github.com/imskr/Plant_Disease_Detection/graphs/contributors">
<strong>other contributors</strong>
</a>
</sub>
</p>
<hr noshade>
<br>
## My Article in [TowardsDataScience](https://t.co/iVmRCeUiDI?amp=1)
Models are trained on the preprocessed dataset which can be downloaded [here](https://drive.google.com/open?id=0B_voCy5O5sXMTFByemhpZllYREU).
## Local Set-Up
### Local:
- It is recommended to set up the project inside a virtual environment to keep the dependencies separated.
* [Python](https://realpython.com/python-virtual-environments-a-primer/#why-the-need-for-virtual-environments)
* [Conda](https://docs.conda.io/projects/conda/en/latest/user-guide/tasks/manage-environments.html)
- Activate your virtual environment.
- Install dependencies by running `pip install -r requirements.txt`.
- Start up the server by running `python app/server.py serve`.
- Visit <http://localhost:8080/> to explore and test.
### Docker:
*Make Sure the Docker is installed in your local Machine. [Click Here](https://docs.docker.com/install/) to know that how to install Docker*.
- **Mac:**
```bash
$ git clone https://github.com/imskr/Plant_Disease_Detection.git
$ cd Plant_Disease_Detection
$ docker build -t fastai-v3 .
$ docker run --rm -it -p 8080:8080 fastai-v3
```
**Go to http://localhost:8080/ to test your app.**
- **Windows:**
```PowerShell or Command Prompt
$ git clone https://github.com/imskr/Plant_Disease_Detection.git
$ cd Plant_Disease_Detection
$ docker build -t fastai-v3 .
$ docker run --rm -it -p 8080:8080 fastai-v3
```
**Go to http://localhost:8080/ to test your app.**
**Note:** Windows 10 Pro required.
- **Linux:**
```Terminal
$ git clone https://github.com/imskr/Plant_Disease_Detection.git
$ cd Plant_Disease_Detection
$ docker build -t fastai-v3 .
$ docker run --rm -it -p 8080:8080 fastai-v3
```
**Note:** If this doesn't work use `--no-cache` flag in the build command.
**Go to http://localhost:8080/ to test your app.**
## Deployment
- **Google Cloud Platform:**
The complete guideline to deploy the *Plant Disease Detection App* can be found [*here*](./deployment_guide/gcp_deployment.md)
- **AWS Elastic BeanStalk:**
The complete guideline to deploy the *Plant Disease Detection App* can be found [*here*](./deployment_guide/aws_deployment.md)
## Server Set-Up (For Training)
- **Google Cloud Platform (Intermediate)** - The complete tutorial can be found [*here*](https://course.fast.ai/start_gcp.html)
- **Gradient (Easy)** - The complete tutorial can be found [*here*](https://course.fast.ai/start_gradient.html)
- **AWS EC2 (Advance)** - The complete tutorial can be found [*here*](https://course.fast.ai/start_aws.html)
## Dataset Description:
|Name | No of Classes | Class Names
| ------------- |:-------------:|:-----------------:|
| Apple | 04 | 'Apple___Apple_scab','Apple___Black_rot','Apple___Cedar_apple_rust' 'Apple___healthy' |
| Blueberry | 01 | 'Blueberry___healthy' |
| Cherry | 02 | 'Cherry_(including_sour)_Powdery_mildew', 'Cherry_(including_sour)_healthy' |
| Corn | 04 | 'Corn___Cercospora_leaf_spot', 'Corn___Common_rust','Corn___Northern_Leaf_Blight','Corn___healthy' |
| Grape | 04 | 'Grape___Black_rot','Grape___Esca_(Black_Measles)','Leaf_blight_(Isariopsis_Leaf_Spot)','Grape___healthy' |
| Orange | 01 | 'Orange___Haunglongbing_(Citrus_greening)' |
| Peach | 02 | 'Peach___Bacterial_spot','Peach___healthy' |
| Pepper | 02 | 'Pepper,_bell___Bacterial_spot','Pepper,_bell___healthy' |
| Potato | 03 | 'Potato___Early_blight','Potato___Late_blight','Potato___healthy' |
| Raspberry | 01 | 'Raspberry___healthy' |
| Soyabean | 01 | 'Soybean___healthy' |
| Squash | 01 | 'Squash___Powdery_mildew' |
| Strawberry| 02 | 'Strawberry___Leaf_scorch','Strawberry___healthy' |
| Tomato | 10 | Tomato: 'Bacterial_spot','Early_blight', 'Late_blight', 'Leaf_Mold', 'Septoria_leaf_spot', 'Spider_mites','Target_Spot', 'Yellow_Leaf_Curl_Virus', 'Mosaic_virus', 'Healthy' |
Before making your valuable contribution to this project do check [CONTRIBUTING.md](https://github.com/imskr/Plant_Disease_Detection/blob/master/CONTRIBUTING.md) file.
## Citation
When using any part of this repo, please cite: [Plant Village Paper](https://arxiv.org/abs/1511.08060).
