Pytorch 如何将数据_并行模型移动到特定的cuda设备？

我目前需要通过在特定的cuda设备上设置来使用预训练模型。预训练模型定义如下：

DataParallel(
  (module): MobileFaceNet(
    (conv1): Conv_block(
      (conv): Conv2d(3, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
      (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (prelu): PReLU(num_parameters=64)
    )
    (conv2_dw): Conv_block(
      (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=64, bias=False)
      (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (prelu): PReLU(num_parameters=64)
    )
    (conv_23): Depth_Wise(
      (conv): Conv_block(
        (conv): Conv2d(64, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (prelu): PReLU(num_parameters=128)
      )
      (conv_dw): Conv_block(
        (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=128, bias=False)
        (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (prelu): PReLU(num_parameters=128)
      )
      (project): Linear_block(
        (conv): Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (conv_3): Residual(
      (model): Sequential(
        (0): Depth_Wise(
          (conv): Conv_block(
            (conv): Conv2d(64, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (prelu): PReLU(num_parameters=128)
          )
          (conv_dw): Conv_block(
            (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=128, bias=False)
            (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (prelu): PReLU(num_parameters=128)
          )
          (project): Linear_block(
            (conv): Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          )
        )
        (1): Depth_Wise(
          (conv): Conv_block(
            (conv): Conv2d(64, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (prelu): PReLU(num_parameters=128)
          )
          (conv_dw): Conv_block(
            (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=128, bias=False)
            (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (prelu): PReLU(num_parameters=128)
          )
          (project): Linear_block(
            (conv): Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          )
        )
        (2): Depth_Wise(
          (conv): Conv_block(
            (conv): Conv2d(64, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (prelu): PReLU(num_parameters=128)
          )
          (conv_dw): Conv_block(
            (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=128, bias=False)
            (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (prelu): PReLU(num_parameters=128)
          )
          (project): Linear_block(
            (conv): Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          )
        )
        (3): Depth_Wise(
          (conv): Conv_block(
            (conv): Conv2d(64, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (prelu): PReLU(num_parameters=128)
          )
          (conv_dw): Conv_block(
            (conv): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=128, bias=False)
            (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (prelu): PReLU(num_parameters=128)
          )
          (project): Linear_block(
            (conv): Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          )
        )
      )
    )
    (conv_34): Depth_Wise(
      (conv): Conv_block(
        (conv): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (prelu): PReLU(num_parameters=256)
      )
      (conv_dw): Conv_block(
        (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=256, bias=False)
        (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (prelu): PReLU(num_parameters=256)
      )
      (project): Linear_block(
        (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (conv_4): Residual(
      (model): Sequential(
        (0): Depth_Wise(
          (conv): Conv_block(
            (conv): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (prelu): PReLU(num_parameters=256)
          )
          (conv_dw): Conv_block(
            (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=256, bias=False)
            (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (prelu): PReLU(num_parameters=256)
          )
          (project): Linear_block(
            (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          )
        )
        (1): Depth_Wise(
          (conv): Conv_block(
            (conv): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (prelu): PReLU(num_parameters=256)
          )
          (conv_dw): Conv_block(
            (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=256, bias=False)
            (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (prelu): PReLU(num_parameters=256)
          )
          (project): Linear_block(
            (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          )
        )
        (2): Depth_Wise(
          (conv): Conv_block(
            (conv): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (prelu): PReLU(num_parameters=256)
          )
          (conv_dw): Conv_block(
            (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=256, bias=False)
            (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (prelu): PReLU(num_parameters=256)
          )
          (project): Linear_block(
            (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          )
        )
        (3): Depth_Wise(
          (conv): Conv_block(
            (conv): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (prelu): PReLU(num_parameters=256)
          )
          (conv_dw): Conv_block(
            (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=256, bias=False)
            (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (prelu): PReLU(num_parameters=256)
          )
          (project): Linear_block(
            (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          )
        )
        (4): Depth_Wise(
          (conv): Conv_block(
            (conv): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (prelu): PReLU(num_parameters=256)
          )
          (conv_dw): Conv_block(
            (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=256, bias=False)
            (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (prelu): PReLU(num_parameters=256)
          )
          (project): Linear_block(
            (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          )
        )
        (5): Depth_Wise(
          (conv): Conv_block(
            (conv): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (prelu): PReLU(num_parameters=256)
          )
          (conv_dw): Conv_block(
            (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=256, bias=False)
            (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (prelu): PReLU(num_parameters=256)
          )
          (project): Linear_block(
            (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          )
        )
      )
    )
    (conv_45): Depth_Wise(
      (conv): Conv_block(
        (conv): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (prelu): PReLU(num_parameters=512)
      )
      (conv_dw): Conv_block(
        (conv): Conv2d(512, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), groups=512, bias=False)
        (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (prelu): PReLU(num_parameters=512)
      )
      (project): Linear_block(
        (conv): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (conv_5): Residual(
      (model): Sequential(
        (0): Depth_Wise(
          (conv): Conv_block(
            (conv): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (prelu): PReLU(num_parameters=256)
          )
          (conv_dw): Conv_block(
            (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=256, bias=False)
            (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (prelu): PReLU(num_parameters=256)
          )
          (project): Linear_block(
            (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          )
        )
        (1): Depth_Wise(
          (conv): Conv_block(
            (conv): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (prelu): PReLU(num_parameters=256)
          )
          (conv_dw): Conv_block(
            (conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=256, bias=False)
            (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (prelu): PReLU(num_parameters=256)
          )
          (project): Linear_block(
            (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
            (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          )
        )
      )
    )
    (conv_6_sep): Conv_block(
      (conv): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (prelu): PReLU(num_parameters=512)
    )
    (conv_6_dw): Linear_block(
      (conv): Conv2d(512, 512, kernel_size=(7, 7), stride=(1, 1), groups=512, bias=False)
      (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (conv_6_flatten): Flatten()
    (linear): Linear(in_features=512, out_features=512, bias=False)
    (bn): BatchNorm1d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  )
)

如果我按惯例宣布

model.to(device)

当设备位于cuda:1上时，则在转发时出错：

model(imgs)

RuntimeError: module must have its parameters and buffers on device cuda:0 (device_ids[0]) but found one of them on device: cuda:1

我认为这是因为该模型之前在pytorch中使用数据并行UTIL进行了训练

---

如何正确地将模型设置为我特别想要的设备？

您应该首先从

DataParallel

中获取神经网络

假设您的

DataParallel

命名为

model

，您可以执行以下操作：

device = torch.device("cuda:1")
module = model.module.to(device)

---

您应该首先从

DataParallel

中获取神经网络

假设您的

DataParallel

命名为

model

，您可以执行以下操作：

device = torch.device("cuda:1")
module = model.module.to(device)