Skip to content

Getting Started

This documentation explains how to install furiosa-models, how to use available models in furiosa-models, and how to explore the documents.

Prerequisites

furiosa-models can be installed on various Linux distributions, but it has been tested on the followings:

  • CentOS 7 or higher
  • Debian bullseye or higher
  • Ubuntu 20.04 or higher

The following packages should be installed, but the followings are installed by default in most systems. So, only when you have any dependency issue, you need to install the following packages:

  • libstdc++6
  • libgomp

Installing

You can quickly install Furiosa Models by using pip as following:

pip install --upgrade pip setuptools wheel
pip install 'furiosa-models'

Info

Older versions of wheel may reject the native-build wheels of furiosa-models. Please make sure of installing & upgrading Python packaging tools before installing furiosa-models.

Building from Source Code (click to see)

Or you can build from the source code as following:

git clone https://github.com/furiosa-ai/furiosa-models
pip install ./furiosa-models

Quick example and Guides

You can simply load a model and run through furiosa-sdk as the following:

Info

If you want to learn more about the installation of furiosa-sdk and how to use it, please refer to the followings:

from furiosa.models.vision import SSDMobileNet
from furiosa.runtime.sync import create_runner

image = ["tests/assets/cat.jpg"]

mobilenet = SSDMobileNet()
with create_runner(mobilenet.model_source()) as runner:
    inputs, contexts = mobilenet.preprocess(image)
    outputs = runner.run(inputs)
    mobilenet.postprocess(outputs, contexts)

This example does:

  1. Load the SSDMobileNet model
  2. Create a Runner, which is one of the main classes of Furiosa Runtime, that can load an ONNX/tflite model onto NPU and run inferences.
  3. Run an inference with pre/post process functions.

A Model instance is a Python object, including model artifacts, metadata, and its pre/postprocessors. You can learn more about Model object at Model object.

Also, you can find all available models at Available Models. Each model page includes the details of the model, input and output tensors, and pre/post processings, and API reference.

If you want to learn more about Runner in Furiosa Runtime, please refer to below links.