xkrs_manan/RODY

Fork 0

Files

SetParams

app

configs

controller

core

models

schemas

services

utils

yolov5

.github

classify

data

models

utils

aws

docker

flask_rest_api

README.md

example_request.py

restapi.py

google_app_engine

loggers

__init__.py

activations.py

augmentations.py

autoanchor.py

autobatch.py

benchmarks.py

callbacks.py

dataloaders.py

downloads.py

general.py

loss.py

metrics.py

plots.py

torch_utils.py

.dockerignore

.gitattributes

.gitignore

.pre-commit-config.yaml

CONTRIBUTING.md

LICENSE

README.md

detect_server.py

export.py

hubconf.py

train_server.py

tutorial.ipynb

val.py

validate_server.py

zdp_R-ODYv1.pt

__init__.py

exts.py

file_tool.py

json_util.py

run.py

docs

tests

.gitignore

SetParams_Demo.py

__init__.py

deploy.sh

docker-compose.yml

nohup.out

pytest.ini

requirements.txt

requirements_p37.txt

setparams.py

History

552068321@qq.com 6f7de660aa first commit

2022-11-04 17:37:08 +08:00

example_request.py

first commit

2022-11-04 17:37:08 +08:00

README.md

first commit

2022-11-04 17:37:08 +08:00

restapi.py

first commit

2022-11-04 17:37:08 +08:00

README.md

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