PyTorch深度学习笔记（十九）（利用GPU训练）

GPU训练（方式一）

GPU训练主要有三部分，网络模型、数据(输入、标注)、损失函数，这三部分放到GPU上。

网络模型转移到cuda上

if torch.cuda.is_available():
    tudui = tudui.cuda()

损失函数转移到cuda上

if torch.cuda.is_available():
    loss_fn = loss_fn.cuda()

数据放到cuda上

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

GPU训练时间

引入time

import time

记录开始时间

start_time = time.time()

记录结束时间

end_time = time.time()

运行训练一百次后的时间间隔

print(end_time - start_time)

利用GPU训练(方式二)

电脑上有两个显卡时，可以用指定cuda:0、cuda:1

定义训练设备

cpu训练

device = torch.device("cpu")

训练方式一

device = torch.device("cuda")

训练方式二

device = torch.device("cuda:0")

选择设备

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

把设备赋值给tudui网络，也可以不赋值，直接 tudui.to(device) 

tudui = tudui.to(device)

损失函数

loss_fn = loss_fn.to(device)

数据

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

整体代码

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

#device = torch.device("cpu")
#device = torch.device("cuda")   # 使用 GPU 方式一 
#device = torch.device("cuda:0") # 使用 GPU 方式二
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__init__()        
        self.model1 = 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.model1(x)
        return x

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：{}".format(train_data_size))
print("测试数据集的长度：{}".format(test_data_size))

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

tudui = Tudui()
tudui = tudui.to(device)  
#if torch.cuda.is_available():
#    tudui = tudui.cuda()

loss_fn = nn.CrossEntropyLoss() 
loss_fn = loss_fn.to(device)
#if torch.cuda.is_available():
#    loss_fn = loss_fn.cuda() 

learning = 0.01
optimizer = torch.optim.SGD(tudui.parameters(),learning) 

total_train_step = 0

total_test_step = 0

epoch = 10

writer = SummaryWriter("logs")

start_time = time.time()

for i in range(epoch):
    print("-----第 {} 轮训练开始-----".format(i+1))
    
    tudui.train()
    for data in train_dataloader:
        imgs, targets = data
        imgs = imgs.to(device)
        targets = targets.to(device)
        #if torch.cuda.is_available():
        #   imgs = imgs.cuda()
        #   targets = targets.cuda() 
        outputs = tudui(imgs)
        loss = loss_fn(outputs, targets)
        
        optimizer.zero_grad()
        loss.backward() 
        optimizer.step()
        
        total_train_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)
    
    tudui.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)
            #if torch.cuda.is_available():
            #   imgs = imgs.cuda()
            #   targets = targets.cuda()
            outputs = tudui(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(tudui, "./model/tudui_{}.pth".format(i))
    #torch.save(tudui.state_dict(),"tudui_{}.path".format(i))      
    print("模型已保存")
    
writer.close()