<br>
<p align='center'>
<a href="https://www.buymeacoffee.com/imskr" target="_blank"><img src="https://www.buymeacoffee.com/assets/img/custom_images/orange_img.png" alt="Buy Me A Coffee" style="height: 41px !important;width: 174px !important;box-shadow: 0px 3px 2px 0px rgba(190, 190, 190, 0.5) !important;-webkit-box-shadow: 0px 3px 2px 0px rgba(190, 190, 190, 0.5) !important;" ></a>
</p>
没有合适的资源?快使用搜索试试~ 我知道了~
温馨提示
数据采集与预处理:首先,收集和构建一个包含农作物病虫害图像的数据集。可以使用现有的公开数据集或自行采集数据。然后,对图像进行预处理,如调整大小、裁剪、增强等,以提高后续的模型训练和识别性能。 模型训练与优化:使用深度学习算法构建图像分类模型,如卷积神经网络(CNN)。通过在大规模的标注图像数据上进行训练来学习模型参数。可以使用常见的深度学习框架,如Tensorflow、Keras或PyTorch来实现模型训练和优化。 搭建云端服务:将模型部署到云端服务器上,以提供在线的农作物病虫害识别服务。可以使用云平台提供的服务,如Amazon Web Services(AWS)、Google Cloud Platform(GCP)或Microsoft Azure等,来提供高性能的计算和存储环境。 用户接口设计:设计并开发一个用户友好的前端界面,用于用户上传农作物病虫害图像和获取识别结果。可以使用前端框架如React、Vue.js或Django等来实现用户界面。 图像识别和分类:用户通过上传农作物病虫害图像,云端服务器接收到图像后,利用预训练好的深度学习模型进行图像识别和分类。模型会对图像进
资源推荐
资源详情
资源评论
收起资源包目录
SYS(1).zip (60个子文件)
Plant_Disease_Detection-master
.github
CODEOWNERS 295B
ISSUE_TEMPLATE
feature_request_template.md 613B
bug_report_template.md 699B
demo.jpg 161KB
pull_request_template.md 1KB
workflows
greetings.yml 392B
FUNDING.yml 697B
app
demo.jpg 161KB
server.py 3KB
view
2 (3).PNG 1.49MB
1 (3).PNG 1.48MB
4 (3).PNG 1008KB
index.html 3KB
models
models.md 252B
export_resnet34_model.pkl 83.45MB
static
style.css 4KB
SS.png 1.31MB
logo.png 4MB
bgd.jpg 103KB
logoWB.png 170KB
client.js 1KB
Plant_Disease_Detector_logo(With white background).png 102KB
img.jpg 77KB
Plant_Disease_Detector_logo(Transparent background).png 99KB
leaf.png 601B
LICENSE 35KB
CONTRIBUTING.md 5KB
notebook
Plant_Disease_RESNET50.ipynb 258KB
Plant_Detect_PyTorch.ipynb 184KB
Plant_Disease_Detection_TensorFlow.ipynb 1.6MB
Plant_Disease_Detection_Fastai.ipynb 949KB
Plant_Disease_Detection_Keras.ipynb 1.05MB
plant_disease_detector.ipynb 1.87MB
Plant_Disease_DenseNet121.ipynb 306KB
Plant_Disease_VGG19.ipynb 243KB
Plant_Disease_VGG16.ipynb 250KB
demo.jpg 161KB
Dockerfile 312B
CODE_OF_CONDUCT.md 3KB
requirements.txt 174B
app.yaml 89B
deployment_guide
local_flask
templates
index.html 2KB
requirements.txt 57B
webapp.py 3KB
static
style.css 3KB
bgd.jpg 103KB
client.js 1KB
img.jpg 77KB
leaf.png 601B
README.md 933B
aws_deployment.md 4KB
gcp_deployment.md 5KB
images
aws-app-init.png 45KB
gcp-console-example.png 22KB
aws-deployed-banner.png 63KB
gcp-create-project.png 16KB
gcp-open-console.png 13KB
.gitignore 19B
.dockerignore 56B
README.md 5KB
共 60 条
- 1
资源评论
荒野大飞
- 粉丝: 1w+
- 资源: 2700
下载权益
C知道特权
VIP文章
课程特权
开通VIP
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
最新资源
- 燃气表摇杆上料压装机sw18全套技术开发资料100%好用.zip
- 美容品、电脑、书检测17-YOLO(v5至v11)、COCO、CreateML、Paligemma、TFRecord、VOC数据集合集.rar
- Runtime Editor v4.4.6
- 考虑需求响应的微网优化调度matlab 程序采用粒子群算法,风力发电机、光伏发电机、储能装置、燃气轮机、柴油机组等主体,考虑负荷需求响应、soc约束等,程序模块化编程,注释清楚,有对应资料
- STM32F103C8T6实现用2.4G模块NRF2401传输室内温湿度并显示OLED 源程序
- GENEX-Probe-3.5软件及GENEX-Assistant-3.5软件使用及报告输出指导书
- , 免费,局域网,IP电话, SIP, VOIP, 视频通话,可与手机互通,手机上也安装 yealink
- 西门子S7-200PLC和MCGS组态的燃油锅炉控制系统
- Peer-to-peer LAN chat and file transfer, 局域网点对点消息传输和文件 传输,类似飞秋
- FreeModbus从机基于STM32平台移植源码
- 基于高频方波电压注入的永磁同步电机无感FOC 1.采用方波电压注入,减少了提取dq轴基频电流时LPF的使用,提高了系统的动态性能; 2.可实现带载起动和突加负载运行; 提供算法对应的参考文献和仿真模型
- 免费,局域网,IP电话, SIP, VOIP, 视频通话,可与手机互通,需要安装 手机版本
- 旅游景点数据集.zip
- 基于龙贝格观测器的永磁同步电机无感FOC 1.采用龙伯格观测器提取电机反电势,使用PLL从反电势中获得转子位置和速度信息 2.提供算法对应的参考文献和仿真模型,支持技术解答 仿真模型纯手工搭建
- 中国汽车基础软件发展白皮书4.0
- 背包、炸弹、瓶子、椅子、时钟、键盘、老鼠、人检测1-YOLO(v5至v11)、COCO、CreateML、Paligemma、TFRecord、VOC数据集合集.rar
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功