PyTorch-GPU加速實(shí)例

更新時間：2020年06月23日 09:37:11 作者：samylee

這篇文章主要介紹了PyTorch-GPU加速實(shí)例，具有很好的參考價值，希望對大家有所幫助。一起跟隨小編過來看看吧

硬件：NVIDIA-GTX1080

軟件：Windows7、python3.6.5、pytorch-gpu-0.4.1

一、基礎(chǔ)知識

將數(shù)據(jù)和網(wǎng)絡(luò)都推到GPU，接上.cuda()

二、代碼展示

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, '| 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')

三、結(jié)果展示

補(bǔ)充知識：pytorch使用gpu對網(wǎng)絡(luò)計(jì)算進(jìn)行加速

1.基本要求

你的電腦里面有合適的GPU顯卡（NVIDA）,并且需要支持CUDA模塊

你必須安裝GPU版的Torch，（詳細(xì)安裝方法請移步pytorch官網(wǎng)）

2.使用GPU訓(xùn)練CNN

利用pytorch使用GPU進(jìn)行加速方法主要就是將數(shù)據(jù)的形式變成GPU能讀的形式，然后將CNN也變成GPU能讀的形式，具體辦法就是在后面加上.cuda()。

例如：

#如何檢查自己電腦是否支持cuda
print torch.cuda.is_available()
# 返回True代表支持，F(xiàn)alse代表不支持
'''
注意在進(jìn)行某種運(yùn)算的時候使用.cuda()
'''
test_data=test_data.test_labels[:2000].cuda()
'''
對于CNN與損失函數(shù)利用cuda加速
'''
class CNN(nn.Module):
 ...
cnn=CNN()
cnn.cuda()
loss_f = t.nn.CrossEntropyLoss()
loss_f = loss_f.cuda()

而在train時，對于train_data訓(xùn)練過程進(jìn)行GPU加速。也同樣+.cuda()。

for epoch ..:
 for step, ...:
 1
'''
若你的train_data在訓(xùn)練時需要進(jìn)行操作
若沒有其他操作僅僅只利用cnn()則無需另加.cuda()
'''
#eg
 train_data = torch.max(teain_data, 1)[1].cuda()

補(bǔ)充：取出數(shù)據(jù)需要從GPU切換到CPU上進(jìn)行操作

eg：