NNDL实验LeNet

5.3基于LeNet实现手写数字识别

5.3.1观察数据集，可视化其中一张图片，并做预处理

import json
import gzip

# 打印并观察数据集分布情况
train_set, dev_set, test_set = json.load(gzip.open('./mnist.json.gz'))

train_images, train_labels = train_set[0][:1000], train_set[1][:1000]
dev_images, dev_labels = dev_set[0][:200], dev_set[1][:200]
test_images, test_labels = test_set[0][:200], test_set[1][:200]
train_set, dev_set, test_set = [train_images, train_labels], [dev_images, dev_labels], [test_images, test_labels]
print('Length of train/dev/test set:{}/{}/{}'.format(len(train_set[0]), len(dev_set[0]), len(test_set[0])))

import matplotlib.pyplot as plt
from PIL import Image
import numpy as np

image, label = train_set[0][8], train_set[1][8]
image, label = np.array(image).astype('float32'), int(label)
# 原始图像数据为长度784的行向量，需要调整为[28,28]大小的图像
image = np.reshape(image, [28, 28])
image = Image.fromarray(image.astype('uint8'), mode='L')
print("The number in the picture is {}".format(label))
plt.figure(figsize=(5, 5))
plt.imshow(image)
plt.show()
plt.savefig('conv-number5.pdf')

import torchvision.transforms as transforms

# 数据预处理
transforms = transforms.Compose(
    [transforms.Resize(32), transforms.ToTensor(), transforms.Normalize(mean=[0.5], std=[0.5])])

from torch.utils.data import Dataset


class MNIST_dataset(Dataset):
    def __init__(self, dataset, transforms, mode='train'):
        self.mode = mode
        self.transforms = transforms
        self.dataset = dataset

    def __getitem__(self, idx):
        # 获取图像和标签
        image, label = self.dataset[0][idx], self.dataset[1][idx]
        image, label = np.array(image).astype('float32'), int(label)
        image = np.reshape(image, [28, 28])
        image = Image.fromarray(np.unit8(image), mode='L')
        image = self.transforms(image)

        return image, label

    def __len__(self):
        return len(self.dataset[0])


# 加载 mnist 数据集
train_dataset = MNIST_dataset(dataset=train_set, transforms=transforms, mode='train')
test_dataset = MNIST_dataset(dataset=test_set, transforms=transforms, mode='test')
dev_dataset = MNIST_dataset(dataset=dev_set, transforms=transforms, mode='dev')

Length of train/dev/test set:1000/200/200
The number in the picture is 1

5.3.2模型构建

import torch.nn.functional as F
import torch.nn as nn
import torch


class Model_LeNet(nn.Module):
    def __init__(self, in_channels, num_classes=10):
        super(Model_LeNet, self).__init__()
        # 卷积层：输出通道数为6，卷积核大小为5×5
        self.conv1 = nn.Conv2d(in_channels=in_channels, out_channels=6, kernel_size=5)
        # 汇聚层：汇聚窗口为2×2，步长为2
        self.pool2 = nn.MaxPool2d(kernel_size=(2, 2), stride=2)
        # 卷积层：输入通道数为6，输出通道数为16，卷积核大小为5×5，步长为1
        self.conv3 = nn.Conv2d(in_channels=6, out_channels=16, kernel_size=5, stride=1)
        # 汇聚层：汇聚窗口为2×2，步长为2
        self.pool4 = nn.AvgPool2d(kernel_size=(2, 2), stride=2)
        # 卷积层：输入通道数为16，输出通道数为120，卷积核大小为5×5
        self.conv5 = nn.Conv2d(in_channels=16, out_channels=120, kernel_size=5, stride=1)
        # 全连接层：输入神经元为120，输出神经元为84
        self.linear6 = nn.Linear(120, 84)
        # 全连接层：输入神经元为84，输出神经元为类别数
        self.linear7 = nn.Linear(84, num_classes)

