# Grape Disease Detection Tutorial ## 安裝步驟 ### 本專案將進行葡萄分級檢測,可參考以下步驟執行: [開啟ipynb檔執行葡萄檢測](https://drive.google.com/file/d/1qM-l2DreHI8QMEEraQ0kYHX6j2QPVRU_/view?usp=sharing) 葡萄分級檢測將分為兩大步驟: ### 使用Transformer進行 Object Detection 將葡萄影像帶入 Object Detection模型 (DETR) 帶入檢測影像: <img src="https://i.imgur.com/DPBuS1O.jpg" width="150" height="300" align="middle" /> ``` # Upload Grape image. # img_sample = files.upload() # img_path = list(img_sample.keys())[0] # Or Use Sample image img_path = "test_img/disease_0001.jpg" # disease_0001.jpg, disease_0002.jpg, disease_0003.jpg ``` 結果影像 <img src="https://i.imgur.com/Mzitywn.png" width="150" height="300" align="middle" /> 並將結果影像切割成多個單顆葡萄影像後,並儲存至雲端暫存區 content └─ grape-disease-detection-tutorial └─ result ``` output_dir = "./result/" crop_one_grape(img, B_Boxes, output_dir) ``` ### 使用Transformer進行Anomaly Detection 將單顆葡萄影像帶入 Anomaly Detection 模型 (PaDiM) <img src="https://i.imgur.com/g3yGKb5.png" width="600" height="250" align="middle" /> 輸出多個單顆葡萄影像檢測結果 <img src="https://i.imgur.com/aQGADWX.jpg" width="600" height="250" align="middle" />
×
Sign in
Email
Password
Forgot password
or
By clicking below, you agree to our
terms of service
.
Sign in via Facebook
Sign in via Twitter
Sign in via GitHub
Sign in via Dropbox
Sign in with Wallet
Wallet (
)
Connect another wallet
New to HackMD?
Sign up