PyTorch中如何用GPU进行训练【学习笔记】

PyTorch中，使用GPU对神经网络进行训练，只需要对网络、输入、损失函数进行修改。

方法一

import torch
import torchvision.datasets
from torch import nn
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
import time

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

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))

train_dataloader = DataLoader(train_data,batch_size = 64)
test_dataloader = DataLoader(test_data,batch_size = 64)

# 搭建神经网络
class Mioird(nn.Module):
    def __init__(self):
        super(Mioird, 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

mioird = Mioird()
if torch.cuda.is_available():
    mioird = mioird.cuda()

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

# 优化器
learning_rate = 0.01
optimizer = torch.optim.SGD(params=mioird.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
# 训练的轮次
epoch = 10

# 添加TensorBoard
writer = SummaryWriter("logs")
for i in range(epoch):
    print("--------第{}轮训练开始-------".format(i+1))
    start_time = time.time()
    # 训练步骤开始
    mioird.train()
    for data in train_dataloader:
        imgs,targets = data
        if torch.cuda.is_available():
            imgs = imgs.cuda()
            targets = targets.cuda()
        outputs = mioird(imgs)
        loss = loss_fn(outputs,targets)
        #优化器优化模型
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        total_train_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)
    end_time = time.time()
    print("此轮训练耗时：{}".format(end_time - start_time))

    # 测试步骤开始
    mioird.eval()
    total_test_loss = 0
    total_accuracy = 0
    with torch.no_grad():
        for data in test_dataloader:
            if torch.cuda.is_available():
                imgs,targets = data
                imgs = imgs.cuda()
                targets = targets.cuda()
            outputs = mioird(imgs)
            loss = loss_fn(outputs,targets)
            total_test_loss = total_test_loss + loss.item()
            accuracy = (outputs.argmax(1) == targets).sum()
            total_accuracy = 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_loss",total_test_loss,total_test_step)
    writer.add_scalar("test_accuracy",total_accuracy/test_data_size,total_test_step)

    total_test_step = total_test_step + 1

    torch.save(mioird.state_dict(),"mioird_{}.pth".format(i+1))
    print("模型已保存")

writer.close()

为了看得更清楚，我把对网络、输入、损失函数三部分的修改单独展示出来。若不加红字部分，则会在CPU上进行训练。 

mioird = Mioird()
if torch.cuda.is_available():
    mioird = mioird.cuda()

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

imgs,targets = data
if torch.cuda.is_available():
    imgs = imgs.cuda()
    targets = targets.cuda()

方法二

import torch
import torchvision.datasets
from torch import nn
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
import time

# 定义训练的设备
device = torch.device("cuda:0")

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

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))

train_dataloader = DataLoader(train_data,batch_size = 64)
test_dataloader = DataLoader(test_data,batch_size = 64)

# 搭建神经网络
class Mioird(nn.Module):
    def __init__(self):
        super(Mioird, 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

mioird = Mioird()
mioird.to(device)

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

# 优化器
learning_rate = 0.01
optimizer = torch.optim.SGD(params=mioird.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
# 训练的轮次
epoch = 10

# 添加TensorBoard
writer = SummaryWriter("logs")
for i in range(epoch):
    print("--------第{}轮训练开始-------".format(i+1))
    start_time = time.time()
    # 训练步骤开始
    mioird.train()
    for data in train_dataloader:
        imgs,targets = data
        imgs = imgs.to(device)
        targets = targets.to(device)
        outputs = mioird(imgs)
        loss = loss_fn(outputs,targets)
        #优化器优化模型
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        total_train_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)
    end_time = time.time()
    print("此轮训练耗时：{}".format(end_time - start_time))

    # 测试步骤开始
    mioird.eval()
    total_test_loss = 0
    total_accuracy = 0
    with torch.no_grad():
        for data in test_dataloader:
            imgs,targets = data
            imgs = imgs.to(device)
            targets = targets.to(device)
            outputs = mioird(imgs)
            loss = loss_fn(outputs,targets)
            total_test_loss = total_test_loss + loss.item()
            accuracy = (outputs.argmax(1) == targets).sum()
            total_accuracy = 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_loss",total_test_loss,total_test_step)
    writer.add_scalar("test_accuracy",total_accuracy/test_data_size,total_test_step)

    total_test_step = total_test_step + 1

    torch.save(mioird.state_dict(),"mioird_{}.pth".format(i+1))
    print("模型已保存")

writer.close()

为了看得更清楚，我把对网络、输入、损失函数三部分的修改单独展示出来。若不加红字部分，则会在CPU上进行训练。 

# 定义训练的设备
device = torch.device("cuda:0")

mioird = Mioird()
mioird.to(device)

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

imgs,targets = data
imgs = imgs.to(device)
targets = targets.to(device)

感谢B站UP主【我是土堆】老师！！