Vision models

Vision models icon SambaStudio’s vision models enable you to derive meaningful information from digital images. Our vision models train computers to interpret and understand the visual world. Using SambaStudio’s provided dataset, or a custom dataset of your own, the SambaStudio vision models can accurately identify and classify objects.

Model architecture

The table below describes the ML App and architecture for the SambaStudio provided vision models. The linked document provides the following information for each model:

  • Data preparation requirements

  • Prompt guidelines

  • Usage guidelines

  • Hyperparameter and inference settings

Filed of application ML App Architecture Models

Vision

Image classification

ViT