DeGirum AI Hub
DeGirum AI Hub solves the Edge AI development problem by providing the necessary toolchains to design, run, and evaluate AI models across different hardware platforms, all from a single platform.
The DeGirum AI Hub includes the following components:
- DeGirum Device Farm accessible through the Application Server and PySDK
- Application Server
- Model Zoos hosted on DeGirum infrastructure
The DeGirum Device Farm is a set of computing nodes with various AI hardware accelerators installed in those nodes, including: DeGirum ORCA™, Google Edge TPU, Intel® Movidius™ Myriad™ VPU. The farm nodes are hosted by DeGirum.
The Application Server provides web APIs to perform AI inference on the Device Farm. Starting from version 0.3.0, PySDK supports the Application Server web API and provides the same level of functionality transparently to the end user: you may run exactly the same code on the AI Hub as you would for traditional use cases such as local inference or AI server inference.
A AI Hub Model Zoo is a collection of AI models, stored on DeGirum’s infrastructure. A registered DeGirum AI Hub user can create and maintain multiple model zoos with either private or public access. A model zoo with private access is visible to all users belonging to the same organization. A model zoo with public access is visible to all registered users of DeGirum AI Hub. DeGirum maintains a public model zoo with an extensive set of AI models available free of charge to all registered users.
The DeGirum AI Hub Portal provides a GUI to access the various AI Hub assets such as:
- API access tokens, which are required to access the Application Server through PySDK;
- Model zoos belonging to the user’s organization;
- PySDK documentation;
- Model Compiler and Model Parameters Wizard.