pytorch DataParallel 多GPU使用

今天药忘吃喽~ 2023-05-29 03:30 22阅读 0赞

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还是使用CPU， 设置device

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

其次，我们需要制作一个模型实例，并检查是否有多个GPU。 如果我们有多个GPU，则可以使用nn.DataParallel包装模型。 然后我们可以通过model.to（device）将我们的模型放在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)

仅调用my\_tensor.to（device）即可在GPU上返回my\_tensor的新副本，而不是重写my\_tensor。 您需要将其分配给新的张量，并在GPU上使用该张量。

链接：

# [OPTIONAL: DATA PARALLELISM][OPTIONAL_ DATA PARALLELISM] #

[OPTIONAL_ DATA PARALLELISM]: https://pytorch.org/tutorials/beginner/blitz/data_parallel_tutorial.html