一、方式一
网络模型、损失函数、数据(包括输入、标注)
找到以上三种变量,调用它们的.cuda(),再返回即可
python
if torch.cuda.is_available():
mynn = mynn.cuda()
python
if torch.cuda.is_available():
loss_function = loss_function.cuda()
python
for data in train_dataloader:
imgs,targets = data
if torch.cuda.is_available():
imgs = imgs.cuda()
targets = targets.cuda()
python
for data in test_dataloader:
imgs,targets = data
if torch.cuda.is_available():
imgs = imgs.cuda()
targets = targets.cuda()
完整代码:
python
import torch
import torchvision
from torch import nn
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
import time
# from model import *
# 准备数据集
train_data = torchvision.datasets.CIFAR10(root="../datasets",train=True,transform=torchvision.transforms.ToTensor(),download=False)
test_data = torchvision.datasets.CIFAR10(root="../datasets",train=False,transform=torchvision.transforms.ToTensor(),download=False)
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 MyNN(nn.Module):
def __init__(self):
super(MyNN, 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
mynn = MyNN()
if torch.cuda.is_available():
mynn = mynn.cuda()
# 损失函数
loss_function = nn.CrossEntropyLoss()
if torch.cuda.is_available():
loss_function = loss_function.cuda()
# 优化器
learning_rate = 1e-2
optimizer = torch.optim.SGD(mynn.parameters(), lr=learning_rate)
# 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 # 训练的轮数
# 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
mynn.train()
for data in train_dataloader:
imgs,targets = data
if torch.cuda.is_available():
imgs = imgs.cuda()
targets = targets.cuda()
outputs = mynn(imgs)
loss = loss_function(outputs, targets)
# 优化器优化模型
optimizer.zero_grad()
loss.backward()
optimizer.step()
total_train_step += 1
if total_train_step % 100 == 0:
end_time = time.time()
print("所用时间:{}".format(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
mynn.eval()
total_test_loss = 0
total_accuracy = 0
with torch.no_grad():
for data in test_dataloader:
imgs,targets = data
if torch.cuda.is_available():
imgs = imgs.cuda()
targets = targets.cuda()
outputs = mynn(imgs)
loss = loss_function(outputs, targets)
total_test_loss += loss
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_loss",total_test_loss,total_test_step)
writer.add_scalar("test_accuracy",total_accuracy/test_data_size,total_test_step)
total_test_step += 1
torch.save(mynn,"mynn_{}.pth".format(i))
# torch.save(mynn.state_dict(),"mynn_{}.pth".format(i))
print("模型已保存")
writer.close()
比较CPU和GPU的训练时间:
查看GPU信息:
在 终端里输入nvidia-smi
使用Google Colab:Google 为我们提供了一个免费的GPU修改 ------> 笔记本设置 ------> 硬件加速器选择GPU(每周免费使用30h)
二、方式二(更常用)
定义训练设备
python
device = torch.device("cpu")
python
# 对于单显卡来说,以下两种方式没有区别
device = torch.device("cuda")
device = torch.device("cuda:0")
python
# 一种语法的简写,程序在 CPU 或 GPU/cuda 环境下都能运行
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
网络模型、损失函数、数据(包括输入、标注)
找到以上三种变量,.to(device),再返回即可
python
mynn = MyNN()
mynn = mynn.to(device)
# 这里可以不用再赋值给mynn,直接mynn.to(device) 也可以
python
loss_function = nn.CrossEntropyLoss()
loss_function = loss_function.to(device)
# 这里可以不用再赋值给loss_function ,直接loss_function .to(device) 也可以
python
for data in train_dataloader:
imgs,targets = data
imgs = imgs.to(device)
targets = targets.to(device)
# 这里必须赋值
python
for data in test_dataloader:
imgs,targets = data
imgs = imgs.to(device)
targets = imgs.to(device)
# 这里必须赋值
完整代码:
python
import torch
import torchvision
from torch import nn
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
import time
# from model import *
# 定义训练的设备
# device = torch.device("cpu")
# device = torch.device("cuda")
# device = torch.device("cuda:0")
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
# 准备数据集
train_data = torchvision.datasets.CIFAR10(root="../datasets",train=True,transform=torchvision.transforms.ToTensor(),download=False)
test_data = torchvision.datasets.CIFAR10(root="../datasets",train=False,transform=torchvision.transforms.ToTensor(),download=False)
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 MyNN(nn.Module):
def __init__(self):
super(MyNN, 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
mynn = MyNN()
mynn.to(device)
# 损失函数
loss_function = nn.CrossEntropyLoss()
loss_function.to(device)
# 优化器
learning_rate = 1e-2
optimizer = torch.optim.SGD(mynn.parameters(), lr=learning_rate)
# 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 # 训练的轮数
# 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
mynn.train()
for data in train_dataloader:
imgs,targets = data
imgs = imgs.to(device)
targets = targets.to(device)
outputs = mynn(imgs)
loss = loss_function(outputs, targets)
# 优化器优化模型
optimizer.zero_grad()
loss.backward()
optimizer.step()
total_train_step += 1
if total_train_step % 100 == 0:
end_time = time.time()
print("所用时间:{}".format(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
mynn.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 = mynn(imgs)
loss = loss_function(outputs, targets)
total_test_loss += loss
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_loss",total_test_loss,total_test_step)
writer.add_scalar("test_accuracy",total_accuracy/test_data_size,total_test_step)
total_test_step += 1
torch.save(mynn,"mynn_{}.pth".format(i))
# torch.save(mynn.state_dict(),"mynn_{}.pth".format(i))
print("模型已保存")
writer.close()