Communicate between external server to get labels in AI suggestions

[hardikdava]

Is your feature request related to a problem? Please describe.
Currently, makesense supports very few AI model support i.e. yolov5, ssd, etc. The main idea is to enable use of other models also like yolov7, yolox, etc

Describe the solution you'd like
It would be great if tool can make request to an external API that sends an image and get responses of prediction in makesense format. Then the tool can work with any other relative models. An external server can be useful like fastapi, flask or any other servers.

Describe alternatives you've considered
Alternative solution is make prediction first, save it as pascal voc/yolo/coco format and load into makesense tool.

[github-actions]

👋 Hello @hardikdava, thank you for your interest in make-sense - free to use online tool for labelling photos! 🏷️

🐞 Bug reports

If you noticed that make-sense is not working properly, please provide us with as much information as possible. To make your life easier, we have prepared a bug report template containing all the relevant details. We know, we ask for a lot... However, please believe that knowing all that extra information - like the type of browser you use or the version of node you have installed - really helps us to solve your problems faster and more efficiently. 😉

💬 Get in touch

If you've been trying to contact us but for some reason we haven't responded to your issue yet, don't hesitate to get back to us on Gitter or Twitter.

💻 Local setup

# clone repository
git clone https://github.com/SkalskiP/make-sense.git

# navigate to main dir
cd make-sense

# install dependencies
npm install

# serve with hot reload at localhost:3000
npm start

To ensure proper functionality of the application locally, an npm 8.x.x and node.js v16.x.x versions are required. More information about this problem is available in the #16 issue.

[SkalskiP]

Hello @hardikdava 👋! Thank you very much for your interest in make-sense.

I absolutely love the idea! I was thinking about it some time ago, but now that it comes from the community I'll be much more motivated to make it happen.

I think that in order to deliver full solution and great experience for our users we would need to deliver example of a server that we could use for working demo. @hardikdava would you have time to help us build something like that?

[hardikdava]

Hello @SkalskiP, I can help you with an external server. Let me know how you want to proceed further.

[SkalskiP]

Hi, @hardikdava! Sorry for being silent over last 2 days, but I was putting things in motion. I just invited you to new repository make-sense-inference that is not yet public. I asked my friend to help us out with it, he is a real PRO!

[hardikdava]

Hi @SkalskiP, thank you for inviting me to the repository. I have experience with various object detectors specially on edge devices. I am happy to contribute which will help all computer vision community.

[SkalskiP]

Hi, @hardikdava! I saw that Pawel done massive progress over the weekend. I haven't had a chance yet to review it, but it looks promising. I'll keep you posted ;)