    def forward(self, x):
        # C1：卷积层+激活函数

        output = F.relu(self.conv1(x))
        # S2：汇聚层
        output = self.pool2(output)
        # C3：卷积层+激活函数
        output = F.relu(self.conv3(output))
        # S4：汇聚层
        output = self.pool4(output)
        # C5：卷积层+激活函数
        output = F.relu(self.conv5(output))
        # 输入层将数据拉平[B,C,H,W] -> [B,CxHxW]
        output = torch.squeeze(output, dim=3)
        output = torch.squeeze(output, dim=2)
        # F6：全连接层
        output = F.relu(self.linear6(output))
        # F7：全连接层
        output = self.linear7(output)
        return output

# 这里用np.random创建一个随机数组作为输入数据
inputs = np.random.randn(*[1, 1, 32, 32])
inputs = inputs.astype('float32')
# 创建Model_LeNet类的实例，指定模型名称和分类的类别数目
model = Model_LeNet(in_channels=1, num_classes=10)
print(model)
# 通过调用LeNet从基类继承的sublayers()函数，查看LeNet中所包含的子层
print(model.named_parameters())
x = torch.tensor(inputs)
print(x)
for item in model.children():
    # item是LeNet类中的一个子层
    # 查看经过子层之后的输出数据形状
    item_shapex = 0
    names = []
    parameter = []
    for name in item.named_parameters():
        names.append(name[0])
        parameter.append(name[1])
        item_shapex += 1
    try:
        x = item(x)
    except:
        # 如果是最后一个卷积层输出，需要展平后才可以送入全连接层
        x = x.reshape([x.shape[0], -1])
        x = item(x)

    if item_shapex == 2:
        # 查看卷积和全连接层的数据和参数的形状，
        # 其中item.parameters()[0]是权重参数w，item.parameters()[1]是偏置参数b
        print(item, x.shape, parameter[0].shape, parameter[1].shape)
    else:
        # 汇聚层没有参数
        print(item, x.shape)

构造一个形状为 [1,1,32,32]的输入数据送入网络，观察每一层特征图的形状变化

Model_LeNet(
  (conv1): Conv2d(1, 6, kernel_size=(5, 5), stride=(1, 1))
  (pool2): MaxPool2d(kernel_size=(2, 2), stride=2, padding=0, dilation=1, ceil_mode=False)
  (conv3): Conv2d(6, 16, kernel_size=(5, 5), stride=(1, 1))
  (pool4): AvgPool2d(kernel_size=(2, 2), stride=2, padding=0)
  (conv5): Conv2d(16, 120, kernel_size=(5, 5), stride=(1, 1))
  (linear6): Linear(in_features=120, out_features=84, bias=True)
  (linear7): Linear(in_features=84, out_features=10, bias=True)
)

tensor([[[[ 1.5020, -0.6053, -0.1772,  ...,  2.5852, -0.1453, -0.5586],
          [ 0.4105, -0.2150,  1.8041,  ...,  2.1141, -0.4782, -0.2639],
          [ 0.4393,  0.5896,  0.2926,  ..., -0.4829,  0.1956,  0.5326],
          ...,
          [ 1.5113,  0.8501, -1.3457,  ...,  1.5488,  1.2071,  0.8967],
          [-0.6923, -1.2530, -1.2830,  ...,  1.0565, -0.8051, -0.4870],
          [-1.2445,  0.9623,  0.8793,  ...,  0.8626, -0.1742, -0.5756]]]])
Conv2d(1, 6, kernel_size=(5, 5), stride=(1, 1)) torch.Size([1, 6, 28, 28]) torch.Size([6, 1, 5, 5]) torch.Size([6])
MaxPool2d(kernel_size=(2, 2), stride=2, padding=0, dilation=1, ceil_mode=False) torch.Size([1, 6, 14, 14])
Conv2d(6, 16, kernel_size=(5, 5), stride=(1, 1)) torch.Size([1, 16, 10, 10]) torch.Size([16, 6, 5, 5]) torch.Size([16])
AvgPool2d(kernel_size=(2, 2), stride=2, padding=0) torch.Size([1, 16, 5, 5])
Conv2d(16, 120, kernel_size=(5, 5), stride=(1, 1)) torch.Size([1, 120, 1, 1]) torch.Size([120, 16, 5, 5]) torch.Size([120])
Linear(in_features=120, out_features=84, bias=True) torch.Size([1, 84]) torch.Size([84, 120]) torch.Size([84])
Linear(in_features=84, out_features=10, bias=True) torch.Size([1, 10]) torch.Size([10, 84]) torch.Size([10])

