# SuperBruceJia/EEG-DL

A Deep Learning library for EEG Tasks (Signals) Classification, based on TensorFlow.

Repository: https://github.com/SuperBruceJia/EEG-DL
Canonical: https://ross.abutalabs.com/products/eeg-dl
Homepage: https://www.nitrc.org/projects/eeg_dl_library
Language: Python
License: MIT
License Family: permissive
Topics: deep-learning, eeg-classification, eeg-signals-processing, tensorflow, motor-imagery-classification, eeg-data, cnn, rnn, gcn, one-shot-learning, residual-learning, densenet, resnet, graph-convolutional-neural-networks, lstm, gru, attention-mechanism, fully-convolutional-networks, transformer, transformers
Last push: 2025-07-20T19:10:46+00:00

## Health v2 (maintenance only)
Score: 47/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 32, release rhythm 35, longevity 100
- inputs: {"age_days": 2316, "days_push": 409, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1167, forks 230 (observed 2026-08-28T04:03:50.734794+00:00)

## What it is
EEG-DL is a deep learning library built on TensorFlow for classifying EEG signals, supporting many architectures including CNNs, RNNs, GCNs, ResNets, Transformers, and attention mechanisms. It is aimed at neuroscience and brain-computer interface research, particularly motor imagery task decoding.

## Use cases
- classify EEG motor imagery signals with deep learning
- decode four-class motor imagery tasks from EEG
- apply CNNs or GCNs to raw EEG signals
- experiment with transformers and attention models on EEG data
- build brain-computer interface classifiers
- benchmark deep learning models on EEG datasets

## When to choose
- you need ready-to-use TensorFlow models for EEG classification
- you want to compare many DL architectures (CNN, RNN, GCN, Transformer) on EEG tasks
- you are doing BCI or motor imagery research in Python

## When to avoid
- you need real-time EEG processing or a production BCI system
- you work with PyTorch instead of TensorFlow
- your signals are not EEG/neurophysiological

## Facets
- artifact type: library
- maturity: active
- function: deep-learning, machine-learning, nlp
- domain: deep-learning, machine-learning, healthcare, artificial-intelligence
- platform: python, cross-platform
- tags: eeg, tensorflow, brain-computer-interface, motor-imagery, signal-classification, cnn, rnn, graph-convolutional-networks, transformer, neuroscience

## Member repositories
- SuperBruceJia/EEG-DL (main) score 47

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:50.734794+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:28:50.002457+00:00, confidence not recorded.
  - readme: https://github.com/SuperBruceJia/EEG-DL (fetched 2026-08-28T04:03:50.734794+00:00, sha 8ea3ad03d9a6)
  - homepage: https://www.nitrc.org/projects/eeg_dl_library (fetched 2026-08-29T12:34:55.505105+00:00, sha feaf119f703a)
  - site_page: https://www.nitrc.org/include/about_us.php (fetched 2026-08-29T12:34:55.514484+00:00, sha 3f9fc3c1b6c2)
- Data as of 2026-08-30T08:39:29.467469+00:00.