FAQ

These are our customers most frequently asked questions (FAQ).

General questions

What is the Peltarion Platform anyway?

In short, the Peltarion Platform is a cloud-based operational AI platform that allows you to build and deploy your own deep learning models, even if you’re not an AI superstar.

To get started, check out our tutorials.

What do I need to use the Peltarion Platform?

To use Peltarion Platform you basically need Google Chrome installed on your computer. Then you’re good to go! For more detailed requirements, check our details in the Technical requirements article.

Where do I ask for help?

If you have any questions about the Peltarion platform functionality, please contact support@peltarion.com.

How do I report a bug?

If you find a bug, please submit a bug report through Platform issue report or send us an email to support@peltarion.com.

Datasets view

How do I navigate to the Datasets view?

First, click + New project in the left panel to create a project. Then click on Open. This will take you to the Datasets view.

To get familiar with the workflow, check out our tutorials that will guide you step by step.

I use the downloaded .h5 when I test. Do I have to standardize the test dataset in the same way as the training dataset?

Yes, you have to be consistent and perform the same preprocessing for your train and test dataset.

If you use the Deployment API instead of a downloaded .h5, the same data processes that have been done during training will be performed automatically. That is, you don’t need to do anything.

How can I view my results for the test dataset?

You can’t use a test dataset on the Peltarion Platform right now. But you can use our tool Sidekick.

But first, make sure that your deployment is Enabled. This is how you can enable a deployment.

Test with Sidekick

Use Sidekick! Sidekick handles the mundane tasks like sending data examples to the deployment endpoints to get predictions.

Test with CURL or python using JSON requests

Another way to test your model is to use this code for CURL or this for python using JSON requests.

How do I prepare my data to fit the Platform?

Use Sidekick! The code in Peltarion’s public GitHub repo Sidekick handles the mundane tasks like bundling up data into the Platform’s preferred format.
Link: https://github.com/Peltarion/sidekick

You should also check the article on our requirements.

Modeling view

I got an error message in the Modeling view. What does it mean?

There are several error messages on the Platform. We try to make them as short and full of information as possible. But if you want further guidance, check out cause and remedy for each error message in Error messages.

Can I have multiple input blocks?

Yes, you can have multiple inputs, e.g., in our Tutorial - Predict California house prices, we use both images and tabular data as input.

Use the concatenate block or the add block to combine the inputs.

Which block should use when I’m designing my model?

It depends on your data and on your task. Check out our cheat sheets for tips and tricks on how to solve your problem.

How many nodes should I have in the last dense block?

As many as the shape of your target, so it depends on your task.

This is explained in our webinar: Hands on with deep learning and predictive maintenance.

For more info check out our cheat sheets for tips and tricks on how to solve your problem.

How do I work with multiple experiments?

Easy experimenting is a key feature of the Peltarion Platform.

You can run multiple experiments at the same time. If you notice that an experiment is performing better, you can easily duplicate it. Click on the Experiments option menu (ThreeDotsButton_A) and select Duplicate. Name the new experiment and then decide if and from which checkpoint you want to copy the weights.
Continue experimenting in the new experiment and then keep duplicating, tweaking and running until you are happy with the result!

Deployment view

How do I use a deployed model?

First, follow the instructions in the Deployment view part of the Knowledge center.

Use Sidekick

Then you should use Sidekick! The code in Peltarion’s public GitHub repo Sidekick handles tasks like sending data examples to the deployment endpoints to get predictions.
Link: https://github.com/Peltarion/sidekick

Subscription questions

How do I reset my password?

  1. To reset your password, go to this link: Reset password.

  2. Enter your e-mail and click Send.

You will now receive an e-mail with instructions on how to reset your password.

How do I upgrade my usage plan?

To upgrade your usage plan, please contact sales@peltarion.com.