目录
1.写在前面
在 GPU 训练可以大幅提升运算速度. 而且 Torch 也有一套很好的 GPU 运算体系. 但是要强调的是:
- 你的电脑里有合适的 GPU 显卡(NVIDIA), 且支持 CUDA 模块. 请在NVIDIA官网查询
- 必须安装 GPU 版的 Torch, 点击这里查看如何安装
2.用 GPU 训练 CNN
这份 GPU 的代码是依据之前CNN的代码修改的. 大概修改的地方包括将数据的形式变成 GPU 能读的形式, 然后将 CNN 也变成 GPU 能读的形式. 做法就是在后面加上 .cuda()
, 很简单.
...
test_data = torchvision.datasets.MNIST(root='./mnist/', train=False)
# !!!!!!!! 修改 test data 形式 !!!!!!!!! #
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()
再来把我们的 CNN 参数也变成 GPU 兼容形式.
class CNN(nn.Module):
...
cnn = CNN()
# !!!!!!!! 转换 cnn 去 CUDA !!!!!!!!! #
cnn.cuda() # Moves all model parameters and buffers to the GPU.
然后就是在 train 的时候, 将每次的training data 变成 GPU 形式. + .cuda()
for epoch ..:
for step, ...:
# !!!!!!!! 这里有修改 !!!!!!!!! #
b_x = x.cuda() # Tensor on GPU
b_y = y.cuda() # Tensor on GPU
...
if step % 50 == 0:
test_output = cnn(test_x)
# !!!!!!!! 这里有修改 !!!!!!!!! #
pred_y = torch.max(test_output, 1)[1].cuda().data.squeeze() # 将操作放去 GPU
accuracy = torch.sum(pred_y == test_y) / test_y.size(0)
...
test_output = cnn(test_x[:10])
# !!!!!!!! 这里有修改 !!!!!!!!! #
pred_y = torch.max(test_output, 1)[1].cuda().data.squeeze() # 将操作放去 GPU
...
print(test_y[:10], 'real number')
3.完整代码演示
import torch
import torch.nn as nn
import torch.utils.data as Data
import torchvision
# torch.manual_seed(1)
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 # 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 # move the computation in GPU
print(pred_y, 'prediction number')
print(test_y[:10], 'real number')
4.转移至 CPU
如果你有些计算还是需要在 CPU 上进行的话呢, 比如 plt
的可视化, 我们需要将这些计算或者数据转移至 CPU.
cpu_data = gpu_data.cpu()