测试两个模型的时间：

import time

# 这里用np.random创建一个随机数组作为测试数据
inputs = np.random.randn(*[1, 1, 32, 32])
inputs = inputs.astype('float32')
x = torch.tensor(inputs)

# 创建Model_LeNet类的实例，指定模型名称和分类的类别数目
model = Model_LeNet(in_channels=1, num_classes=10)
# 创建Torch_LeNet类的实例，指定模型名称和分类的类别数目
torch_model = Torch_LeNet(in_channels=1, num_classes=10)

# 计算Model_LeNet类的运算速度
model_time = 0
for i in range(60):
    strat_time = time.time()
    out = model(x)
    end_time = time.time()
    # 预热10次运算，不计入最终速度统计
    if i < 10:
        continue
    model_time += (end_time - strat_time)
avg_model_time = model_time / 50
print('Model_LeNet speed:', avg_model_time, 's')
# 计算Torch_LeNet类的运算速度
torch_model_time = 0
for i in range(60):
    strat_time = time.time()
    torch_out = torch_model(x)
    end_time = time.time()
    # 预热10次运算，不计入最终速度统计
    if i < 10:
        continue
    torch_model_time += (end_time - strat_time)
avg_torch_model_time = torch_model_time / 50

print('Torch_LeNet speed:', avg_torch_model_time, 's')

Model_LeNet speed: 0.0008177709579467773 s
Torch_LeNet speed: 0.0008776140213012695 s

5.3.5模型训练

class RunnerV3(object):
    def __init__(self, model, optimizer, loss_fn, metric, **kwargs):
        self.model = model
        self.optimizer = optimizer
        self.loss_fn = loss_fn
        self.metric = metric  # 只用于计算评价指标
 
        # 记录训练过程中的评价指标变化情况
        self.dev_scores = []
 
        # 记录训练过程中的损失函数变化情况
        self.train_epoch_losses = []  # 一个epoch记录一次loss
        self.train_step_losses = []  # 一个step记录一次loss
        self.dev_losses = []
 
        # 记录全局最优指标
        self.best_score = 0
 
    def train(self, train_loader, dev_loader=None, **kwargs):
        # 将模型切换为训练模式
        self.model.train()
 
        # 传入训练轮数，如果没有传入值则默认为0
        num_epochs = kwargs.get("num_epochs", 0)
        # 传入log打印频率，如果没有传入值则默认为100
        log_steps = kwargs.get("log_steps", 100)
        # 评价频率
        eval_steps = kwargs.get("eval_steps", 0)
 
        # 传入模型保存路径，如果没有传入值则默认为"best_model.pdparams"
        save_path = kwargs.get("save_path", "best_model.pdparams")
 
        custom_print_log = kwargs.get("custom_print_log", None)
 
        # 训练总的步数
        num_training_steps = num_epochs * len(train_loader)
 
        if eval_steps:
            if self.metric is None:
                raise RuntimeError('Error: Metric can not be None!')
            if dev_loader is None:
                raise RuntimeError('Error: dev_loader can not be None!')
 
