missing flask app for google app engine

[robmarkcole]

🚀 Feature

Some files related to deploying yolov5 on app engine were added in #964 but still missing is the actual flask app which would comprise of a main.py. Additionally a README would be nice here.

Motivation

I assume once everything is in place it is a one line command to deploy the app, which would be neat

CC @Guilhen

[github-actions]

👋 Hello @robmarkcole, thank you for your interest in 🚀 YOLOv5! Please visit our ⭐️ Tutorials to get started, where you can find quickstart guides for simple tasks like Custom Data Training all the way to advanced concepts like Hyperparameter Evolution.

If this is a 🐛 Bug Report, please provide screenshots and minimum viable code to reproduce your issue, otherwise we can not help you.

If this is a custom training ❓ Question, please provide as much information as possible, including dataset images, training logs, screenshots, and a public link to online W&B logging if available.

For business inquiries or professional support requests please visit https://www.ultralytics.com or email Glenn Jocher at glenn.jocher@ultralytics.com.

Requirements

Python 3.8 or later with all requirements.txt dependencies installed, including torch>=1.7. To install run:

$ pip install -r requirements.txt

Environments

YOLOv5 may be run in any of the following up-to-date verified environments (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled):

• Google Colab and Kaggle notebooks with free GPU:
• Google Cloud Deep Learning VM. See GCP Quickstart Guide
• Amazon Deep Learning AMI. See AWS Quickstart Guide
• Docker Image. See Docker Quickstart Guide

Status

If this badge is green, all YOLOv5 GitHub Actions Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv5 training (train.py), testing (test.py), inference (detect.py) and export (export.py) on MacOS, Windows, and Ubuntu every 24 hours and on every commit.

[glenn-jocher]

@Guilhen in reference to your Google app engine PR #964, would you be able to provide a minimum Flask app example as requested by @robmarkcole? I think this would comprise a main.py file with a short READEME.md. If possible this would help everyone use the app engine directory that you created initially. Thanks!

[robmarkcole]

I expect it will not be much more complicated than the example at https://pytorch.org/tutorials/intermediate/flask_rest_api_tutorial.html#integrating-the-model-in-our-api-server

[Guilhen]

ok got it, I have done this in the past. As @robmarkcole mentioned, creating the app is fairly straightforward. The tricky point could be the image encoding/decoding. You are right @robmarkcole you can deploy to the cloud from the terminal using the gcloud command.
I'll put something together and create a PR.

[glenn-jocher]

@Guilhen thanks Guilhen! I think a tutorial/demo would really help people (me too!) get started with it more easily.

[glenn-jocher]

@robmarkcole do you think we should use https://github.com/jzhang533/yolov5-flask as a reference?

[robmarkcole]

@glenn-jocher I actually forked that and tidied it up a bit https://github.com/robmarkcole/yolov5-flask

In the process of getting yolov5-flask up and running I created a pair of related issues want to look at before proceeding with this issue:

• Model predict with forward will fail if PIL image does not have filename attribute #2702
• Return predictions as json #2703

[robmarkcole]

Both the two issues referenced above are now closed, so full steam ahead on this one :-)

[glenn-jocher]

@robmarkcole yeah thanks for spotting those issues! I think the hub models are quite improved now.

Yes I think completing a Flask app with a README in the directory would be great, especially for non web-developers like me to understand this better. If we had a main.py that we just had to execute with python main.py for the demo to start that would be awesome.

[github-actions]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.