Pytroch 深度学习 跑CIFAR10数据集

 CPU跑

from torch.utils.tensorboard import SummaryWriter

#from model import *

import torchvision
from torch import nn
from torch.utils.data import DataLoader


# 准备数据集
train_data = torchvision.datasets.CIFAR10(root='./data', train=True, transform=torchvision.transforms.ToTensor(),
                                          download=True)
test_data = torchvision.datasets.CIFAR10(root='./data', train=False, transform=torchvision.transforms.ToTensor(),
                                          download=True)

# 数据集的长度
train_data_size = len(train_data)
test_data_size = len(test_data)
print("训练数据集的长度为：{}".format(train_data_size))
print("测试数据集的长度为：{}".format(test_data_size))

# 利用 DataLoader 来加载数据集
train_dataloader = DataLoader(train_data, batch_size=64)
test_dataloader = DataLoader(test_data, batch_size=64)

# 创建网络模型
# 搭建神经网络
class Demo(nn.Module):
    def __init__(self):
        super(Demo, self).__init__()
        self.model = nn.Sequential(
            nn.Conv2d(3, 32, 5, 1, 2),
            nn.MaxPool2d(2),
            nn.Conv2d(32, 32, 5, 1, 2),
            nn.MaxPool2d(2),
            nn.Conv2d(32, 64, 5, 1, 2),
            nn.MaxPool2d(2),
            nn.Flatten(),
            nn.Linear(64*4*4, 64),
            nn.Linear(64, 10)
        )

    def forward(self, x):
        x = self.model(x)
        return x
demo = Demo()

# 损失函数
loss_fn = nn.CrossEntropyLoss()

# 优化器
# learning_rate = 0.01
# 1e-2 = 1 *(10)^(-2) = 1 / 100 = 0.01
learning_rate = 1e-2
optimizer = torch.optim.SGD(demo.parameters(), lr=learning_rate)

# 设置训练网络的一些参数
# 记录训练的次数
total_train_step = 0
# 记录测试的次数
total_test_step = 0
# 训练的轮数
epoch = 10

# 添加tensorboard
writer = SummaryWriter("./logs_train")

for i in range(epoch):
    print("----------第 {} 轮训练开始----------".format(i+1))

    # 训练步骤开始
    demo.train()
    for data in train_dataloader:
        imgs, targets = data
        outputs = demo(imgs)
        loss = loss_fn(outputs, targets)

        # 优化器优化模型

        # 优化器梯度清零
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        total_train_step += 1
        if total_train_step % 100 == 0:
            print("训练次数：{}， Loss：{}".format(total_train_step, loss.item()))
            writer.add_scalar("train_loss", loss.item(), total_train_step)

    # 测试步骤开始
    demo.eval()
    total_test_loss = 0

    total_accuracy = 0
    # 没有了梯度，保证不会进行调优，进行测试
    with torch.no_grad():
        for data in test_dataloader:
            imgs, targets = data
            outputs = demo(imgs)
            loss = loss_fn(outputs, targets)
            total_test_loss += loss.item()
            accuracy = (outputs.argmax(1) == targets).sum()
            total_accuracy += accuracy

    print("整体测试集上的Loss：{}".format(total_test_loss))
    print("整体测试集上的正确率：{}".format(total_accuracy/test_data_size))
    writer.add_scalar("test_accuracy", total_accuracy/test_data_size, total_test_step)
    writer.add_scalar("test_loss", total_test_loss, total_test_step)
    total_test_step += 1

    # 保存每一轮训练的结果
    torch.save(demo, "demo_{}.pth".format(i))
    #torch.save(demo.state_dict(), "demo_{}.pth".format(i))
    print("模型已保存")

writer.close()

---

GPU跑

两种调用cuda的方式

方式一

'''
需要调用 gpu（.cuda） 的三个地方：
1. 网络模型
2. 数据（输入、标注）
3. 损失函数
'''


import time
import torch
from torch.utils.tensorboard import SummaryWriter
# from model import *
import torchvision
from torch import nn
from torch.utils.data import DataLoader