        # 运行的step数目
        global_step = 0
 
        # 进行num_epochs轮训练
        for epoch in range(num_epochs):
            # 用于统计训练集的损失
            total_loss = 0
            for step, data in enumerate(train_loader):
                X, y = data
                # 获取模型预测
                logits = self.model(X)
                loss = self.loss_fn(logits, y)  # 默认求mean
                total_loss += loss
 
                # 训练过程中，每个step的loss进行保存
                self.train_step_losses.append((global_step, loss.item()))
 
                if log_steps and global_step % log_steps == 0:
                    print(
                        f"[Train] epoch: {epoch}/{num_epochs}, step: {global_step}/{num_training_steps}, loss: {loss.item():.5f}")
 
                # 梯度反向传播，计算每个参数的梯度值
                loss.backward()
 
                if custom_print_log:
                    custom_print_log(self)
 
                # 小批量梯度下降进行参数更新
                self.optimizer.step()
                # 梯度归零
                optimizer.zero_grad()
 
                # 判断是否需要评价
                if eval_steps > 0 and global_step > 0 and \
                        (global_step % eval_steps == 0 or global_step == (num_training_steps - 1)):
 
                    dev_score, dev_loss = self.evaluate(dev_loader, global_step=global_step)
                    print(f"[Evaluate]  dev score: {dev_score:.5f}, dev loss: {dev_loss:.5f}")
 
                    # 将模型切换为训练模式
                    self.model.train()
 
                    # 如果当前指标为最优指标，保存该模型
                    if dev_score > self.best_score:
                        self.save_model(save_path)
                        print(
                            f"[Evaluate] best accuracy performence has been updated: {self.best_score:.5f} --> {dev_score:.5f}")
                        self.best_score = dev_score
 
                global_step += 1
 
            # 当前epoch 训练loss累计值
            trn_loss = (total_loss / len(train_loader)).item()
            # epoch粒度的训练loss保存
            self.train_epoch_losses.append(trn_loss)
 
        print("[Train] Training done!")
 
    # 模型评估阶段，使用'paddle.no_grad()'控制不计算和存储梯度
    @torch.no_grad()
    def evaluate(self, dev_loader, **kwargs):
        assert self.metric is not None
 
        # 将模型设置为评估模式
        self.model.eval()
 
        global_step = kwargs.get("global_step", -1)
 
        # 用于统计训练集的损失
        total_loss = 0
 
        # 重置评价
        self.metric.reset()
 
        # 遍历验证集每个批次
        for batch_id, data in enumerate(dev_loader):
            X, y = data
 
            # 计算模型输出
            logits = self.model(X)
 
            # 计算损失函数
            loss = self.loss_fn(logits, y).item()
            # 累积损失
            total_loss += loss
 
            # 累积评价
            self.metric.update(logits, y)
 
        dev_loss = (total_loss / len(dev_loader))
        dev_score = self.metric.accumulate()
 
        # 记录验证集loss
        if global_step != -1:
            self.dev_losses.append((global_step, dev_loss))
            self.dev_scores.append(dev_score)
 
        return dev_score, dev_loss
 
    # 模型评估阶段，使用'paddle.no_grad()'控制不计算和存储梯度
    @torch.no_grad()
    def predict(self, x, **kwargs):
        # 将模型设置为评估模式
        self.model.eval()
        # 运行模型前向计算，得到预测值
        logits = self.model(x)
        return logits
 
    def save_model(self, save_path):
        torch.save(self.model.state_dict(), save_path)
 
