1. GPU优化的点
网络模型
数据（输入、标注)
损失函数
- .cuda方式
代码：
import torch.optim
import torchvision
from torch import nn
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter# 1. 准备数据集
train_data = torchvision.datasets.CIFAR10('data',train=True,transform=torchvision.transforms.ToTensor(),download=True)
test_data = torchvision.datasets.CIFAR10('data',train=False,transform=torchvision.transforms.ToTensor(),download=True)
# 数据集大小
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))# 2 利用DataLoader加载数据集
train_dataloader = DataLoader(train_data,batch_size=64)
test_dataloader = DataLoader(test_data,batch_size=64)# 3 搭建神经网络
# 3 搭建神经网络
class Tudui(nn.Module):def __init__(self):super().__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(1024,64),nn.Linear(64, 10))def forward(self,x):x = self.model(x)return x# 4 创建网络模型
tudui = Tudui()
# --------------------------
if torch.cuda.is_available():tudui = tudui.cuda()# 5 损失函数
loss_fn = nn.CrossEntropyLoss()
# ---------------------------
if torch.cuda.is_available():loss_fn = loss_fn.cuda()# 6 优化器 1e-2=1x10^(-2)
learning_rate = 0.01
optimizer = torch.optim.SGD(tudui.parameters(),lr=learning_rate)# 7 设置训练网络的一些参数
total_train_step = 0 # 记录训练次数
total_test_step = 0 # 记录测试次数
epoch = 10 #训练轮数
# 添加tensorboard
writer = SummaryWriter('logs_model')
for i in range(epoch):print('-----------第{}轮训练开始-----------'.format(i+1))# 训练开始# 训练步骤开始 dropout batchNorm仅对某些层次有作用tudui.train()for data in train_dataloader:imgs, targets = data# ---------------------------if torch.cuda.is_available():imgs = imgs.cuda()targets = targets.cuda()output = tudui(imgs) #训练模型的预测输出loss = loss_fn(output,targets)# 优化器优化模型optimizer.zero_grad()loss.backward()optimizer.step()total_train_step += 1if total_train_step % 100 == 0:print('训练次数是{}时，loss是{}'.format(total_train_step,loss.item()))# 加了item() tensor变成了数字writer.add_scalar('train_loss',loss.item(),total_train_step)# 训练完一轮，看是否训练好,有没有达到想要的需求，测试数据集中跑一篇看准确率或者损失# 测试步骤开始tudui.eval()total_test_loss = 0total_accuracy = 0# 测试不需要对梯度进行调整with torch.no_grad():for data in test_dataloader:imgs,targets = data# ---------------------------if torch.cuda.is_available():imgs = imgs.cuda()targets = targets.cuda()outputs = tudui(imgs)loss = loss_fn(outputs,targets)total_test_loss += loss.item()accuracy = (outputs.argmax(1) == targets).sum()total_accuracy += accuracyprint('整体测试集上的loss是{}'.format(total_test_loss))print('整体测试集上的正确率是{}'.format(total_accuracy/test_data_size))writer.add_scalar('test_loss',total_test_loss,total_test_step)writer.add_scalar('test_accuracy', total_accuracy, total_test_step)total_test_step+=1torch.save(tudui,'tudui_{}.pth'.format(i))print('模型已保存')writer.close()
3…to(device)方式
device = torch.device("cpu")
# 第一张显卡
torch.device("cuda")
torch.device("cuda:0")
# 第二张
torch.device("cuda:1")
代码：
import torch.optim
import torchvision
from torch import nn
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
# 定义训练的设备
device = torch.device('cuda')# 1. 准备数据集
train_data = torchvision.datasets.CIFAR10('data',train=True,transform=torchvision.transforms.ToTensor(),download=True)
test_data = torchvision.datasets.CIFAR10('data',train=False,transform=torchvision.transforms.ToTensor(),download=True)
# 数据集大小
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))# 2 利用DataLoader加载数据集
train_dataloader = DataLoader(train_data,batch_size=64)
test_dataloader = DataLoader(test_data,batch_size=64)# 3 搭建神经网络
# 3 搭建神经网络
class Tudui(nn.Module):def __init__(self):super().__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(1024,64),nn.Linear(64, 10))def forward(self,x):x = self.model(x)return x# 4 创建网络模型
tudui = Tudui()
# --------------------------
# if torch.cuda.is_available():
# tudui = tudui.cuda()
tudui = tudui.to(device)# 5 损失函数
loss_fn = nn.CrossEntropyLoss()
# ---------------------------
# if torch.cuda.is_available():
# loss_fn = loss_fn.cuda()
loss_fn = loss_fn.to(device)# 6 优化器 1e-2=1x10^(-2)
learning_rate = 0.01
optimizer = torch.optim.SGD(tudui.parameters(),lr=learning_rate)# 7 设置训练网络的一些参数
total_train_step = 0 # 记录训练次数
total_test_step = 0 # 记录测试次数
epoch = 10 #训练轮数
# 添加tensorboard
writer = SummaryWriter('logs_model')
for i in range(epoch):print('-----------第{}轮训练开始-----------'.format(i+1))# 训练开始# 训练步骤开始 dropout batchNorm仅对某些层次有作用tudui.train()for data in train_dataloader:imgs, targets = data# ---------------------------# if torch.cuda.is_available():# imgs = imgs.cuda()# targets = targets.cuda()imgs = imgs.to(device)targets = targets.to(device)output = tudui(imgs) #训练模型的预测输出loss = loss_fn(output,targets)# 优化器优化模型optimizer.zero_grad()loss.backward()optimizer.step()total_train_step += 1if total_train_step % 100 == 0:print('训练次数是{}时，loss是{}'.format(total_train_step,loss.item()))# 加了item() tensor变成了数字writer.add_scalar('train_loss',loss.item(),total_train_step)# 训练完一轮，看是否训练好,有没有达到想要的需求，测试数据集中跑一篇看准确率或者损失# 测试步骤开始tudui.eval()total_test_loss = 0total_accuracy = 0# 测试不需要对梯度进行调整with torch.no_grad():for data in test_dataloader:imgs,targets = data# ---------------------------# if torch.cuda.is_available():# imgs = imgs.cuda()# targets = targets.cuda()imgs = imgs.to(device)targets = targets.to(device)outputs = tudui(imgs)loss = loss_fn(outputs,targets)total_test_loss += loss.item()accuracy = (outputs.argmax(1) == targets).sum()total_accuracy += accuracyprint('整体测试集上的loss是{}'.format(total_test_loss))print('整体测试集上的正确率是{}'.format(total_accuracy/test_data_size))writer.add_scalar('test_loss',total_test_loss,total_test_step)writer.add_scalar('test_accuracy', total_accuracy, total_test_step)total_test_step+=1torch.save(tudui,'tudui_{}.pth'.format(i))print('模型已保存')writer.close()