# 准备数据集
train_data = torchvision.datasets.CIFAR10(root='./data', train=True, transform=torchvision.transforms.ToTensor(),
                                          download=True)
test_data = torchvision.datasets.CIFAR10(root='./data', train=False, transform=torchvision.transforms.ToTensor(),
                                          download=True)

# 数据集的长度
train_data_size = len(train_data)
test_data_size = len(test_data)
print("训练数据集的长度为：{}".format(train_data_size))
print("测试数据集的长度为：{}".format(test_data_size))

# 利用 DataLoader 来加载数据集
train_dataloader = DataLoader(train_data, batch_size=64)
test_dataloader = DataLoader(test_data, batch_size=64)


# 创建网络模型
class Demo(nn.Module):
    def __init__(self):
        super(Demo, self).__init__()
        self.model = nn.Sequential(
            nn.Conv2d(3, 32, 5, 1, 2),
            nn.MaxPool2d(2),
            nn.Conv2d(32, 32, 5, 1, 2),
            nn.MaxPool2d(2),
            nn.Conv2d(32, 64, 5, 1, 2),
            nn.MaxPool2d(2),
            nn.Flatten(),
            nn.Linear(64*4*4, 64),
            nn.Linear(64, 10)
        )

    def forward(self, x):
        x = self.model(x)
        return x
demo = Demo()
#调用gpu
if torch.cuda.is_available():
    demo = demo.cuda()

# 损失函数
loss_fn = nn.CrossEntropyLoss()
#调用gpu
if torch.cuda.is_available():
    loss_fn = loss_fn.cuda()

# 优化器
# learning_rate = 0.01
# 1e-2 = 1 *(10)^(-2) = 1 / 100 = 0.01
learning_rate = 1e-2
optimizer = torch.optim.SGD(demo.parameters(), lr=learning_rate)

# 设置训练网络的一些参数
# 记录训练的次数
total_train_step = 0
# 记录测试的次数
total_test_step = 0
# 训练的轮数
epoch = 5

# 添加tensorboard
writer = SummaryWriter("./logs_train")
start_time = time.time()
for i in range(epoch):
    print("----------第 {} 轮训练开始----------".format(i+1))

    # 训练步骤开始
    demo.train()
    for data in train_dataloader:
        imgs, targets = data
        # 调用gpu
        if torch.cuda.is_available():
            imgs = imgs.cuda()
            targets = targets.cuda()
        outputs = demo(imgs)
        loss = loss_fn(outputs, targets)

        # 优化器优化模型

        # 优化器梯度清零
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        total_train_step += 1
        if total_train_step % 100 == 0:
            end_time = time.time()
            print(end_time - start_time)
            print("训练次数：{}， Loss：{}".format(total_train_step, loss.item()))
            writer.add_scalar("train_loss", loss.item(), total_train_step)

    # 测试步骤开始
    demo.eval()
    total_test_loss = 0

    total_accuracy = 0
    # 没有了梯度，保证不会进行调优，进行测试
    with torch.no_grad():
        for data in test_dataloader:
            imgs, targets = data
            # 调用gpu
            if torch.cuda.is_available():
                imgs = imgs.cuda()
                targets = targets.cuda()
            outputs = demo(imgs)
            loss = loss_fn(outputs, targets)
            total_test_loss += loss.item()
            accuracy = (outputs.argmax(1) == targets).sum()
            total_accuracy += accuracy

    print("整体测试集上的Loss：{}".format(total_test_loss))
    print("整体测试集上的正确率：{}".format(total_accuracy/test_data_size))
    writer.add_scalar("test_accuracy", total_accuracy/test_data_size, total_test_step)
    writer.add_scalar("test_loss", total_test_loss, total_test_step)
    total_test_step += 1

    # 保存每一轮训练的结果
    torch.save(demo, "demo_{}.pth".format(i))
    #torch.save(demo.state_dict(), "demo_{}.pth".format(i))
    print("模型已保存")

writer.close()