    def load_model(self, model_path):
        state_dict = torch.load(model_path)
        self.model.load_state_dict(state_dict)
import torch
#新增准确率计算函数
def accuracy(preds, labels):
    """
    输入：
        - preds：预测值，二分类时，shape=[N, 1]，N为样本数量，多分类时，shape=[N, C]，C为类别数量
        - labels：真实标签，shape=[N, 1]
    输出：
        - 准确率：shape=[1]
    """
    print(preds)
    # 判断是二分类任务还是多分类任务，preds.shape[1]=1时为二分类任务，preds.shape[1]>1时为多分类任务
    if preds.shape[1] == 1:
        # 二分类时，判断每个概率值是否大于0.5，当大于0.5时，类别为1，否则类别为0
        # 使用'torch.can_cast'将preds的数据类型转换为float32类型
        preds = torch.can_cast((preds>=0.5).dtype,to=torch.float32)
    else:
        # 多分类时，使用'torch.argmax'计算最大元素索引作为类别
        preds = torch.argmax(preds,dim=1)
        torch.can_cast(preds.dtype,torch.int32)
    return torch.mean(torch.tensor((preds == labels), dtype=torch.float32))
 
 
class Accuracy():
    def __init__(self):
        """
        输入：
           - is_logist: outputs是logist还是激活后的值
        """
 
        # 用于统计正确的样本个数
        self.num_correct = 0
        # 用于统计样本的总数
        self.num_count = 0
 
        self.is_logist = True
 
    def update(self, outputs, labels):
        """
        输入：
           - outputs: 预测值, shape=[N,class_num]
           - labels: 标签值, shape=[N,1]
        """
 
        # 判断是二分类任务还是多分类任务，shape[1]=1时为二分类任务，shape[1]>1时为多分类任务
        if outputs.shape[1] == 1: # 二分类
            outputs = torch.squeeze(outputs, axis=-1)
            if self.is_logist:
                # logist判断是否大于0
                preds = torch.can_cast((outputs>=0), dtype=torch.float32)
            else:
                # 如果不是logist，判断每个概率值是否大于0.5，当大于0.5时，类别为1，否则类别为0
                preds = torch.can_cast((outputs>=0.5), dtype=torch.float32)
        else:
            # 多分类时，使用'paddle.argmax'计算最大元素索引作为类别
            preds = torch.argmax(outputs, dim=1).int()
 
        # 获取本批数据中预测正确的样本个数
        labels = torch.squeeze(labels, dim=-1)
        batch_correct = torch.sum((preds == labels).clone().detach()).numpy()
        batch_count = len(labels)
 
        # 更新num_correct 和 num_count
        self.num_correct += batch_correct
        self.num_count += batch_count
 
    def accumulate(self):
        # 使用累计的数据，计算总的指标
        if self.num_count == 0:
            return 0
        return self.num_correct / self.num_count
 
    def reset(self):
        # 重置正确的数目和总数
        self.num_correct = 0
        self.num_count = 0
 
    def name(self):
        return "Accuracy"
 
 
import torch.optim as opti
from torch.utils.data import DataLoader
torch.manual_seed(100)
# 学习率大小
lr = 0.1
# 批次大小
batch_size = 64
# 加载数据
train_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
dev_loader = DataLoader(dev_dataset, batch_size=batch_size)
test_loader = DataLoader(test_dataset, batch_size=batch_size)
model = Model_LeNet(in_channels=1, num_classes=10)
optimizer = opti.SGD(model.parameters(), 0.2)
# 定义损失函数
loss_fn = F.cross_entropy
# 定义评价指标
metric = Accuracy()
# 实例化 RunnerV3 类，并传入训练配置。
runner = RunnerV3(model, optimizer, loss_fn, metric)
# 启动训练
log_steps = 15
eval_steps = 15
runner.train(train_loader, dev_loader, num_epochs=6, log_steps=log_steps,
             eval_steps=eval_steps, save_path="best_model.pdparams")

