NanjingForestryUniversity/supermachine--tomato-passion_fruit

Fork 0

mirror of https://github.com/NanjingForestryUniversity/supermachine--tomato-passion_fruit.git synced 2025-11-08 22:34:00 +00:00

TG 242bb9a71b feat:新增20240627test4为现场部署版本的测试版（包含传统方法、实例分割、目标检测、图像分类多个模型）

fix:修复在20240627test4中的classifier.py的analyze_tomato函数中white_defect的函数忘记传递两个阈值量的错误；修复analyze_tomato函数中的叶片实例分割存在的问题，解决由于变量污染引起的分割错误；

2024-07-21 22:17:46 +08:00

1.7 KiB

Raw Blame History

Flask REST API

REST APIs are commonly used to expose Machine Learning (ML) models to other services. This folder contains an example REST API created using Flask to expose the YOLOv5s model from PyTorch Hub.

Requirements

Flask is required. Install with:

$ pip install Flask

Run

After Flask installation run:

$ python3 restapi.py --port 5000

Then use curl to perform a request:

$ curl -X POST -F image=@zidane.jpg 'http://localhost:5000/v1/object-detection/yolov5s'

The model inference results are returned as a JSON response:

[
  {
    "class": 0,
    "confidence": 0.8900438547,
    "height": 0.9318675399,
    "name": "person",
    "width": 0.3264600933,
    "xcenter": 0.7438579798,
    "ycenter": 0.5207948685
  },
  {
    "class": 0,
    "confidence": 0.8440024257,
    "height": 0.7155083418,
    "name": "person",
    "width": 0.6546785235,
    "xcenter": 0.427829951,
    "ycenter": 0.6334488392
  },
  {
    "class": 27,
    "confidence": 0.3771208823,
    "height": 0.3902671337,
    "name": "tie",
    "width": 0.0696444362,
    "xcenter": 0.3675483763,
    "ycenter": 0.7991207838
  },
  {
    "class": 27,
    "confidence": 0.3527112305,
    "height": 0.1540903747,
    "name": "tie",
    "width": 0.0336618312,
    "xcenter": 0.7814827561,
    "ycenter": 0.5065554976
  }
]

An example python script to perform inference using requests is given in example_request.py

1.7 KiB Raw Blame History

Flask REST API

Requirements

Run

1.7 KiB

Raw Blame History