GPU并行计算,可以将数据分割分发给不同的GPU,每个GPU计算之后再将结果汇总返回
这里面我们做一个实验
1 定义一些参数
input_size = 5
output_size = 2
batch_size = 30
data_size = 100
device = torch.device('cuda:0' if torch.cuda.is_available() else "cpu")
2 自己做一个数据集
class RandomDataset(Dataset):
def __init__(self,size,length):
self.len = length
self.data = torch.randn(length,size)
def __getitem__(self, index):
return self.data[index]
def __len__(self):
return self.len
rand_loader = DataLoader(dataset=RandomDataset(input_size,data_size),
batch_size=batch_size,shuffle=True)
3 创建模型
class Model(nn.Module):
def __init__(self,input_size,output_size):
super(Model,self).__init__()
self.fc = nn.Linear(input_size,output_size)
def forward(self,input):
output = self.fc(input)
print("\tIn Model: input size",input.size(),"output size",output.size())
return output
4 开始训练
使用nn.DataParallel封装模型然后放在GPU上model.to(device)
每次训练时先将数据放到GPU data.to(device)再训练
model = Model(input_size,output_size)
if(torch.cuda.device_count() > 1):
print("Let's use",torch.cuda.device_count(),"CPUs!")
model = nn.DataParallel(model)
else:
print("can not use parallel")
model.to(device)
for data in rand_loader:
input = data.to(device)
output = model(input)
print("Outside:input size",input.size(),"output size",output.size())
5 完整代码
import torch
import torch.nn as nn
from torch.utils.data import Dataset,DataLoader
input_size = 5
output_size = 2
batch_size = 30
data_size = 100
device = torch.device('cuda:0' if torch.cuda.is_available() else "cpu")
class RandomDataset(Dataset):
def __init__(self,size,length):
self.len = length
self.data = torch.randn(length,size)
def __getitem__(self, index):
return self.data[index]
def __len__(self):
return self.len
rand_loader = DataLoader(dataset=RandomDataset(input_size,data_size),
batch_size=batch_size,shuffle=True)
class Model(nn.Module):
def __init__(self,input_size,output_size):
super(Model,self).__init__()
self.fc = nn.Linear(input_size,output_size)
def forward(self,input):
output = self.fc(input)
print("\tIn Model: input size",input.size(),"output size",output.size())
return output
model = Model(input_size,output_size)
if(torch.cuda.device_count() > 1):
print("Let's use",torch.cuda.device_count(),"CPUs!")
model = nn.DataParallel(model)
else:
print("can not use parallel")
model.to(device)
for data in rand_loader:
input = data.to(device)
output = model(input)
print("Outside:input size",input.size(),"output size",output.size())