[Train] epoch: 0/6, step: 0/96, loss: 2.31081
[Train] epoch: 0/6, step: 15/96, loss: 2.29632
[Evaluate]  dev score: 0.11000, dev loss: 2.29774
[Evaluate] best accuracy performence has been updated: 0.00000 --> 0.11000
[Train] epoch: 1/6, step: 30/96, loss: 2.22703
[Evaluate]  dev score: 0.20000, dev loss: 2.24587
[Evaluate] best accuracy performence has been updated: 0.11000 --> 0.20000
[Train] epoch: 2/6, step: 45/96, loss: 2.21103
[Evaluate]  dev score: 0.25500, dev loss: 2.16948
[Evaluate] best accuracy performence has been updated: 0.20000 --> 0.25500
[Train] epoch: 3/6, step: 60/96, loss: 2.13194
[Evaluate]  dev score: 0.45000, dev loss: 1.97490
[Evaluate] best accuracy performence has been updated: 0.25500 --> 0.45000
[Train] epoch: 4/6, step: 75/96, loss: 0.97917
[Evaluate]  dev score: 0.62000, dev loss: 1.10211
[Evaluate] best accuracy performence has been updated: 0.45000 --> 0.62000
[Train] epoch: 5/6, step: 90/96, loss: 0.74466
[Evaluate]  dev score: 0.70500, dev loss: 0.81270
[Evaluate] best accuracy performence has been updated: 0.62000 --> 0.70500
[Evaluate]  dev score: 0.68000, dev loss: 0.87858
[Train] Training done!

画出训练集和测试集的变化情况：

# 可视化误差
def plot(runner, fig_name):
    plt.figure(figsize=(10, 5))
 
    plt.subplot(1, 2, 1)
    train_items = runner.train_step_losses[::30]
    train_steps = [x[0] for x in train_items]
    train_losses = [x[1] for x in train_items]
 
    plt.plot(train_steps, train_losses, color='#8E004D', label="Train loss")
    if runner.dev_losses[0][0] != -1:
        dev_steps = [x[0] for x in runner.dev_losses]
        dev_losses = [x[1] for x in runner.dev_losses]
        plt.plot(dev_steps, dev_losses, color='#E20079', linestyle='--', label="Dev loss")
    # 绘制坐标轴和图例
    plt.ylabel("loss", fontsize='x-large')
    plt.xlabel("step", fontsize='x-large')
    plt.legend(loc='upper right', fontsize='x-large')
 
    plt.subplot(1, 2, 2)
    # 绘制评价准确率变化曲线
    if runner.dev_losses[0][0] != -1:
        plt.plot(dev_steps, runner.dev_scores,
                 color='#E20079', linestyle="--", label="Dev accuracy")
    else:
        plt.plot(list(range(len(runner.dev_scores))), runner.dev_scores,
                 color='#E20079', linestyle="--", label="Dev accuracy")
    # 绘制坐标轴和图例
    plt.ylabel("score", fontsize='x-large')
    plt.xlabel("step", fontsize='x-large')
    plt.legend(loc='lower right', fontsize='x-large')
 
    plt.savefig(fig_name)
    plt.show()
 
 
runner.load_model('best_model.pdparams')
plot(runner, 'cnn-loss1.pdf')

5.3.4模型评价

# 加载最优模型
runner.load_model('best_model.pdparams')
# 模型评价
score, loss = runner.evaluate(test_loader)
print("[Test] accuracy/loss: {:.4f}/{:.4f}".format(score, loss))

结果

[Test] accuracy/loss: 0.7450/0.6820

5.3.5模型预测

# 获取测试集中第一条数
X, label = next(iter(test_loader))
logits = runner.predict(X)
# 多分类，使用softmax计算预测概率
pred = F.softmax(logits,dim=1)
print(pred.shape)
# 获取概率最大的类别
pred_class = torch.argmax(pred[2]).numpy()
print(pred_class)
label = label[2].numpy()
# 输出真实类别与预测类别
print("The true category is {} and the predicted category is {}".format(label, pred_class))
# 可视化图片
plt.figure(figsize=(2, 2))
image, label = test_set[0][10], test_set[1][10]
image= np.array(image).astype('float32')
image = np.reshape(image, [28, 28])
image = Image.fromarray(image.astype('uint8'), mode='L')
plt.imshow(image)
plt.savefig('cnn-number1.pdf')

