python - 转移到 GPU 时张量类型不匹配

Question

尝试将我的网络和张量移动到 GPU 时出现以下错误。我检查过网络参数是否已移至 GPU，并检查每批处理的张量并移动它们(如果它们尚未在 GPU 上)。但我仍然遇到这个问题，说张量类型不匹配——一个是 torch.cuda.FloatTensor，另一个是 torch.FloatTensor？有人能告诉我我做错了什么吗？谢谢。

我的代码:

class Train():
  def __init__(self, network, training, address):
    self.network    = network
    self.address    = address
    self.batch_size = training['batch_size']
    self.iterations = training['iterations']
    self.samples    = training['samples']
    self.data       = training['data']
    self.lr         = training['lr']
    self.noisy_lr   = training['nlr']
    self.cuda       = training['cuda']
    self.save       = training['save']
    self.scale      = training['scale']
    self.limit      = training['limit']
    self.replace    = training['strategy']
    self.optimizer  = torch.optim.Adam(self.network.parameters(), lr=self.lr)

  def tensor_to_Variable(self, t):
    if next(self.network.parameters()).is_cuda and not t.is_cuda:
        t = t.cuda()

    return Variable(t)

  def train(self):
    if self.cuda:
        self.network.cuda()
    dh = DataHandler(self.data)
    loss_fn = torch.nn.MSELoss()
    losses    = []
    validate  = []
    val_size  = 100
    val_diff  = 1
    total_val = float(val_size * self.batch_size)
    hypos     = []
    labels    = []

    # training loop
    for i in range(self.iterations):
        x, y = dh.get_batch(self.batch_size)
        x = self.tensor_to_Variable(x)
        y = self.tensor_to_Variable(y)

        self.optimizer.zero_grad()
        hypo = self.network(x)
        loss = loss_fn(hypo, y)
        loss.backward()
        self.optimizer.step()


class Feedforward(nn.Module):
   def __init__(self, topology):
    super(Feedforward, self).__init__()
    self.input_dim     = topology['features']
    self.num_hidden    = topology['hidden_layers']
    self.hidden_dim    = topology['hidden_dim']
    self.output_dim    = topology['output_dim']
    self.input_layer   = nn.Linear(self.input_dim, self.hidden_dim)
    self.hidden_layer  = nn.Linear(self.hidden_dim, self.hidden_dim)
    self.output_layer  = nn.Linear(self.hidden_dim, self.output_dim)
    self.dropout_layer = nn.Dropout(p=0.2)


def forward(self, x):
    batch_size = x.size()[0]
    feat_size  = x.size()[1]
    input_size = batch_size * feat_size

    self.input_layer = nn.Linear(input_size, self.hidden_dim)
    hidden = self.input_layer(x.view(1, input_size)).clamp(min=0)

    for _ in range(self.num_hidden):
        hidden = self.dropout_layer(F.relu(self.hidden_layer(hidden)))

    output_size = batch_size * self.output_dim
    self.output_layer = nn.Linear(self.hidden_dim, output_size)
    return self.output_layer(hidden).view(output_size)

错误:

Traceback (most recent call last):
  File "/media/project/train.py", line 78, in train
    hypo = self.network(x)

 * (torch.cuda.FloatTensor mat1, torch.cuda.FloatTensor mat2)
 * (torch.cuda.sparse.FloatTensor mat1, torch.cuda.FloatTensor mat2)
 * (float beta, torch.cuda.FloatTensor mat1, torch.cuda.FloatTensor mat2)
 * (float alpha, torch.cuda.FloatTensor mat1, torch.cuda.FloatTensor mat2)
 * (float beta, torch.cuda.sparse.FloatTensor mat1, torch.cuda.FloatTensor mat2)
 * (float alpha, torch.cuda.sparse.FloatTensor mat1, torch.cuda.FloatTensor mat2)
 * (float beta, float alpha, torch.cuda.FloatTensor mat1, torch.cuda.FloatTensor mat2)
      didn't match because some of the arguments have invalid types: (int, int, torch.cuda.FloatTensor, torch.FloatTensor)
 * (float beta, float alpha, torch.cuda.sparse.FloatTensor mat1, torch.cuda.FloatTensor mat2)
      didn't match because some of the arguments have invalid types: (int, int, torch.cuda.FloatTensor, torch.FloatTensor)

堆栈跟踪:

Traceback (most recent call last):
File "smpl.py", line 90, in <module>
main()
File "smpl.py", line 80, in main
trainer.train()
File "/media/mpl/temp/train.py", line 82, in train
hypo = self.network(x)
File "/usr/local/lib/python2.7/dist-packages/torch/nn/modules/module.py", line 206, in call
result = self.forward(input, **kwargs)
File "model/network.py", line 35, in forward
hidden = self.input_layer(x.view(1, input_size)).clamp(min=0)
File "/usr/local/lib/python2.7/dist-packages/torch/nn/modules/module.py", line 206, in call
result = self.forward(input, *kwargs)
File "/usr/local/lib/python2.7/dist-packages/torch/nn/modules/linear.py", line 54, in forward
return self.backend.Linear()(input, self.weight, self.bias)
File "/usr/local/lib/python2.7/dist-packages/torch/nn/_functions/linear.py", line 10, in forward
output.addmm(0, 1, input, weight.t())
TypeError: addmm_ received an invalid combination of arguments - got (int, int, torch.cuda.FloatTensor, torch.FloatTensor), but expected one of: (torch.cuda.FloatTensor mat1, torch.cuda.FloatTensor mat2)
(torch.cuda.sparse.FloatTensor mat1, torch.cuda.FloatTensor mat2) (float beta, torch.cuda.FloatTensor mat1, torch.cuda.FloatTensor mat2)
(float alpha, torch.cuda.FloatTensor mat1, torch.cuda.FloatTensor mat2) (float beta, torch.cuda.sparse.FloatTensor mat1, torch.cuda.FloatTensor mat2)
(float alpha, torch.cuda.sparse.FloatTensor mat1, torch.cuda.FloatTensor mat2) (float beta, float alpha, torch.cuda.FloatTensor mat1, torch.cuda.FloatTensor mat2)
didn't match because some of the arguments have invalid types: (int, int, torch.cuda.FloatTensor, torch.FloatTensor)
* (float beta, float alpha, torch.cuda.sparse.FloatTensor mat1, torch.cuda.FloatTensor mat2)
didn't match because some of the arguments have invalid types: (int, int, torch.cuda.FloatTensor, torch.FloatTensor

Answer 1

发生这种情况是因为您在 forward() 函数中重新初始化 self.input_layer。

调用 self.network.cuda() 将所有模型参数移动到 cuda 中。这意味着您在创建 FeedForward 对象时初始化的所有层都将移动到 cuda 内存中。但是，当您在 forward() 函数中重新初始化 self.input_layer 时，您会在 cpu 而不是 gpu 中初始化该层的参数。 self.output_layer 也是如此。