21.1 .cuda() 方式
# "Ctrl + A"全选
21.1.1 直观理解
21.1.2 代码实现
import torch
import torchvision
from torch.utils.tensorboard import SummaryWriter
from model import * # 引入 model 中的所有内容(需在同一文件夹下)
from torch import nn
from torch.utils.data import DataLoader
import time # 比较时间
# 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)
# length 长度
train_data_size = len(train_data)
test_data_size = len(test_data)
# 若 train_data_size=10,训练数据集的长度为:10
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)
# 搭建神经网络
class Avlon(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(64*4*4, 64)
)
def forward(self, x):
x = self.model(x)
return x
avlon = Avlon()
if torch.cuda.is_available(): # 先判断GPU加速是否可用
avlon = avlon.cuda()
# 损失函数
loss_fn = nn.CrossEntropyLoss()
loss_fn = loss_fn.cuda()
# 优化器
# 1e-2=1 × (10)^(-2) = 1/100 = 0.01
learning_rate = 1e-2 # 便于修改
optimizer = torch.optim.SGD(avlon.parameters(), learning_rate)
# 设置训练网络的一些参数
# 记录训练次数
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")
start_time = time.time() # 获取程序运行起始时间
for i in range(epoch):
print("--------第 {} 轮训练开始--------".format(i+1))
# 训练步骤开始
# avlon.train() # 训练模式只对 Dropout, BatchNorm 等部分层有效
for data in train_dataloader:
imgs, targets = data # 针对批量数据进行操作
if torch.cuda.is_available():
imgs = imgs.cuda()
targets = targets.cuda()
outputs = avlon(imgs) # imgs 数据特征
loss = loss_fn(outputs, targets) # targets 样本对应的真实标签
# 优化器优化模型
optimizer.zero_grad() # 梯度清零
loss.backward() # 获取梯度
optimizer.step() # 对每一参数进行调优
total_train_step = total_train_step + 1
if total_train_step % 100 == 0: # 每逢 100 打印一次
end_time = time.time() # 每经过 100 次训练,记录当前时间
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)
# 测试开始
avlon.eval() # 测试模式同样只对部分层有效
total_test_loss = 0
total_accuracy = 0
with torch.no_grad(): # 测试中不调优
for data in test_dataloader:
imgs, targets = data
if torch.cuda.is_available():
imgs = imgs.cuda()
targets = targets.cuda()
outputs = avlon(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Accuracy: {}".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(avlon, "avlon_{}.pth".format(i))
# torch.save(avlon.state_dict(), "avlon_{}.pth".format(i))
print("模型已保存")
writer.close()
21.1.3 其他
# 在终端输入"nvidia-smi" 可获取GPU信息
# 可以使用 google colab 体验 GPU 加速 (网址link)
# 终端功能需要在语句开头加 ‘!’
21.2 .to(device) 方式
21.2.1 直观理解
# 数字表示使用第几张显卡
21.2.2 代码实现
import torch
import torchvision
from torch.utils.tensorboard import SummaryWriter
# from model import * # 引入 model 中的所有内容(需在同一文件夹下)
from torch import nn
from torch.utils.data import DataLoader
import time
# 定义训练的设备
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(device)
# 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)
# length 长度
train_data_size = len(train_data)
test_data_size = len(test_data)
# 若 train_data_size=10,训练数据集的长度为:10
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)
# 搭建神经网络
class Avlon(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(64*4*4, 64)
)
def forward(self, x):
x = self.model(x)
return x
avlon = Avlon()
avlon.to(device) # 模型无需重新赋值
# 损失函数
loss_fn = nn.CrossEntropyLoss()
loss_fn.to(device) # 损失函数无需重新赋值
# 优化器
# 1e-2=1 × (10)^(-2) = 1/100 = 0.01
learning_rate = 1e-2 # 便于修改
optimizer = torch.optim.SGD(avlon.parameters(), learning_rate)
# 设置训练网络的一些参数
# 记录训练次数
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")
start_time = time.time() # 获取程序运行起始时间
for i in range(epoch):
print("--------第 {} 轮训练开始--------".format(i+1))
# 训练步骤开始
# avlon.train() # 训练模式只对 Dropout, BatchNorm 等部分层有效
for data in train_dataloader:
imgs, targets = data # 针对批量数据进行操作
imgs = imgs.to(device)
targets = targets.to(device)
outputs = avlon(imgs) # imgs 数据特征
loss = loss_fn(outputs, targets) # targets 样本对应的真实标签
# 优化器优化模型
optimizer.zero_grad() # 梯度清零
loss.backward() # 获取梯度
optimizer.step() # 对每一参数进行调优
total_train_step = total_train_step + 1
if total_train_step % 100 == 0: # 每逢 100 打印一次
end_time = time.time() # 每经过 100 次训练,记录当前时间
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)
# 测试开始
avlon.eval() # 测试模式同样只对部分层有效
total_test_loss = 0
total_accuracy = 0
with torch.no_grad(): # 测试中不调优
for data in test_dataloader:
imgs, targets = data
imgs = imgs.to(device)
targets = targets.to(device)
outputs = avlon(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Accuracy: {}".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(avlon, "avlon_{}.pth".format(i))
# torch.save(avlon.state_dict(), "avlon_{}.pth".format(i))
print("模型已保存")
writer.close()