torch.Size([64, 10])
1

选做

前馈神经网络合LnNet对比：

import torch
import torch.nn as nn
from matplotlib import pyplot as plt
from torch.utils.data import DataLoader
from torchvision import transforms
from torchvision import datasets
 
batch_size = 64
lr = 0.01
momentum = 0.5
epoch = 5
 
# 归一化
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))])
# train=True训练集，=False测试集
train_dataset = datasets.MNIST(root='./pythonProject/mnist', train=True, transform=transform, download=True)
test_dataset = datasets.MNIST(root='./pythonProject/mnist', train=False, transform=transform, download=True)
train_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
test_loader = DataLoader(test_dataset, batch_size=batch_size, shuffle=False)
 
fig = plt.figure()
for i in range(12):
    plt.subplot(3, 4, i + 1)
    plt.tight_layout()
    plt.imshow(train_dataset.train_data[i], cmap='gray', interpolation='none')
    plt.title("Labels: {}".format(train_dataset.train_labels[i]))
    plt.xticks([])
    plt.yticks([])
plt.show()
 
 
# 定义前馈神经网络
class Model_MLP_L2_V3(nn.Module):
    def __init__(self):
        super(Model_MLP_L2_V3, self).__init__()
        self.conv1 = torch.nn.Sequential(torch.nn.Conv2d(1, 10, kernel_size=(5, 5)), torch.nn.ReLU(),
                                         torch.nn.MaxPool2d(kernel_size=2))
        self.conv2 = torch.nn.Sequential(torch.nn.Conv2d(10, 20, kernel_size=(5, 5)), torch.nn.ReLU(),
                                         torch.nn.MaxPool2d(kernel_size=2))
        self.fc = torch.nn.Sequential(torch.nn.Linear(320, 50), torch.nn.Linear(50, 10))
 
    def forward(self, x):
        batch_size = x.size(0)
        x = self.conv1(x)  # 一层卷积层,一层池化层,一层激活层
        x = self.conv2(x)
        x = x.view(batch_size, -1)  # flatten变成全连接网络需要的输入(batch, 20,4,4)==>(batch,320),-1此处自动算出的是320
        x = self.fc(x)
        return x
 
 
model = Model_MLP_L2_V3()
 
# 设置损失函数和优化器
criterion = torch.nn.CrossEntropyLoss()  # 交叉熵损失
optimizer = torch.optim.SGD(model.parameters(), lr=lr, momentum=momentum)
 
 
def train(epoch):
    running_loss = 0.0  # 这整个epoch的loss清零
    running_total = 0
    running_correct = 0
    for batch_idx, data in enumerate(train_loader, 0):
        inputs, target = data
        optimizer.zero_grad()
 
        # forward + backward + update
        outputs = model(inputs)
        loss = criterion(outputs, target)
 
        loss.backward()
        optimizer.step()
 
        # 把运行中的loss累加起来，为了下面300次一除
        running_loss += loss.item()
        # 把运行中的准确率acc算出来
        _, predicted = torch.max(outputs.data, dim=1)
        running_total += inputs.shape[0]
        running_correct += (predicted == target).sum().item()
 
        if batch_idx % 100 == 99:
            print('[%d, %5d]: loss: %.3f , acc: %.2f %%' % (
            epoch + 1, batch_idx + 1, running_loss / 300, 100 * running_correct / running_total))
            running_loss = 0.0  # 该批次loss清零
            running_total = 0
            running_correct = 0  # 该批次acc清零
 
 
def test():
    correct = 0
    total = 0
    with torch.no_grad():
        for data in test_loader:
            images, labels = data
            outputs = model(images)
            _, predicted = torch.max(outputs.data, dim=1)  # dim=1 列是第0个维度，行是第1个维度，沿着行(第1个维度)去找1.最大值和2.最大值的下标
            total += labels.size(0)  # 张量之间的比较运算
            correct += (predicted == labels).sum().item()
    accuracy = correct / total  # 测试准确率=正确数/总数
    print('[%d]: Accuracy on test set: %.1f %% ' % (epoch + 1, 100 * accuracy))
    return accuracy
 
