PalletML (beta)
HomeCourseTwitter
2020.01.01
2020.01.01
  • Machine Learning on Mobile
  • Quickstart
    • Your First No-Code Smart App
    • Download Pre-Built Models
  • Deploy
    • Deploy Your Model
    • Share Your Model
  • Explore
    • Explore
  • Create an Image Classifier
    • Google Teachable Machine (No-Code)
  • Contact
    • Share Feedback
    • Support
    • Twitter
Powered by GitBook
On this page
  • Introducing Pallet
  • Create an Image Classification App
  • Prepare Your Model
  • Deploy Your Model With Pallet
  • Up Next

Was this helpful?

  1. Quickstart

Your First No-Code Smart App

PreviousMachine Learning on MobileNextDownload Pre-Built Models

Last updated 4 years ago

Was this helpful?

Learn how to create an image classification app with Pallet in under 15 minutes, without code!

Introducing Pallet

The technology for building AI-enhanced applications is more accessible than ever before, but the process of actually building & distributing these 'smart apps' can still be a challenge.

Pallet is a no-code platform that enables you to quickly turn machine learning models into shareable apps, and access them anytime through a simple consistent interface.

In this tutorial you will use Pallet to create an image classification app just 15 minutes.

Create an Image Classification App

Creating an image classification app with Pallet is overall just a quick 3-step process:

  1. Create a new Project,

  2. Upload your model assets, and

  3. Tune your Project’s settings according to your model

All you need to get started is an image classification model and corresponding set of classification labels - a common pair of files we call model assets.

Let's start by preparing your model assets for deployment.

Prepare Your Model

To create a classification app with Pallet, you just need a TensorFlow Lite model and a corresponding list of labels.

If you already have these model assets, you're ready to deploy, and you can skip this step. If you don't have model assets on hand, get started with a pre-built model, or follow one of our tutorials on quickly building and training custom image classification models:

Developed by Google, this model can classify 1,000 different objects - from umbrellas to volcanoes!

Each download is zip file containing a TensorFlow Lite Model + Labels pair. When the download completes, unzip the model assets to your computer.

Classifies daisies, dandelions, roses, sunflowers, and tulips.

Each download is zip file containing a TensorFlow Lite Model + Labels pair. When the download completes, unzip the model assets to your computer.

This model can distinguish between 120 different dog breeds.

Each download is zip file containing a TensorFlow Lite Model + Labels pair. When the download completes, unzip the model assets to your computer.

This model can tell if you're throwing Rock, Paper, or Scissors from the classic game.

(For best results, take a picture of your hand in Rock, Paper, or Scissors formation over a clear plain surface.)

Each download is zip file containing a TensorFlow Lite Model + Labels pair. When the download completes, unzip the model assets to your computer.

Deploy Your Model With Pallet

and Sign Up to create a new account

3. Every model you deploy with Pallet belongs to a Project. Create a New Project for your model.

4. Choose a name for your project and click Create.

5. Browse or Drag & Drop the model assets that you prepared earlier, then click Upload.

7. Tap your Project to open a detailed view. (You'll learn how to add details to your Project in another guide).

With Pallet, classification models for photos work out of the box, so you don't need to tune any settings for this project right now.

You can immediately start classifying photos by taking a picture with your camera, selecting a picture stored on your device, or submitting a link to an image.

In just a few minutes, you were able to turn an image classification model into a mobile app, without any code!

By deploying with Pallet, your model is infinitely scalable, easily upgradable, and ready to be shared with the world.

Up Next

Now that you've got the hang of deploying models with Pallet:

  • Learn how to quickly share your model with any number friends, colleagues, and other users in just a few taps.

  • Learn how to train and deploy your own custom image classification model:

  • Create more classification apps from our pre-built models:

  • Explore more of Pallet

If you only want to explore Pallet, just and check out the section of this guide to see everything you can do.

Don't worry if you don't have these assets ready. Use one of our to get started quickly.

Currently, Pallet supports models trained for image classification, and will eventually support models and frameworks designed for a variety of different tasks.

In this tutorial, you will use the to deploy a model to your phone. In another tutorial we'll show you how to deploy models right from the itself.

Examples below:

1. Install Pallet from the Google Play Store

2. In your computer browser, visit in a new tab and Log In to the account you just created.

And that's it! Your model is now deployed.

6. Return to the Pallet app, navigate to your Profile , and pull to refresh your list of Projects.

Your new Project will appear.

8. Now Launch your app (Skip the Tune Settings dialog by tapping Launch)

9. Congratulations

✅
👤
✨
🚀
🎉
download the app
Explore
TensorFlow Lite
Pallet Web Console
Pallet app
Create a custom image classification model →
Download a pre-built image classification model →
app.palletml.com
Share Your Model
Create an Image Classifier
Download Pre-Built Models
Explore
example models
I have a model ↓
12MB
MobileNet.zip
archive
Download MobileNet assets
8MB
FlowerNet.zip
archive
Download FlowerNet assets
8MB
Dog Breeds.zip
archive
Download Dog Breeds assets
8MB
Rock-Paper-Scissors.zip
archive
Download RPS assets