python与深度学习【初步尝试】

学习资源来自b站，一点点手敲代码初步接触深度学习训练模型。感觉还是很神奇的！！

         将训练资源下载下来并通过训练模型来实现，本篇主要用来记录当时的一些代码和注释，方便后续回顾。

#######################################  net.py  ########################################
import torch
from torch import nn
 
 
# 定义一个网络模型
class MyLeNet5(nn.Module):
    # 初始化网络
    # 主要是复现LeNet-5
    def __init__(self):
        super(MyLeNet5, self).__init__()
 
        # 卷积层c1
        self.c1 = nn.Conv2d(in_channels=1, out_channels=6, kernel_size=5, padding=2)
        # 单纯单通道 so in=1，输出为6，约定俗成的卷积核是5，padding可以用公式算出来设置为2
 
        # 激活函数
        self.Sigmoid = nn.Sigmoid()
 
        # 平均池化（定义一个池化层） !注意! 池化层不改变通道大小，但是会改变特征图片的窗口大小
        self.s2 = nn.AvgPool2d(kernel_size=2, stride=2)
        # 卷积核为2，步长为2
 
        # 卷积层c3
        self.c3 = nn.Conv2d(in_channels=6, out_channels=16, kernel_size=5)
 
        # 池化层s4
        self.s4 = nn.AvgPool2d(kernel_size=2, stride=2)
 
        # 卷积层c5
        self.c5 = nn.Conv2d(in_channels=16, out_channels=120, kernel_size=5)
 
        # 平展层
        self.flatten = nn.Flatten()
        # 设置线性连接层
        self.f6 = nn.Linear(120, 84)
        # 输入、输出
        self.output = nn.Linear(84, 10)
 
    def forward(self, x):
        # 用Sigmoid函数激活
        x = self.Sigmoid(self.c1(x))
        # 池化层
        x = self.s2(x)
        # 以此类推
        x = self.Sigmoid(self.c3(x))
        x = self.s4(x)
        x = self.c5(x)
        x = self.flatten(x)
        x = self.f6(x)
        x = self.output(x)
        return x
 
 
if __name__ == "__main__":
    # 随机生成一个  批次1，通道1，大小是28*28  实例化
    x = torch.rand([1, 1, 28, 28])
    model = MyLeNet5()
    y = model(x)

########################################  test.py  ########################################
import torch
from net import MyLeNet5
from torch.autograd import Variable
from torchvision import datasets, transforms
from torchvision.transforms import ToPILImage
 
# 将数据转化为tensor格式（数据是矩阵格式，要进行转化为tensor格式）
data_transform = transforms.Compose([
    transforms.ToTensor()
])
 
# 加载训练数据集
train_dataset = datasets.MNIST(root='./data', train=True, transform=data_transform, download=True)
train_dataloader = torch.utils.data.DataLoader(dataset=train_dataset, batch_size=16, shuffle=True)
 
# 加载测试数据集
test_dataset = datasets.MNIST(root='./data', train=False, transform=data_transform, download=True)
test_dataloader = torch.utils.data.DataLoader(dataset=test_dataset, batch_size=16, shuffle=True)
 
# 如果有显卡，转到GPU
device = "cuda" if torch.cuda.is_available() else 'cpu'
 
# 调用net里面定义的模型，将模型数据转到GPU
model = MyLeNet5().to(device)
 
model.load_state_dict(torch.load("C:/Users/79926/PycharmProjects/pythonProject1/save_model/best_model.pth"))
 
# 获取结果
classes = [
    "0",
    "1",
    "2",
    "3",
    "4",
    "5",
    "6",
    "7",
    "8",
    "9",
]
 
# 把tensor转化为图片，方便可视化
show = ToPILImage()
 
# 进入验证
for i in range(5):
    X, y = test_dataset[i][0], test_dataset[i][1]
    show(X).show()
    # 这里会显示出5张图片
 
    X = Variable(torch.unsqueeze(X, dim=0).float(), requires_grad=False).to(device)
    with torch.no_grad():
        pred = model(X)
 
        predicted, actual = classes[torch.argmax(pred[0])], classes[y]
 
        print(f'predicted:"{predicted}",actual:"{actual}"')

