

This model provides top-k category predictions out of 1000 classes on ImageNet. This network provides state of the art accuracy on ImageNet validation (top-1: 82.242 - top-5: 96.114) at the same time it provides a smaller model and faster inference. It features a simple pricing model where only pay for what you use with a simple metered pricing model.

This Algorithm allows you to easily train a model for image classification based on the state of the art EfficientNet algorithm. After training a custom model you can deploy the trained model as an endpoint. It features a simple pricing model where only pay for what you use with a simple metered pricing model

Detect objects on images using the state of the art Mask R-CNN

Extrapolations is a platform designed to streamline the process of integrating predictive analytics into decision-making workflows. By leveraging advanced machine learning models, Extrapolations allows users to extrapolate valuable insights from complex datasets, empowering businesses and researchers to make data-driven decisions with greater accuracy and efficiency. The platform offers comprehensive documentation available at [https://docs.extrapolations.dev/](https://docs.extrapolations.dev/), guiding users through its features and capabilities. With a focus on usability and scalability, Extrapolations caters to a broad range of industries, facilitating enhanced forecasting and trend analysis.