Inference uses a trained model to make predictions or draw conclusions based on input data. This process applies the learned knowledge and statistical relationships encoded in the model to new, unseen data. Specifically, in image inference, an image is passed through a trained AI model to obtain a classification or other predictions based on the patterns within the model.
The AML Dashboard is a web-based tool that allows users to interact with the AML framework. This tutorial guides you through the process of managing AML-IP Agent Nodes—creating, stopping, and deleting them—using the AML Dashboard. It also demonstrates how to perform distributed training and inference over WANs and fetch a pretrained model from a computer situated in another LAN to continue training your model.
The eProsima Fast DDS Monitor is a powerful graphical desktop application designed for monitoring networks that utilize the eProsima Fast DDS library. It enables real-time tracking of communication statuses among various entities, making it an essential tool for debugging and optimizing distributed systems, including AML-IP networks. Fast DDS Monitor allows accessing comprehensive data on each DDS domain, gaining insights into DomainParticipants, publishers, subscribers, and topics, and viewing a graphical representation of the network's physical architecture.
The AML Dashboard is designed to simplify the interaction with the AML framework, making it easier for researchers, computer scientists, and creative professionals to train, evaluate, and apply AML models.
The Agent Node relies on the eProsima DDS Router. This tool, developed and maintained by eProsima, enables the connection of distributed DDS networks. DDS entities such as publishers and subscribers deployed in one geographic location and using a dedicated local network will be able to communicate with other DDS entities deployed in different geographic areas on their dedicated local networks as if they were all on the same network.
The ALMA project leverages AML properties to develop a new generation of interactive, human-centered machine learning systems.
Plaza de la Encina 10-11, Núcleo 4, 2ª Pl.
28760 Tres cantos - Madrid (España)
This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 952091.
