Latest News

The AML Dashboard is a web-based tool that allows users, developers and researchers  to interact with the AML framework.

This tutorial showcases the process of making predictions using an AML model through the AML Dashboard, covering both real-time and batch prediction workflows.

Prerequisites

Ensure you have installed the AML Dashboard using one of the following methods:

• Linux Installation
• Docker Image Installation

For more information, check the AML Dashboard Interfaces and AML Dashboard Usage sections.

Running the demo

To run the necessary components for evaluating a model and making predictions using the AML Dashboard, follow these steps:

Start the backend server

1. Navigate to the backend directory.

cd backend

2. Load the AML-IP environment.

source /AML-IP/install/setup.bash

3. Start the server:

python3 server.py

Start the Inference Node

Warning

Before starting the inference node, ensure that there is at least one model and training set available in the download directory.

1. Load the AML-IP environment.

source /AML-IP/install/setup.bash

2. Navigate to the backend directory.

cd backend

3. Start an inference node:

python3 inference.py

Start the AML Dashboard

1. Navigate to the frontend/aml_dashboard directory.

cd frontend/aml_dashboard

2. Start the AML Dashboard:

npm run dev

3. Access the dashboard at http://localhost:5173/.

Evaluating the Model

To evaluate a model using the AML Dashboard, follow these steps:

1. Navigate to the Batch Prediction tab on the AML Dashboard.
2. Click on the Update Predictions button in the Algebraic Machine Learning section to initiate the predictions.
3. The confusion matrix for the model’s predictions will be displayed. This matrix helps in assessing the model’s performance by showing the accuracy and errors.

Note

If binary classification is used, the target class chosen in the training will be displayed as the positive class, while the other classes will be considered as the negative class.

Real-Time Predictions

Warning

This feature is only available when the dataset is Sensors.

To make real-time predictions using the trained model with the AML Dashboard, follow these steps:

1. Go to the Real-time Prediction tab on the AML Dashboard.
2. Click on the toggle prediction button in the Predict for AML section to start the real-time prediction process.
3. In the webcam section, toggle the activate video button to enable the webcam.

Next Steps

In the upcoming article, we will provide a step-by-step tutorial on performing a Distributed Inference Scenarion with TensorFlow on the ROSbot 2R.

By Denisa Alexandru from eProsima

MORE INFORMATION ABOUT ALMA:

For any questions please contact This email address is being protected from spambots. You need JavaScript enabled to view it..