全国高校计算机能力挑战赛--人工智能应用赛样题解析（三）深度学习算法应用

任务一：图片分类模型训练

数据中给出了手写数字识别 mnist 数据集的 0，1 和 2 的全部数据，包括训练和测试。现要求利用卷积神经网络或全连接网络在训练集进行训练，并输出测试集的准确率。需提交所有代码及运行截图。

考察数据集的制作，划分，简单神经网络的构建等知识
个人而言比较关注是数据集同标签的关联方法，ImageFolder可以在分类任务中达成此目的详细的解析可以查看：
链接: 此博客.

from torchvision.datasets import ImageFolder
import torch.utils.data as Data
import torch
import torch.nn as nn
import torchvision.transforms as transforms
from torch.autograd import Variable
import torch.nn.functional as F

num_epochs = 20
batch_size = 512
learning_rate = 0.001


# 将数据处理成Variable, 如果有GPU, 可以转成cuda形式
def get_variable(x):
    x = Variable(x)
    return x.cuda() if torch.cuda.is_available() else x


data_transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5])
])

train_set = ImageFolder("./task1/train", transform=data_transform)
test_set = ImageFolder("./task1/test", transform=data_transform)

train_loader = Data.DataLoader(dataset=train_set, batch_size=batch_size, shuffle=True)
test_loader = Data.DataLoader(dataset=test_set, batch_size=batch_size, shuffle=True)

# 定义模型
class CNN(nn.Module):
    def __init__(self):
        super().__init__()
        # 1*1*28*28
        self.conv1 = nn.Conv2d(3, 10, 5)
        self.conv2 = nn.Conv2d(10, 20, 3)
        self.fc1 = nn.Linear(20 * 10 * 10, 500)
        self.fc2 = nn.Linear(500, 10)

    def forward(self, x):
        in_size = x.size(0)
        out = self.conv1(x)  # 1* 10 * 24 *24
        out = F.relu(out)
        out = F.max_pool2d(out, 2, 2)  # 1* 10 * 12 * 12
        out = self.conv2(out)  # 1* 20 * 10 * 10
        out = F.