簡述

• 基于之前的框架
• 【Kaggle-MNIST之路】自定義程序結構（七）
• 得分：0.9914
• 排名：900+

代碼

• CNN.py 文件內容

import torch.nn as nn import torchclass CNN(nn.Module):def __init__(self):super(CNN, self).__init__()self.N = 1self.layer1 = nn.Sequential(# (1, 28, 28)nn.Conv2d(in_channels=1,out_channels=32,kernel_size=3, # 卷積filter, 移動塊長stride=1, # filter的每次移動步長),nn.ReLU(),nn.BatchNorm2d(32),nn.Conv2d(in_channels=32,out_channels=32,kernel_size=3, # 卷積filter, 移動塊長stride=1, # filter的每次移動步長),nn.ReLU(),nn.BatchNorm2d(32),nn.Conv2d(in_channels=32,out_channels=32,kernel_size=5, # 卷積filter, 移動塊長stride=2, # filter的每次移動步長padding=2,),nn.ReLU(),nn.BatchNorm2d(32),nn.Dropout(0.4),)self.layer2 = nn.Sequential(nn.Conv2d(in_channels=32,out_channels=64,kernel_size=3, # 卷積filter, 移動塊長stride=1, # filter的每次移動步長),nn.ReLU(),nn.BatchNorm2d(64),nn.Conv2d(in_channels=64,out_channels=64,kernel_size=3, # 卷積filter, 移動塊長stride=1, # filter的每次移動步長),nn.ReLU(),nn.BatchNorm2d(64),nn.Conv2d(in_channels=64,out_channels=64,kernel_size=5, # 卷積filter, 移動塊長stride=2, # filter的每次移動步長padding=2,),nn.ReLU(),nn.BatchNorm2d(64),nn.Dropout(0.4),)self.layer3 = nn.Sequential(nn.Conv2d(in_channels=64,out_channels=128,kernel_size=4, # 卷積filter, 移動塊長stride=1, # filter的每次移動步長),nn.ReLU(),nn.BatchNorm2d(128),)self.layer4 = nn.Linear(128 * self.N, 10)def forward(self, x):con = torch.Tensor()for i in range(self.N):temp = x.clone()temp = self.layer1(temp)temp = self.layer2(temp)temp = self.layer3(temp)con = torch.cat((con, temp), dim=1) # 在dim=1上concatcon = con.view(con.size(0), -1)con = self.layer4(con)return con

總結

以上是生活随笔為你收集整理的【Kaggle-MNIST之路】CNN再添加一个层卷积（八）的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。