Quick start

Deploy sample AI model using Syndicai Platform
Yolo V5 model prediction

In this super-fast tutorial, you will deploy one of the most popular object detection algorithms YoloV5 with just a click of a button.

Impossible? Let's do it!

Requirements

You just need 5min to go through the quick start.

  • No need to prepare your own model.

  • No need to have access to any cloud.

  • No need to fork the repository.

Tutorial

Step 1 - Deploy a Model

Go to the YoloV5 repository, and click the button Syndicai Deploy. You will be redirected to the Syndicai Platform. As soon as you finish the form, the platform will start deploying the model. To monitor the status of the deployment process go to the “Builds” section. You will need to wait a couple of minutes until you see the Active status next to your model name.

Step 2 - Run a Model

After you complete the deployment, please wait for the model to become Active so that you can run it via platform by pasting the following sample_input.json with image url.

{
"url": "https://images.pexels.com/photos/2083866/pexels-photo-2083866.jpeg?auto=compress&cs=tinysrgb&h=750&w=1260"
}

...or you can access it via generated REST API. Just go to "Integrate" section and use the API below.

curl -X POST https://***.c1.syndic.ai \
-H 'content-type: application/json' \
-d @sample_data.json

Conlusion - What just happend?!

  1. We took a deep learning model that was:

    1. trained,

    2. prepared (syndicai.py & requirements.txt),

    3. placed in git repository

  2. By clicking a button Syndicai Deploy a git repository with your model was connected to the platform and the whole environment and infrastructure was automatically created during the deployment process.

What's next?

Integrate API

Copy & paste REST API of the model (which at the bottom of the Model Profile Page) and integrate with any kind of device you want.

Create a Showcase

With generated API you can create a Showcase website based on your deployed models. In order to do it quickly, you can use our boilerplate and easily deliver your AI model in a stylish way.

Check other sample models

Go to our repository with prepared models ready-to-deploy in order to play a little more and explore how they are prepared so they can be easily deployed.

Deploy your model

You can also take any machine learning model you like and deploy it on the platform. In order to do it properly go to Develop section.