GUP训练方法
- ①找到:
- 网络模型
- 数据(输入、标注)
- 损失函数
这三样,然后调用其.cuda()方法,最后返回即可。
- ②使用Google Colab(前提是能访问Google)
- ③可以尝试使用kaggle提供的虚拟机
import tensorboard
import torch
import torchvision
from torch.utils.tensorboard import SummaryWriter
from torch import nn
from torch.utils.data import DataLoader
import time
# 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)
train_data_size = len(train_data)
test_data_size = len(test_data)
print("训练集的长度为:{}".format(train_data_size))
print("测试的长度为:{}".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 Tudui(nn.Module):
def __init__(self):
super(Tudui, self).__init__()
self.model = nn.Sequential(
nn.Conv2d(3, 32, 5, 1, padding=2),
nn.MaxPool2d(2),
nn.Conv2d(32, 32, 5, 1, padding=2),
nn.MaxPool2d(2),
nn.Conv2d(32, 64, 5, 1, padding=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
tudui = Tudui()
if torch.cuda.is_available():
tudui = tudui.cuda()
# 创建损失函数
loss_fn = nn.CrossEntropyLoss()
if torch.cuda.is_available():
loss_fn = loss_fn.cuda()
# 定义优化器
learning_rate = 0.01
optimizer = torch.optim.SGD(tudui.parameters(), lr=learning_rate)
# 设置训练网络的一些参数
# 记录训练的次数
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()
for i in range(epoch):
print("--------第{}轮训练开始----------".format(i + 1))
# 训练步骤开始
tudui.train()
for data in train_dataloader:
imgs, targets = data
if torch.cuda.is_available():
imgs = imgs.cuda()
targets = targets.cuda()
outputs = tudui(imgs)
loss = loss_fn(outputs, targets)
# 优化器调优
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)
# 测试步骤开始
tudui.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 = 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, "tudui_{}.pth".format(i))
# torch.save(tudui.state_dict(),"tudui_{}.pth".format(i))
print("模型已保存")
writer.close()
gpu对比未用gpu:用了gpu的速度快
nvidia-smi查看gpu
- ④调用.to()方法
网络模型和损失函数是不需要重新赋值的,只有数据需要重新赋值。
- device :torch.device("cuda”)
- device s torch.device("cuda:0”)
- device = torch,device(“cuda” if torch,cuda.is available()else “cpu”)
#定义训练的设备
device=torch.device("cpu")
-------------------------------------
tudui=tudui.to(device)
-------------------------------------
loss_fn=loss_fn.to(device)
-------------------------------------
imgs=imgs.to(device)
targets=targets.to(device)