方式二

'''
需要调用 gpu（.cuda） 的三个地方：
1. 网络模型
2. 数据（输入、标注）
3. 损失函数
'''


import time
import torch
from torch.utils.tensorboard import SummaryWriter
# from model import *
import torchvision
from torch import nn
from torch.utils.data import DataLoader

# 定义训练的设备
device = torch.device("cuda")


# 准备数据集
train_data = torchvision.datasets.CIFAR10(root='./data', train=True, transform=torchvision.transforms.ToTensor(),
                                          download=True)
test_data = torchvision.datasets.CIFAR10(root='./data', train=False, transform=torchvision.transforms.ToTensor(),
                                          download=True)

# 数据集的长度
train_data_size = len(train_data)
test_data_size = len(test_data)
print("训练数据集的长度为：{}".format(train_data_size))
print("测试数据集的长度为：{}".format(test_data_size))

# 利用 DataLoader 来加载数据集
train_dataloader = DataLoader(train_data, batch_size=64)
test_dataloader = DataLoader(test_data, batch_size=64)


# 创建网络模型
class Demo(nn.Module):
    def __init__(self):
        super(Demo, self).__init__()
        self.model = nn.Sequential(
            nn.Conv2d(3, 32, 5, 1, 2),
            nn.MaxPool2d(2),
            nn.Conv2d(32, 32, 5, 1, 2),
            nn.MaxPool2d(2),
            nn.Conv2d(32, 64, 5, 1, 2),
            nn.MaxPool2d(2),
            nn.Flatten(),
            nn.Linear(64*4*4, 64),
            nn.Linear(64, 10)
        )

    def forward(self, x):
        x = self.model(x)
        return x
demo = Demo()
#调用gpu
demo = demo.to(device)


# 损失函数
loss_fn = nn.CrossEntropyLoss()
#调用gpu
loss_fn = loss_fn.to(device)

# 优化器
# learning_rate = 0.01
# 1e-2 = 1 *(10)^(-2) = 1 / 100 = 0.01
learning_rate = 1e-2
optimizer = torch.optim.SGD(demo.parameters(), lr=learning_rate)

# 设置训练网络的一些参数
# 记录训练的次数
total_train_step = 0
# 记录测试的次数
total_test_step = 0
# 训练的轮数
epoch = 5

# 添加tensorboard
writer = SummaryWriter("./logs_train")
start_time = time.time()
for i in range(epoch):
    print("----------第 {} 轮训练开始----------".format(i+1))

    # 训练步骤开始
    demo.train()
    for data in train_dataloader:
        imgs, targets = data
        # 调用gpu
        imgs = imgs.to(device)
        targets = targets.to(device)
        outputs = demo(imgs)
        loss = loss_fn(outputs, targets)

        # 优化器优化模型

        # 优化器梯度清零
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        total_train_step += 1
        if total_train_step % 100 == 0:
            end_time = time.time()
            print(end_time - start_time)
            print("训练次数：{}， Loss：{}".format(total_train_step, loss.item()))
            writer.add_scalar("train_loss", loss.item(), total_train_step)

    # 测试步骤开始
    demo.eval()
    total_test_loss = 0

    total_accuracy = 0
    # 没有了梯度，保证不会进行调优，进行测试
    with torch.no_grad():
        for data in test_dataloader:
            imgs, targets = data
            # 调用gpu
            imgs = imgs.to(device)
            targets = targets.to(device)
            outputs = demo(imgs)
            loss = loss_fn(outputs, targets)
            total_test_loss += loss.item()
            accuracy = (outputs.argmax(1) == targets).sum()
            total_accuracy += accuracy

    print("整体测试集上的Loss：{}".format(total_test_loss))
    print("整体测试集上的正确率：{}".format(total_accuracy/test_data_size))
    writer.add_scalar("test_accuracy", total_accuracy/test_data_size, total_test_step)
    writer.add_scalar("test_loss", total_test_loss, total_test_step)
    total_test_step += 1

    # 保存每一轮训练的结果
    torch.save(demo, "demo_{}.pth".format(i))
    #torch.save(demo.state_dict(), "demo_{}.pth".format(i))
    print("模型已保存")

writer.close()