dAIEDGE-VLab is a virtual environment designed to compare and evaluate the performance of AI models across various objectives, providing users with an intuitive interface to configure tests, visualise results, and compare models in different environments and contexts. All of this takes place within a secure setting, where data and models are handled with the highest level of protection.
In this initial phase, access is restricted to partners, relevant organisations, and researchers, including participants in the open call, as required. If you meet the criteria, gain access today and request your account by clicking here.
Within dAIEDGE-VLab, our API enables users to streamline the process of training, evaluating, and deploying artificial intelligence models on edge devices.
To get started, dAIEDGE-VLab offers a step-by-step user guide that details how to set up the environment and begin working with the API. This documentation is essential to ensure a smooth experience right from the start.
The typical workflow includes preparing the dataset, such as the MNIST set of handwritten digits, which is normalised and split into training, validation, and test sets. Next, a simple neural network is defined and trained using this data. The trained model is converted to an optimised format (TensorFlow Lite) and saved locally. Finally, it is evaluated on various devices, such as a Raspberry Pi 5 or a Qualcomm Bree Gen 2, using the provided data.
Would you like to see all these steps in action? Click here to watch the full video on YouTube.