簡述

• 這里再添加了一個卷積層。用一個kernal=4的卷積層做一個卷積之后，再做映射。
• 基于之前的一個版本
• 【Kaggle-MNIST之路】CNN結構改進+改進過的損失函數（五）
• 成績：0.9898
• 排名：1000+

代碼

• 注意，下一個版本會重新安排架構。
• 這是本次架構的最后一個版本了。

import pandas as pd import torch.utils.data as data import torch import torch.nn as nnfile = './all/train.csv' LR = 0.01class MNISTCSVDataset(data.Dataset):def __init__(self, csv_file, Train=True):self.dataframe = pd.read_csv(csv_file, iterator=True)self.Train = Traindef __len__(self):if self.Train:return 42000else:return 28000def __getitem__(self, idx):data = self.dataframe.get_chunk(100)ylabel = data['label'].as_matrix().astype('float')xdata = data.ix[:, 1:].as_matrix().astype('float')return ylabel, xdataclass CNN(nn.Module):def __init__(self):super(CNN, self).__init__()self.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, 10)def forward(self, x):# print(x.shape)x = self.layer1(x)# print(x.shape)x = self.layer2(x)x = self.layer3(x)x = x.view(x.size(0), -1)x = self.layer4(x)return xnet = CNN() loss_function = nn.CrossEntropyLoss() optimizer = torch.optim.Adam(net.parameters(), lr=LR) EPOCH = 10 for epoch in range(EPOCH):mydataset = MNISTCSVDataset(file)train_loader = torch.utils.data.DataLoader(mydataset, batch_size=1, shuffle=True)print('epoch %d' % epoch)for step, (yl, xd) in enumerate(train_loader):xd = xd.reshape(100, 1, 28, 28).float()output = net(xd)yl = yl.long()loss = loss_function(output, yl.squeeze())optimizer.zero_grad()loss.backward()optimizer.step()if step % 40 == 0:print('step %d' % step, loss)torch.save(net, 'divided-net.pkl')

總結

以上是生活随笔為你收集整理的【Kaggle-MNIST之路】CNN结构再改进+交叉熵损失函数（六）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。