OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Models

Arl Eegmodels

Arl Eegmodels is a Python collection of Keras and TensorFlow convolutional neural network models for EEG signal processing and classification. It includes EEGNet, an SSVEP-oriented EEGNet variant, DeepConvNet and ShallowConvNet, with a documented workflow for configuring, fitting and predicting with a selected model.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Arl Eegmodels — OpenViST project profile in AI Models.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you are building a Python-based EEG classification workflow and want several documented CNN architectures to configure and compare on your data.

Who it is for

  • Researchers comparing convolutional architectures on EEG data
  • Developers building EEG classification pipelines or brain-computer interface prototypes

Documented uses

  • Configure a documented CNN architecture for a classification task using class, channel and sample dimensions.
  • Fit an EEG classifier and use it to predict on test data.
  • Compare EEGNet, its SSVEP variant, DeepConvNet and ShallowConvNet within a research workflow.
  • Explore EEGNet single-trial feature relevance using the separately documented DeepExplain approach.
Before you choose

Requirements & limits

  • The README requires Python 3.7 or 3.8 and TensorFlow 2.x; it reports CPU and GPU operation with TensorFlow 2.0–2.3.
  • Model construction requires the user to provide the number of classes, channels and samples; the README does not supply dataset-specific values.
  • The ERP sample script has additional MNE, PyRiemann, scikit-learn and matplotlib dependencies.
  • Feature-relevance examples use DeepExplain, and the README notes extra steps for TensorFlow 2.
  • The repository’s legal section describes the project as governed by CC0 1.0 and notes that other portions are subject to copyright protection under 17 USC Sec. 105 and Apache 2.0 licensing.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Configure and train a model for EEG classification

Import a selected model, configure its input dimensions, then compile, fit and predict as shown in the README.

Before you start

  • Python 3.7 or 3.8
  • TensorFlow 2.x; the README reports CPU and GPU operation with versions 2.0–2.3
  • Repository contents placed in the PYTHONPATH environment variable
  • EEG data and labels prepared for the selected classification task

Steps

  1. Place the repository folder contents in PYTHONPATH.

  2. Import EEGNet, ShallowConvNet or DeepConvNet from EEGModels.

  3. Configure the model with the number of classes, channels and samples.

  4. Compile with categorical cross-entropy and Adam, then fit on training data and call predict on test data.

Expected outcome

A configured and fitted classifier that can generate predictions for test data.

Guide limitations

  • The README gives illustrative placeholders for model dimensions and training data; it does not provide a complete dataset-specific training recipe.
  • TensorFlow operation is reported as verified for versions 2.0–2.3, not as a compatibility guarantee for other versions.
  • For the EEG/MEG ERP sample script, additional dependencies are required: MNE >= 0.17.1, PyRiemann >= 0.2.5, scikit-learn >= 0.20.1 and matplotlib >= 2.2.3.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
vlawhern/arl-eegmodels · Official homepage title · retained in its source language
How we review sourcesSuggest a correction