Palletworks with any image classification model developed with TensorFlow. Just convert your model to TensorFlow Lite, prepare a plaintext labels file, and follow the steps for deployment.
You can also use a no-code tool to train and export a ready-to-deploy image classification model. (Learn how)
Eventually Pallet will support models and frameworks designed for a variety of different tasks.
How many models can I deploy?
The number of models you can deploy depends on your plan, and the amount of Cloud Storage that comes with it.
On the Free Plan you can deploy up to 3 Models, and the Pro Plan comes with 500 MB of Cloud Storage (enough space to deploy 50 cat-or-dog classifiers).
If none of our plans are suited to your needs, just get in touch and we'll work something out.
Where and how is my data stored?
Unless otherwise noted, all model inference occurs locally on your device. When you save a classification (optional), the image and prediction results are saved to your account and synced to the cloud.
In other words, no data related to the images you send into a classifier, or the results, ever leave your device without your permission.
Models and predictions that are uploaded to the cloud are stored securely with Amazon Web Services (AWS), the same cloud used by Netflix, Airbnb, Pinterest, Duolingo, and Slack.