Pytorch——实现简单的三层网络

"""简单的三层全连接神经网络"""
from torch import nn


# 输入维度，第一层神经元个数，第二层神经元个数，输出层神经元个数
class simpleNet(nn.Module):
    def __init__(self, in_dim, n_hidden_1, n_hidden_2, out_dim):
        super(simpleNet, self).__init__()
        self.layer1 = nn.Linear(in_dim, n_hidden_1)
        self.layer2 = nn.Linear(n_hidden_1, n_hidden_2)
        self.layer3 = nn.Linear(n_hidden_2, out_dim)

    def forward(self, x):
        x = self.layer1
        x = self.layer2
        x = self.layer3
        return(x)

# 添加激活函数——增加网络的非线性，Sequential在模型中线性叠加


class Activation_Net(nn.Module):
    def __init__(self, in_dim, n_hidden_1, n_hidden_2, out_dim):
        super(Activation_Net, self).__init__()
        self.layer1 = nn.Sequential(
            nn.Linear(in_dim, n_hidden_1), nn.ReLU(True))
        self.layer2 = nn.Sequential(
            nn.Linear(n_hidden_1, n_hidden_2), nn.ReLU(True))
        self.layer3 = nn.Sequential(nn.Linear(n_hidden_2, out_dim))

    def forward(self, x):
        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        return (x)

# 添加批标准化——提高收敛速度


class Batch_Net(nn.Module):
    """通常放到全链接层后面，激活函数前面"""

    def __init__(self, in_dim, n_hidden_1, n_hidden_2, out_dim):
        super(Batch_Net, self).__init__()
        self.layer1 = nn.Sequential(
            nn.Linear(in_dim, n_hidden_1), nn.BatchNorm1d(n_hidden_1), nn.ReLU(True))
        self.layer2 = nn.Sequential(
            nn.Linear(n_hidden_1, n_hidden_2), nn.BatchNorm1d(n_hidden_2), nn.ReLU(True))
        self.layer3 = nn.Sequential(nn.Linear(n_hidden_2, out_dim))

    def forward(self, x):
        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        return (x)