########################################  train.py ########################################
import torch
from torch import nn
from net import MyLeNet5
from torch.optim import lr_scheduler
from torchvision import datasets, transforms
import os
 
# 将数据转化为tensor格式（数据是矩阵格式，要进行转化为tensor格式）
data_transform = transforms.Compose([
    transforms.ToTensor()
])
 
# 加载训练数据集
train_dataset = datasets.MNIST(root='./data', train=True, transform=data_transform, download=True)
train_dataloader = torch.utils.data.DataLoader(dataset=train_dataset, batch_size=16, shuffle=True)
 
# 加载测试数据集
test_dataset = datasets.MNIST(root='./data', train=False, transform=data_transform, download=True)
test_dataloader = torch.utils.data.DataLoader(dataset=test_dataset, batch_size=16, shuffle=True)
 
# 如果有显卡，转到GPU
device = "cuda" if torch.cuda.is_available() else 'cpu'
 
# 调用net里面定义的模型，将模型数据转到GPU
model = MyLeNet5().to(device)
 
# 定义一个损失函数（交叉熵损失）
loss_fn = nn.CrossEntropyLoss()
 
# 定义一个优化器
# (梯度下降)
optimizer = torch.optim.SGD(model.parameters(), lr=1e-3, momentum=0.9)
 
# 学习率每隔10轮变为原来的0.1
lr_scheduler = lr_scheduler.StepLR(optimizer, step_size=10, gamma=0.1)
 
 
# 定义训练函数
def train(dataloader, model, loss_fn, optimizer):
    loss, current, n = 0.0, 0.0, 0
    for batch, (X, y) in enumerate(dataloader):
        # 前向传播
        X, y = X.to(device), y.to(device)
        output = model(X)
        # 损失函数（用来反向传播）
        cur_loss = loss_fn(output, y)
        _, pred = torch.max(output, axis=1)
 
        # 计算精确度（累加->一轮的）
        cur_acc = torch.sum(y == pred) / output.shape[0]
 
        optimizer.zero_grad()
        cur_loss.backward()
        optimizer.step()
 
        loss += cur_loss.item()
        current += cur_acc.item()
        n = n + 1
    print("train_loss" + str(loss / n))
    print("train_acc" + str(current / n))
 
 
def val(dataloader, model, loss_fn):
    model.eval()
    loss, current, n = 0.0, 0.0, 0
    with torch.no_grad():
        for batch, (X, y) in enumerate(dataloader):
            # 前向传播
            X, y = X.to(device), y.to(device)
            output = model(X)
            # 损失函数（用来反向传播）
            cur_loss = loss_fn(output, y)
            _, pred = torch.max(output, axis=1)
            cur_acc = torch.sum(y == pred) / output.shape[0]
            loss += cur_loss.item()
            current += cur_acc.item()
            n = n + 1
        print("val_loss" + str(loss / n))
        print("val_acc" + str(current / n))
        return current/n
 
# 开始训练
epoch = 50
min_acc = 0
for t in range(epoch):
    print(f'epoch{t + 1}\n--------------')
    train(train_dataloader, model, loss_fn, optimizer)
    a=val(test_dataloader, model, loss_fn)
    #保存最好模型权重
    if a>min_acc:
        folder = 'save_model'
        if not os.path.exists(folder):
            os.mkdir('save_model')
        min_acc = a
        print('save best model')
        torch.save(model.state_dict(),'save_model/best_model.pth')
print('Done!')
 

附：该up主视频资源：（讲的很棒）

网络模型搭建_哔哩哔哩_bilibili

训练模型搭建_哔哩哔哩_bilibili

测试模型搭建_哔哩哔哩_bilibili