当前位置：首页 > article >正文

模型搭建与复现

article 2025/3/29 7:59:44

模型搭建与复现

神经网络的模版
神经网络中各种常见的结构
组建可复用的网络模块

神经网络模版

需要有以下元素组成

class Model(nn.Module):
    def __init__(self):
        super().__init__(self)
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forwart(self, x):
        x = F.relu((self.conv1(x)))
        return F.relu(self.conv2(x))

模型搭建

import torch
import torch.nn as nn

m = nn.Linear(2, 3)
input = torch.randn(5, 2)
print(input)
output = m(input)
print(output)
print(output.size())

图片仅供学习用，如有侵权请联系我删除

激活函数

Sigmoid

ReLU

Softmax

随机失活Dropout

综合案例

复现LeNet-5

import torch.nn.functional as F


class Model(nn.Module):
    def __init__(self):
        super().__init__(self)
        self.conv1 = nn.Conv2d(1, 6, kernel_size=5)
        self.pool1 = nn.AvgPool2d(kernel_size=2, stride=2)
        self.conv2 = nn.Conv2d(6, 16, kernel_size=5)
        self.pool2 = nn.AvgPool2d(kernel_size=2, stride=2)
        self.conv3 = nn.Conv2d(16, 120, kernel_size=5)
        self.linear1 = nn.Linear(120, 84)
        self.linear2 = nn.Linear(84, 10)

    def forward(self, x):
        x = self.conv1(x)
        x = F.tanh(x)
        x = self.pool1(x)
        x = self.conv2(x)
        x = F.tanh(x)
        x = self.pool2(x)
        x = self.conv3(x)
        x = F.tanh(x)
        x = x.view(x.size(0), -1)  # 将batch展平
        # 接下来全连接
        x = self.linear1(x)
        x = F.tanh(x)
        x = self.linear2(x)
        return x

查看全文

http://www.kler.cn/a/599358.html