天天看點

pytorch DataParallel 多GPU使用OPTIONAL: DATA PARALLELISM

import torch
import torch.nn as nn
from torch.utils.data import Dataset, DataLoader


# Parameters and DataLoaders
input_size = 5
output_size = 2

batch_size = 30
data_size = 100

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print(device)


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):
    # Our model

    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(), "GPUs!")
  # dim = 0 [30, xxx] -> [10, ...], [10, ...], [10, ...] on 3 GPUs
  model = nn.DataParallel(model)

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())

           

核心:

首先,确定使用GPU還是使用CPU, 設定device

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
           

其次,我們需要制作一個模型執行個體,并檢查是否有多個GPU。 如果我們有多個GPU,則可以使用nn.DataParallel包裝模型。 然後我們可以通過model.to(device)将我們的模型放在GPU上

model = Model(input_size, output_size)
if torch.cuda.device_count() > 1:
  print("Let's use", torch.cuda.device_count(), "GPUs!")
  # dim = 0 [30, xxx] -> [10, ...], [10, ...], [10, ...] on 3 GPUs
  model = nn.DataParallel(model)

model.to(device)
           

注意:

mytensor = my_tensor.to(device)
           

僅調用my_tensor.to(device)即可在GPU上傳回my_tensor的新副本,而不是重寫my_tensor。 您需要将其配置設定給新的張量,并在GPU上使用該張量。

連結:

OPTIONAL: DATA PARALLELISM