3.1模型创建步骤与nn.Module

import os
import random
import numpy as np
import torch
import torch.nn as nn
from torch.utils.data import DataLoader
import torchvision.transforms as transforms
import torch.optim as optim
from matplotlib import pyplot as plt
from model.lenet import LeNet
from tools.my_dataset import RMBDataset


def set_seed(seed=1):
    random.seed(seed)
    np.random.seed(seed)
    torch.manual_seed(seed)
    torch.cuda.manual_seed(seed)


set_seed()  # 设置随机种子
rmb_label = {"1": 0, "100": 1}

# 参数设置
MAX_EPOCH = 10
BATCH_SIZE = 16
LR = 0.01
log_interval = 10
val_interval = 1

# ============================ step 1/5 数据 ============================

split_dir = os.path.join("..", "..", "data", "rmb_split")
train_dir = os.path.join(split_dir, "train")
valid_dir = os.path.join(split_dir, "valid")

norm_mean = [0.485, 0.456, 0.406]
norm_std = [0.229, 0.224, 0.225]

train_transform = transforms.Compose([
    transforms.Resize((32, 32)),
    transforms.RandomCrop(32, padding=4),
    transforms.ToTensor(),
    transforms.Normalize(norm_mean, norm_std),
])

valid_transform = transforms.Compose([
    transforms.Resize((32, 32)),
    transforms.ToTensor(),
    transforms.Normalize(norm_mean, norm_std),
])

# 构建MyDataset实例
train_data = RMBDataset(data_dir=train_dir, transform=train_transform)
valid_data = RMBDataset(data_dir=valid_dir, transform=valid_transform)

# 构建DataLoder
train_loader = DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)
valid_loader = DataLoader(dataset=valid_data, batch_size=BATCH_SIZE)

# ============================ step 2/5 模型 ============================
# 【1】第一次使用模型，创建了模型模块，在lenet的构造函数__init__里面
net = LeNet(classes=2)
net.initialize_weights()

# ============================ step 3/5 损失函数 ============================
criterion = nn.CrossEntropyLoss()                                                   # 选择损失函数

# ============================ step 4/5 优化器 ============================
optimizer = optim.SGD(net.parameters(), lr=LR, momentum=0.9)                        # 选择优化器
scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=10, gamma=0.1)     # 设置学习率下降策略

# ============================ step 5/5 训练 ============================
train_curve = list()
valid_curve = list()

for epoch in range(MAX_EPOCH):

    loss_mean = 0.
    correct = 0.
    total = 0.

    net.train()
    for i, data in enumerate(train_loader):

        # forward
        inputs, labels = data

        # 【2】再次使用模型是在训练的时候---》传入数据inputs（张量）
        # 什么时候进行拼接子模块，实现forword前向传播
        outputs = net(inputs)

        # backward
        optimizer.zero_grad()
        loss = criterion(outputs, labels)
        loss.backward()

        # update weights
        optimizer.step()

        # 统计分类情况
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).squeeze().sum().numpy()

        # 打印训练信息
        loss_mean += loss.item()
        train_curve.append(loss.item())
        if (i+1) % log_interval == 0:
            loss_mean = loss_mean / log_interval
            print("Training:Epoch[{:0>3}/{:0>3}] Iteration[{:0>3}/{:0>3}] Loss: {:.4f} Acc:{:.2%}".format(
                epoch, MAX_EPOCH, i+1, len(train_loader), loss_mean, correct / total))
            loss_mean = 0.

    scheduler.step()  # 更新学习率

    # validate the model
    if (epoch+1) % val_interval == 0:

        correct_val = 0.
        total_val = 0.
        loss_val = 0.
        net.eval()
        with torch.no_grad():
            for j, data in enumerate(valid_loader):
                inputs, labels = data
                outputs = net(inputs)
                loss = criterion(outputs, labels)

                _, predicted = torch.max(outputs.data, 1)
                total_val += labels.size(0)
                correct_val += (predicted == labels).squeeze().sum().numpy()

                loss_val += loss.item()

            valid_curve.append(loss_val)
            print("Valid:\t Epoch[{:0>3}/{:0>3}] Iteration[{:0>3}/{:0>3}] Loss: {:.4f} Acc:{:.2%}".format(
                epoch, MAX_EPOCH, j+1, len(valid_loader), loss_val, correct / total))


train_x = range(len(train_curve))
train_y = train_curve

train_iters = len(train_loader)
valid_x = np.arange(1, len(valid_curve)+1) * train_iters*val_interval # 由于valid中记录的是epochloss，需要对记录点进行转换到iterations
valid_y = valid_curve

plt.plot(train_x, train_y, label='Train')
plt.plot(valid_x, valid_y, label='Valid')

plt.legend(loc='upper right')
plt.ylabel('loss value')
plt.xlabel('Iteration')
plt.show()

# ============================ inference ============================

BASE_DIR = os.path.dirname(os.path.abspath(__file__))
test_dir = os.path.join(BASE_DIR, "test_data")

test_data = RMBDataset(data_dir=test_dir, transform=valid_transform)
valid_loader = DataLoader(dataset=test_data, batch_size=1)

for i, data in enumerate(valid_loader):
    # forward
    inputs, labels = data
    outputs = net(inputs)
    _, predicted = torch.max(outputs.data, 1)

    rmb = 1 if predicted.numpy()[0] == 0 else 100
    print("模型获得{}元".format(rmb))

