1.EEGNet 网络代码复现(2020.09.23)

最新推荐文章于 2025-03-20 18:49:05 发布

燥栋

最新推荐文章于 2025-03-20 18:49:05 发布

阅读量5.8k

点赞数 12

分类专栏： EEG_MI-学习笔记文章标签：深度学习 python 神经网络

本文链接：https://blog.csdn.net/qq_45363979/article/details/108755643

版权

EEG_MI-学习笔记专栏收录该内容

1 篇文章

订阅专栏

本文介绍了一种用于脑机接口的紧凑型卷积神经网络EEGNet。该网络利用深度可分离卷积实现高效的特征提取，并通过三个主要模块进行信号处理。首先通过卷积层增强通道间的依赖关系，随后采用深度卷积降低参数数量，最后通过分离卷积进一步提取特征并减少计算复杂度。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

《EEGNet: A Compact Convolutional Neural Network for EEG-based Brain-Computer Interfaces》

有时间再详细写一下网络的具体结构和深度可分离卷积的知识。

# 导入工具包
import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F


class EEGNet(nn.Module):
    def __init__(self, classes_num):
        super(EEGNet, self).__init__()
        self.drop_out = 0.25

        self.block_1 = nn.Sequential(
            # Pads the input tensor boundaries with zero
            # left, right, up, bottom
            nn.ZeroPad2d((31, 32, 0, 0)),
            nn.Conv2d(
                in_channels=1,  # input shape (1, C, T)
                out_channels=8,  # num_filters
                kernel_size=(1, 64),  # filter size
                bias=False
            ),  # output shape (8, C, T)
            nn.BatchNorm2d(8)  # output shape (8, C, T)
        )

        # block 2 and 3 are implementations of Depthwise Convolution and Separable Convolution
        self.block_2 = nn.Sequential(
            nn.Conv2d(
                in_channels=8,  # input shape (8, C, T)
                out_channels=16,  # num_filters
                kernel_size=(22, 1),  # filter size
                groups=8,
                bias=False
            ),  # output shape (16, 1, T)
            nn.BatchNorm2d(16),  # output shape (16, 1, T)
            nn.ELU(),
            nn.AvgPool2d((1, 4)),  # output shape (16, 1, T//4)
            nn.Dropout(self.drop_out)  # output shape (16, 1, T//4)
        )

        self.block_3 = nn.Sequential(
            nn.ZeroPad2d((7, 8, 0, 0)),
            nn.Conv2d(
                in_channels=16,  # input shape (16, 1, T//4)
                out_channels=16,  # num_filters
                kernel_size=(1, 16),  # filter size
                groups=16,
                bias=False
            ),  # output shape (16, 1, T//4)
            nn.Conv2d(
                in_channels=16,  # input shape (16, 1, T//4)
                out_channels=16,  # num_filters
                kernel_size=(1, 1),  # filter size
                bias=False
            ),  # output shape (16, 1, T//4)
            nn.BatchNorm2d(16),  # output shape (16, 1, T//4)
            nn.ELU(),
            nn.AvgPool2d((1, 8)),  # output shape (16, 1, T//32)
            nn.Dropout(self.drop_out)
        )

        self.out = nn.Linear((16 * 35), classes_num)

    def forward(self, x):
        x = self.block_1(x)
        print("block1", x.shape)
        x = self.block_2(x)
        print("block2", x.shape)
        x = self.block_3(x)
        print("block3", x.shape)

        x = x.view(x.size(0), -1)
        x = self.out(x)
        return F.softmax(x, dim=1), x  # return x for visualization
if __name__ == '__main__':
    input = torch.randn(32,1,22,1125)

    model = EEGNet(4)

    out = model(input)

    print(model)