用pytorch生成一个5层一维卷积神经网络，要求第一层卷积层输入特征数为41，卷积核为3

x3，其余四层卷积层的输入特征都为64，卷积核大小分别为5x5、3x3、3x3和1x1。其中除了最后一层卷积层外，其余各层都有Batch Normalization和ReLU激活函数。

import torch.nn as nn

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv1d(41, 64, kernel_size=3, stride=1, padding=1) # 第一层卷积层
        self.bn1 = nn.BatchNorm1d(64) # Batch Normalization
        self.conv2 = nn.Conv1d(64, 64, kernel_size=5, stride=1, padding=2) # 第二层卷积层
        self.bn2 = nn.BatchNorm1d(64) # Batch Normalization
        self.conv3 = nn.Conv1d(64, 64, kernel_size=3, stride=1, padding=1) # 第三层卷积层
        self.bn3 = nn.BatchNorm1d(64) # Batch Normalization
        self.conv4 = nn.Conv1d(64, 64, kernel_size=3, stride=1, padding=1) # 第四层卷积层
        self.bn4 = nn.BatchNorm1d(64) # Batch Normalization
        self.conv5 = nn.Conv1d(64, 1, kernel_size=1, stride=1, padding=0) # 最后一层卷积层

    def forward(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = nn.ReLU()(x) # ReLU激活函数
        x = self.conv2(x)
        x = self.bn2(x)
        x = nn.ReLU()(x) # ReLU激活函数
        x = self.conv3(x)
        x = self.bn3(x)
        x = nn.ReLU()(x) # ReLU激活函数
        x = self.conv4(x)
        x = self.bn4(x)
        x = nn.ReLU()(x) # ReLU激活函数
        x = self.conv5(x)
        return x