1、在net = LeNet(classes=2) 设置断点---》step Into--》lenet.py类中如何构建一个模型

2、单步：step over--》运行到此 self.fc3 = nn.Linear(84, classes)--》跳出--》
到create_module.py:  net.initialize_weights()

3、 outputs = net(inputs)：上面已经构建了lenet子模块，但是还没有拼接这些子模块，没有实现forward
step Into这行

4、进入module.py的call函数：lenet继承module---》表明这个实例是可以被调用的
 def __call__(self, *input, **kwargs):
        for hook in self._forward_pre_hooks.values():
            result = hook(self, input)
            if result is not None:
                if not isinstance(result, tuple):
                    result = (result,)
                input = result
        if torch._C._get_tracing_state():
            result = self._slow_forward(*input, **kwargs)
        else:
            result = self.forward(*input, **kwargs)----》进入这个函数 step Into
                                                  ---》lenet.py--->def forward():--》return out
        for hook in self._forward_hooks.values():
            hook_result = hook(self, input, result)
            if hook_result is not None:
                result = hook_result
        if len(self._backward_hooks) > 0:
            var = result
            while not isinstance(var, torch.Tensor):
                if isinstance(var, dict):
                    var = next((v for v in var.values() if isinstance(v, torch.Tensor)))
                else:
                    var = var[0]
            grad_fn = var.grad_fn
            if grad_fn is not None:
                for hook in self._backward_hooks.values():
                    wrapper = functools.partial(hook, self)
                    functools.update_wrapper(wrapper, hook)
                    grad_fn.register_hook(wrapper)
        return result

5、lenet.py--->def forward():


二：nn.Module的创建以及它对属性的管理的机制
1、在net = LeNet(classes=2) 设置断点---》step Into--》lenet.py类中如何构建一个模型

2、lenet.py--》  super(LeNet, self).__init__()---》step Into---》module.py
 def __init__(self):
        self._construct()---->step Into
        # initialize self.training separately from the rest of the internal
        # state, as it is managed differently by nn.Module and ScriptModule
        self.training = True---》step over-----》到了lenet.py 
                                super(LeNet, self).__init__() 

3、 实现八个字典的有序初始化
   def _construct(self):
        """
        Initializes internal Module state, shared by both nn.Module and ScriptModule.
        """
        torch._C._log_api_usage_once("python.nn_module")
        self._backend = thnn_backend
        self._parameters = OrderedDict()
        self._buffers = OrderedDict()
        self._backward_hooks = OrderedDict()
        self._forward_hooks = OrderedDict()
        self._forward_pre_hooks = OrderedDict()
        self._state_dict_hooks = OrderedDict()
        self._load_state_dict_pre_hooks = OrderedDict()
        self._modules = OrderedDict()

4、self.training = True--》step over--》跳回到lenet.py
这里就构建好了lenet基本属性

5、 self.conv1 = nn.Conv2d(3, 6, 5) ---》step Into---》conv.py
(在这里已经创建了一个模块，控制台上的 self可以看八个有序字典)
 
 在lenet.py中self.conv1 = nn.Conv2d(3, 6, 5) --》step over---》可以在控制台上---》self-----》
 Modules（里面会记录这一网络层，这一网络层属于module）

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


class LeNet(nn.Module):
    def __init__(self, classes):
        super(LeNet, self).__init__()     # 实现一个父类函数的调用功能
        # self.自命名  = nn(模块).(子模块)
        self.conv1 = nn.Conv2d(3, 6, 5)   # self 中已经构建了8个字典
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1 = nn.Linear(16*5*5, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, classes)

# 具体实现了前向传播，具体实现每一层的计算
    def forward(self, x):
        out = F.relu(self.conv1(x))
        out = F.max_pool2d(out, 2)
        out = F.relu(self.conv2(out))
        out = F.max_pool2d(out, 2)
        out = out.view(out.size(0), -1)
        out = F.relu(self.fc1(out))
        out = F.relu(self.fc2(out))
        out = self.fc3(out)
        return out
# 返回out，得到output：分类的概率向量

    def initialize_weights(self):
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.xavier_normal_(m.weight.data)
                if m.bias is not None:
                    m.bias.data.zero_()
            elif isinstance(m, nn.BatchNorm2d):
                m.weight.data.fill_(1)
                m.bias.data.zero_()
            elif isinstance(m, nn.Linear):
                nn.init.normal_(m.weight.data, 0, 0.1)
                m.bias.data.zero_()


class LeNet2(nn.Module):
    def __init__(self, classes):
        super(LeNet2, self).__init__()
        self.features = nn.Sequential(
            nn.Conv2d(3, 6, 5),
            nn.ReLU(),
            nn.MaxPool2d(2, 2),
            nn.Conv2d(6, 16, 5),
            nn.ReLU(),
            nn.MaxPool2d(2, 2)
        )
        self.classifier = nn.Sequential(
            nn.Linear(16*5*5, 120),
            nn.ReLU(),
            nn.Linear(120, 84),
            nn.ReLU(),
            nn.Linear(84, classes)
        )

    def forward(self, x):
        x = self.features(x)
        x = x.view(x.size()[0], -1)
        x = self.classifier(x)
        return x