莫烦Python_GPU加速运算

最新推荐文章于 2026-07-16 12:18:59 发布

转载最新推荐文章于 2026-07-16 12:18:59 发布 · 585 阅读

0 ·

本内容遵循CC 4.0 BY-SA版权协议

原文链接：https://mofanpy.com/tutorials/machine-learning/torch/GPU/

收录于

Pytorch教程

该博客介绍了如何将PyTorch模型和数据迁移到GPU以利用CUDA加速训练过程。通过添加.cuda()方法，将数据和模型转换为GPU可处理的形式，从而提升训练速度。同时，注意到在CPU和GPU之间转移数据时，需要使用.cpu()方法。文章还强调了GPU训练的模型不能直接在CPU上加载，反之则可以。

代码需要修改的地方包括将数据的形式变成GPU能读的形式，将CNN也变成GPU能读的形式，做法就是在后面加上.cuda()：

import torch
import torch.nn as nn
import torch.utils.data as Data
import torchvision

EPOCH = 1
BATCH_SIZE = 50
LR = 0.001
DOWNLOAD_MNIST = False

train_data = torchvision.datasets.MNIST(root='./mnist/', train=True, transform=torchvision.transforms.ToTensor(), download=DOWNLOAD_MNIST, )
train_loader = Data.DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)

test_data = torchvision.datasets.MNIST(root='./mnist/', train=False)

# Change in here
test_x = torch.unsqueeze(test_data.test_data, dim=1).type(torch.FloatTensor)[:2000].cuda() / 255.  # Tensor on GPU
test_y = test_data.test_labels[:2000].cuda()

class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        self.conv1 = nn.Sequential(
            nn.Conv2d(in_channels=1, out_channels=16, kernel_size=5, stride=1, padding=2, ),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2),
        )
        self.conv2 = nn.Sequential(
            nn.Conv2d(16, 32, 5, 1, 2),
            nn.ReLU(),
            nn.MaxPool2d(2),
        )
        self.out = nn.Linear(32 * 7 * 7, 10)

    def forward(self, x):
        x = self.conv1(x)
        x = self.conv2(x)
        x = x.view(x.size(0), -1)
        output = self.out(x)
        return output

cnn = CNN()

# Change in here
cnn.cuda()  # Moves all model parameters and buffers to the GPU

optimizer = torch.optim.Adam(cnn.parameters(), lr=LR)
loss_func = nn.CrossEntropyLoss()

for epoch in range(EPOCH):
    for step, (x, y) in enumerate(train_loader):
        # Change in here
        b_x = x.cuda()  # Tensor on GPU
        b_y = y.cuda()  # Tensor on GPU

        output = cnn(b_x)
        loss = loss_func(output, b_y)
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if step % 50 == 0:
            test_output = cnn(test_x)
            # Change in here
            pred_y = torch.max(test_output, 1)[1].cuda().data.squeeze()  # move the computation in GPU
            accuracy = torch.sum(pred_y == test_y).type(torch.FloatTensor) / test_y.size(0)
            print('Epoch:', epoch, '| train loss: %.4f' % loss.data.cpu().numpy(), '| test accuracy: %.2f' % accuracy)

test_output = cnn(test_x[:10])

# Change in here
pred_y = torch.max(test_output, 1)[1].cuda().data.squeeze()  # move the computation in GPU

print(pred_y, 'prediction number')
print(test_y[:10], 'real number')