EEG-Conformer
EEG-Conformer copied to clipboard
eeyhsong
EEG Transformer 2.0. i. Convolutional Transformer for EEG Decoding. ii. Novel visualization - Class Activation Topography.
Hi there, I read the paper and was excited to see a method that is lightweight and efficient. However, when I was trying on my own data set, the size...
Dear author, I have used your conformer recently and its effect is really good. I would like to ask you the following questions: 1. I feel that the fitting speed...
It seems that the visualization script is missing a way to select which target category to visualize. In the CAT.py script, a variable called `target_category` exists but is not used...
I found that using my preprocessing program below ``` % 获取文件夹中的所有 gdf 文件 gdfFolder = './BCICIV_2a_gdf/'; % 指定文件夹路径 matFolder = './true_labels/'; outFolder = './Data/'; gdfFiles = dir(fullfile(gdfFolder, '*.gdf')); % 获取文件夹中的所有...
Hi, Thanks for sharing your very interesting work. Can you share the code for the band-pass filter [8] and the augmentation code for this BCI Competition IV Dataset 2a so...
作者您好，我最近在复现您的模型中出了精度偏低的问题，A01acc为0.78，A02acc为0.50，A03也为0.86左右但是S5的acc确意外地达到了75，我是用mne进行预处理的，提取2-6s和ID为768的运动想象数据，并在预处理阶段进行了数据标准化（原论文中的get_data模块已经做了调整改成了自己预处理之后的数据），代码其他部分我并没有修改。avg_acc在73左右 另一个发生是：不做带通滤波似乎对精度有所提升（多次实验结果） 以下是我的python代码(未作滤波操作) ``` import random from collections import Counter import mne import numpy as np import torch from sklearn.preprocessing import StandardScaler,OneHotEncoder import scipy.io import torchvision.transforms as transforms from sklearn.model_selection...
I downloaded data BCI-IV-2a from the official website. Referring to your paper, I used the python MNE package for preprocessing. Running your Conformerd code on GitHub without filtering has an...
