AI Rank
EN
← 开源
eeyhsong

EEG-Conformer

[TNSRE 23] EEG Transformer 2.0. i. Convolutional Transformer for EEG Decoding. ii. Novel visualization - Class Activation Topography.

Model DevelopmentArchitecturePython
在 GitHub 打开
增长势头
+024 小时新增 Star0.0%
766
Star
122
Fork
+2
本周
2
贡献者
创建于 2022-07-26 · 更新于 2026-10-15 · 今日第 14053 名
主要开发者
eeyhsongBCI-Bench

eeyhsong/EEG-Conformer 排名第 14,053，有 766 个星标。

同类别比较

eeyhsong/EEG-Conformer 排名第 14,053，此处有 8 个同类条目；ThoughtWorksInc/DeepLearning.scala 排名第 14,051。

同类别比较
名称排名指标
yaserkl/RLSeq2Seq14,044
语言:
Python
星标数:
767
分叉数:
160
简介:
Deep Reinforcement Learning For Sequence to Sequence Models
4uiiurz1/pytorch-deform-conv-v214,046
语言:
Python
星标数:
766
分叉数:
140
简介:
PyTorch implementation of Deformable ConvNets v2 (Modulated Deformable Convolution)
IntelLabs/RAG-FiT14,049
语言:
Python
星标数:
766
分叉数:
62
简介:
Framework for enhancing LLMs for RAG tasks using fine-tuning.
ThoughtWorksInc/DeepLearning.scala14,051
语言:
Scala
星标数:
766
分叉数:
86
简介:
A simple library for creating complex neural networks
mlfoundations/wise-ft14,058
语言:
Python
星标数:
766
分叉数:
72
简介:
Robust fine-tuning of zero-shot models
NVlabs/HOVER14,063
语言:
Python
星标数:
765
分叉数:
91
简介:
HOVER
ChenghaoMou/text-dedup14,067
语言:
Python
星标数:
764
分叉数:
81
简介:
All-in-one text de-duplication
buppt/ChineseNRE14,073
语言:
Python
星标数:
764
分叉数:
177
简介:
中文实体关系抽取，pytorch，bilstm+attention
关键参数与规格
关键参数与规格
参数值
语言Python
类别Model Development
子类别Architecture
关键词Biomedical, Healthcare
星标数766
分叉数122
贡献者2
创建日期2022-07-26
更新日期2026-10-15
1 天星标数0
7 天星标数2
排名14,053
上次排名6,459
排名变化-7,594
7 天星标排名8,517
上次 7 天星标排名7,269
7 天星标排名变化-1,248
总星标排名13,834
上次总星标排名13,804
总星标排名变化-30
README 摘录

EEG-Conformer EEG Conformer: Convolutional Transformer for EEG Decoding and Visualization [Paper] Core idea: spatial-temporal conv + pooling + self-attention News 🎉🎉🎉 We've joined in braindecode toolbox. Thanks to Bru and colleagues for helping with the modifications. Abstract We propose a compact convolutional Transformer, EEG Conformer, to encapsulate local and global features in a unified EEG classification framework. The convolution module learns the low-level local features throughout the one-dimensional temporal and spatial convolution layers. The self-attention module is

straightforwardly connected to extract the global correlation within the local temporal features. Subsequently, the simple classifier module based on fully-connected layers is followed to predict the categories for EEG signals. We also devise a visualization strategy to project the class activation mapping onto the brain topography. 12 Datasets Please use consistent train-val-test split when comparing with other methods. 66% (hold out) BCI_competition_IV2b - acc 84. 30% (5-fold) Citation Hope this code can be useful. I

would appreciate you citing us in your paper.

常见问题

记录了多少星标和分叉？

eeyhsong/EEG-Conformer 有 766 个星标和 122 个分叉。

仓库排名是多少？

eeyhsong/EEG-Conformer 排名第 14,053。

记录的语言和类别是什么？

eeyhsong/EEG-Conformer 有 766 个星标，语言为 Python，类别为 Model Development。

哪个仓库排名最接近？

eeyhsong/EEG-Conformer 与 ThoughtWorksInc/DeepLearning.scala 比较，后者排名第 14,051，有 766 个星标。

README

EEG-Conformer

EEG Conformer: Convolutional Transformer for EEG Decoding and Visualization [Paper]

Core idea: spatial-temporal conv + pooling + self-attention

News

🎉🎉🎉 We've joined in braindecode toolbox. Use here for detailed info.

Thanks to Bru and colleagues for helping with the modifications.

Abstract

  • We propose a compact convolutional Transformer, EEG Conformer, to encapsulate local and global features in a unified EEG classification framework.
  • The convolution module learns the low-level local features throughout the one-dimensional temporal and spatial convolution layers. The self-attention module is straightforwardly connected to extract the global correlation within the local temporal features. Subsequently, the simple classifier module based on fully-connected layers is followed to predict the categories for EEG signals.
  • We also devise a visualization strategy to project the class activation mapping onto the brain topography.

Requirements:

  • Python 3.10
  • Pytorch 1.12

Datasets

Please use consistent train-val-test split when comparing with other methods.

Citation

Hope this code can be useful. I would appreciate you citing us in your paper. 😊

@article{song2023eeg,
  title = {{{EEG Conformer}}: {{Convolutional Transformer}} for {{EEG Decoding}} and {{Visualization}}},
  shorttitle = {{{EEG Conformer}}},
  author = {Song, Yonghao and Zheng, Qingqing and Liu, Bingchuan and Gao, Xiaorong},
  year = {2023},
  journal = {IEEE Transactions on Neural Systems and Rehabilitation Engineering},
  volume = {31},
  pages = {710--719},
  issn = {1558-0210},
  doi = {10.1109/TNSRE.2022.3230250}
}
排名相邻
同类项目