 
# 主函数
if __name__ == '__main__':
    acc_list_test = []
    for epoch in range(epoch):
        train(epoch)
        acc_test = test()
        acc_list_test.append(acc_test)
 
    plt.plot(acc_list_test)
    plt.xlabel('Epoch')
    plt.ylabel('Accuracy')
    plt.show()

[1,   100]: loss: 0.588 , acc: 48.97 %
[1,   200]: loss: 0.178 , acc: 84.39 %
[1,   300]: loss: 0.115 , acc: 89.59 %
[1,   400]: loss: 0.094 , acc: 91.58 %
[1,   500]: loss: 0.071 , acc: 93.58 %
[1,   600]: loss: 0.059 , acc: 94.56 %
[1,   700]: loss: 0.055 , acc: 95.03 %
[1,   800]: loss: 0.050 , acc: 95.44 %
[1,   900]: loss: 0.048 , acc: 95.80 %
[1]: Accuracy on test set: 96.2 % 
[2,   100]: loss: 0.036 , acc: 96.83 %
[2,   200]: loss: 0.040 , acc: 96.16 %
[2,   300]: loss: 0.033 , acc: 96.95 %
[2,   400]: loss: 0.035 , acc: 96.92 %
[2,   500]: loss: 0.031 , acc: 97.47 %
[2,   600]: loss: 0.031 , acc: 97.41 %
[2,   700]: loss: 0.028 , acc: 97.47 %
[2,   800]: loss: 0.029 , acc: 97.52 %
[2,   900]: loss: 0.028 , acc: 97.41 %
[2]: Accuracy on test set: 98.0 % 
[3,   100]: loss: 0.021 , acc: 98.08 %
[3,   200]: loss: 0.024 , acc: 97.89 %
[3,   300]: loss: 0.025 , acc: 97.67 %
[3,   400]: loss: 0.024 , acc: 97.70 %
[3,   500]: loss: 0.027 , acc: 97.44 %
[3,   600]: loss: 0.025 , acc: 97.72 %
[3,   700]: loss: 0.026 , acc: 97.55 %
[3,   800]: loss: 0.025 , acc: 97.86 %
[3,   900]: loss: 0.021 , acc: 98.19 %
[3]: Accuracy on test set: 97.8 % 
[4,   100]: loss: 0.020 , acc: 98.23 %
[4,   200]: loss: 0.020 , acc: 98.23 %
[4,   300]: loss: 0.019 , acc: 98.11 %
[4,   400]: loss: 0.021 , acc: 98.14 %
[4,   500]: loss: 0.020 , acc: 98.12 %
[4,   600]: loss: 0.023 , acc: 97.83 %
[4,   700]: loss: 0.021 , acc: 98.19 %
[4,   800]: loss: 0.020 , acc: 98.08 %
[4,   900]: loss: 0.018 , acc: 98.38 %
[4]: Accuracy on test set: 98.2 % 
[5,   100]: loss: 0.018 , acc: 98.12 %
[5,   200]: loss: 0.017 , acc: 98.41 %
[5,   300]: loss: 0.021 , acc: 98.11 %
[5,   400]: loss: 0.019 , acc: 98.42 %
[5,   500]: loss: 0.018 , acc: 98.58 %
[5,   600]: loss: 0.016 , acc: 98.47 %
[5,   700]: loss: 0.018 , acc: 98.36 %
[5,   800]: loss: 0.016 , acc: 98.56 %
[5,   900]: loss: 0.017 , acc: 98.30 %
[5]: Accuracy on test set: 98.6 % 

相比之下前馈神经网络收敛快但是上限低，LeNet收敛慢但是上限高

总结

别人的代码看不懂很正常莫名的报错也很正常，不懂思路结构也很正常，因为不是你写的，抄也要从头打一遍吧