Pytorch 使用GPU训练
使用 GPU 训练只需要在原来的代码中修改几处就可以了。
我们有两种方式实现代码在 GPU 上进行训练
方法一 .cuda()
我们可以通过对网络模型，数据，损失函数这三种变量调用 .cuda() 来在GPU上进行训练
model = Model()
model = model.cuda()
loss_fn = nn.CrossEntropyLoss()
loss_fn = loss_fn.cuda()
for data in dataloader:
imgs, targets = data
imgs = imgs.cuda()
targets = targets.cuda()
但是如果电脑没有 GPU 就会报错，更好的写法是先判断 cuda 是否可用：
model = Model()
if torch.cuda.is_available():
model = model.cuda()
loss_fn = nn.CrossEntropyLoss()
if torch.cuda.is_available():
loss_fn = loss_fn.cuda()
for data in dataloader:
imgs, targets = data
if torch.cuda.is_available():
imgs = imgs.cuda()
targets = targets.cuda()
代码案例：
import torch
import torchvision
from torch import nn
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
import time
train_data = torchvision.datasets.CIFAR10(root="dataset", train=True, transform=torchvision.transforms.ToTensor(), download=True)
test_data = torchvision.datasets.CIFAR10(root="dataset", train=False, transform=torchvision.transforms.ToTensor(), download=True)
train_data_size = len(train_data)
test_data_size = len(test_data)
print("训练数据集及的长度为: {}".format(train_data_size))
print("测试数据集及的长度为: {}".format(test_data_size))
train_dataloader = DataLoader(train_data, batch_size=64)
test_dataloader = DataLoader(test_data, batch_size=64)
class Model(nn.Module):
def __init__(self) -> None:
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),
nn.Linear(64, 10)
)
def forward(self, input):
input = self.model(input)
return input
model = Model()
if torch.cuda.is_available():
model = model.cuda()
loss_fn = nn.CrossEntropyLoss()
if torch.cuda.is_available():
loss_fn = loss_fn.cuda()
learning_rate = 1e-2
optimizer = torch.optim.SGD(model.parameters(), lr = learning_rate)
total_train_step = 0
total_test_step = 0
epoch = 10
writer = SummaryWriter("logs_train")
start_time = time.time()
for i in range(epoch):
print("------第 {} 轮训练开始------".format(i+1))
for data in train_dataloader:
imgs, targets = data
if torch.cuda.is_available():
imgs = imgs.cuda()
targets = targets.cuda()
outputs = model(imgs)
loss = loss_fn(outputs, targets)
optimizer.zero_grad()
loss.backward()
optimizer.step()
total_train_step += 1
if total_train_step % 100 == 0:
end_time = time.time()
print("训练时间: {}".format(end_time - start_time))
print("训练次数: {}, Loss: {}".format(total_train_step, loss))
writer.add_scalar("train_loss", loss.item(), total_train_step)
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 = model(imgs)
loss = loss_fn(outputs, targets)
total_test_loss = 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)
writer.add_scalar("test_accuracy", total_accuracy / test_data_size, total_test_step)
total_test_loss += 1
torch.save(model, "model_{}.pth".format(i))
print("模型已保存")
writer.close()
方法二 .to(device)
指定 训练的设备
device = torch.device("cpu")
device = torch.device("cuda")
device = torch.device("cuda:0")
device = torch.device("cuda:1")
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
使用 GPU 训练
model = model.to(device)
loss_fn = loss_fn.to(device)
for data in train_dataloader:
imgs, targets = data
imgs = imgs.to(device)
targets = targets.to(device)
代码示例：
import torch
import torchvision
from torch import nn
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
import time
device = torch.device("cuda")
train_data = torchvision.datasets.CIFAR10(root="dataset", train=True, transform=torchvision.transforms.ToTensor(), download=True)
test_data = torchvision.datasets.CIFAR10(root="dataset", train=False, transform=torchvision.transforms.ToTensor(), download=True)
train_data_size = len(train_data)
test_data_size = len(test_data)
print("训练数据集及的长度为: {}".format(train_data_size))
print("测试数据集及的长度为: {}".format(test_data_size))
train_dataloader = DataLoader(train_data, batch_size=64)
test_dataloader = DataLoader(test_data, batch_size=64)
class Model(nn.Module):
def __init__(self) -> None:
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),
nn.Linear(64, 10)
)
def forward(self, input):
input = self.model(input)
return input
model = Model()
model = model.to(device)
loss_fn = nn.CrossEntropyLoss()
loss_fn = loss_fn.to(device)
learning_rate = 1e-2
optimizer = torch.optim.SGD(model.parameters(), lr = learning_rate)
total_train_step = 0
total_test_step = 0
epoch = 10
writer = SummaryWriter("logs_train")
start_time = time.time()
for i in range(epoch):
print("------第 {} 轮训练开始------".format(i+1))
for data in train_dataloader:
imgs, targets = data
imgs = imgs.to(device)
targets = targets.to(device)
outputs = model(imgs)
loss = loss_fn(outputs, targets)
optimizer.zero_grad()
loss.backward()
optimizer.step()
total_train_step += 1
if total_train_step % 100 == 0:
end_time = time.time()
print("训练时间: {}".format(end_time - start_time))
print("训练次数: {}, Loss: {}".format(total_train_step, loss))
writer.add_scalar("train_loss", loss.item(), total_train_step)
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 = model(imgs)
loss = loss_fn(outputs, targets)
total_test_loss = 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)
writer.add_scalar("test_accuracy", total_accuracy / test_data_size, total_test_step)
total_test_loss += 1
torch.save(model, "model_{}.pth".format(i))
print("模型已保存")
writer.close()
【注】对于网络模型和损失函数，直接调用 .cuda() 或者 .to() 即可。但是数据和标注需要返回变量
为了方便记忆，最好都返回变量
使用Google colab进行训练
Original: https://blog.csdn.net/weixin_45468845/article/details/122971688
Author: 风吹我亦散
Title: PyTorch 使用GPU训练
原创文章受到原创版权保护。转载请注明出处：https://www.johngo689.com/651512/
转载文章受原作者版权保护。转载请注明原作者出处！