簡述

這一篇跟這個系列的其他文章不一樣，這個是重新安排下程序結構

• 結構如下：
  

其中model這個模型專門放模型就好了

• model/init.py中不用寫就好了。
• model/CNN.py中的內容
• 模型是基于之前的【Kaggle-MNIST之路】CNN結構再改進+交叉熵損失函數（六）

import torch.nn as nnclass 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 x

• 生成模型文件的文件

• Pycharm會報警說model這個庫不存在，這個很麻煩，但是也不影響使用。等沒事的時候，再研究下，如何改成不會報警的那種。目前雖然報警，但是不影響運行

• Kaggle-MNIST-classify.py

import pandas as pd import torch.utils.data as data import torch import torch.nn as nn from model.CNN import CNNfile = './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, xdatanet = 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')

• generate-kaggle-MNIST.py

import torch import torch.utils.data as data import pandas as pd import csv from model.CNN import CNNfile = './all/test.csv'class MNISTCSVDataset(data.Dataset):def __init__(self, csv_file, Train=False):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)xdata = data.as_matrix().astype('float')return xdatanet = torch.load('divided-net.pkl')myMnist = MNISTCSVDataset(file) test_loader = torch.utils.data.DataLoader(myMnist, batch_size=1, shuffle=False)values = [] for _, xd in enumerate(test_loader):xd = xd.reshape(100, 1, 28, 28).float()output = net(xd)values = values + output.argmax(dim=1).numpy().tolist()with open('./all/sample_submission.csv', 'r') as fp_in, open('newfile.csv', 'w', newline='') as fp_out:reader = csv.reader(fp_in)writer = csv.writer(fp_out)for i, row in enumerate(reader):if i == 0:writer.writerow(row)else:row[-1] = str(values[i - 1])writer.writerow(row)

這個就是這個文件的架構啦~

總結

以上是生活随笔為你收集整理的【Kaggle-MNIST之路】自定义程序结构（七）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。