lstm - torch.nn.LSTM 运行时错误

Question

我正在尝试实现“Livelinet:用于预测教育视频中的活力的多模式深度循环神经网络”中的结构。

为了简单说明，我将 10 秒音频剪辑分成 10 个 1 秒音频剪辑，并从该 1 秒音频剪辑中获取频谱图(图片)。然后我使用CNN从图片中获取表示向量，最终得到每个1秒视频片段的10个向量。

接下来，我将这 10 个向量输入 LSTM，但出现了一些错误。我的代码和错误回溯如下:

class AudioCNN(nn.Module):

def __init__(self):
    super(AudioCNN,self).__init__()
    self.features = alexnet.features
    self.features2 = nn.Sequential(*classifier)
    self.lstm = nn.LSTM(512, 256,2)
    self.classifier = nn.Linear(2*256,2)

def forward(self, x):
    x = self.features(x)
    print x.size()
    x = x.view(x.size(0),256*6*6)
    x = self.features2(x)
    x = x.view(10,1,512)
    h_0,c_0 = self.init_hidden()
    _, (_, _) = self.lstm(x,(h_0,c_0)) # x dim : 2 x 1 x 256
    assert False
    x = x.view(1,1,2*256)
    x = self.classifier(x)

    return x

def init_hidden(self):
    h_0 = torch.randn(2,1,256) #layer * batch * input_dim
    c_0 = torch.randn(2,1,256)
    return h_0, c_0

audiocnn = AudioCNN()
input = torch.randn(10,3,223,223)
input = Variable(input)
audiocnn(input)

错误:

RuntimeErrorTraceback (most recent call last)
<ipython-input-64-2913316dbb34> in <module>()
----> 1 audiocnn(input)

/home//local/lib/python2.7/site-packages/torch/nn/modules/module.pyc in __call__(self, *input, **kwargs)
    222         for hook in self._forward_pre_hooks.values():
    223             hook(self, input)
--> 224         result = self.forward(*input, **kwargs)
    225         for hook in self._forward_hooks.values():
    226             hook_result = hook(self, input, result)

<ipython-input-60-31881982cca9> in forward(self, x)
     15         x = x.view(10,1,512)
     16         h_0,c_0 = self.init_hidden()
---> 17         _, (_, _) = self.lstm(x,(h_0,c_0)) # x dim : 2 x 1 x 256
     18         assert False
     19         x = x.view(1,1,2*256)

/home/local/lib/python2.7/site-packages/torch/nn/modules/module.pyc in __call__(self, *input, **kwargs)
    222         for hook in self._forward_pre_hooks.values():
    223             hook(self, input)
--> 224         result = self.forward(*input, **kwargs)
    225         for hook in self._forward_hooks.values():
    226             hook_result = hook(self, input, result)

/home//local/lib/python2.7/site-packages/torch/nn/modules/rnn.pyc in forward(self, input, hx)
    160             flat_weight=flat_weight
    161         )
--> 162         output, hidden = func(input, self.all_weights, hx)
    163         if is_packed:
    164             output = PackedSequence(output, batch_sizes)

/home//local/lib/python2.7/site-packages/torch/nn/_functions/rnn.pyc in forward(input, *fargs, **fkwargs)
    349         else:
    350             func = AutogradRNN(*args, **kwargs)
--> 351         return func(input, *fargs, **fkwargs)
    352 
    353     return forward

/home//local/lib/python2.7/site-packages/torch/nn/_functions/rnn.pyc in forward(input, weight, hidden)
    242             input = input.transpose(0, 1)
    243 
--> 244         nexth, output = func(input, hidden, weight)
    245 
    246         if batch_first and batch_sizes is None:

/home//local/lib/python2.7/site-packages/torch/nn/_functions/rnn.pyc in forward(input, hidden, weight)
     82                 l = i * num_directions + j
     83 
---> 84                 hy, output = inner(input, hidden[l], weight[l])
     85                 next_hidden.append(hy)
     86                 all_output.append(output)

/home//local/lib/python2.7/site-packages/torch/nn/_functions/rnn.pyc in forward(input, hidden, weight)
    111         steps = range(input.size(0) - 1, -1, -1) if reverse else range(input.size(0))
    112         for i in steps:
--> 113             hidden = inner(input[i], hidden, *weight)
    114             # hack to handle LSTM
    115             output.append(hidden[0] if isinstance(hidden, tuple) else hidden)

/home//local/lib/python2.7/site-packages/torch/nn/_functions/rnn.pyc in LSTMCell(input, hidden, w_ih, w_hh, b_ih, b_hh)
     29 
     30     hx, cx = hidden
---> 31     gates = F.linear(input, w_ih, b_ih) + F.linear(hx, w_hh, b_hh)
     32 
     33     ingate, forgetgate, cellgate, outgate = gates.chunk(4, 1)

/home//local/lib/python2.7/site-packages/torch/nn/functional.pyc in linear(input, weight, bias)
    551     if input.dim() == 2 and bias is not None:
    552         # fused op is marginally faster
--> 553         return torch.addmm(bias, input, weight.t())
    554 
    555     output = input.matmul(weight.t())

/home//local/lib/python2.7/site-packages/torch/autograd/variable.pyc in addmm(cls, *args)
    922         @classmethod
    923         def addmm(cls, *args):
--> 924             return cls._blas(Addmm, args, False)
    925 
    926         @classmethod

/home//local/lib/python2.7/site-packages/torch/autograd/variable.pyc in _blas(cls, args, inplace)
    918             else:
    919                 tensors = args
--> 920             return cls.apply(*(tensors + (alpha, beta, inplace)))
    921 
    922         @classmethod

RuntimeError: save_for_backward can only save input or output tensors, but argument 0 doesn't satisfy this condition

Answer 1

错误信息

RuntimeError: save_for_backward can only save input or output tensors, but argument 0 doesn't satisfy this condition

通常表示您正在传递张量或其他无法将历史记录作为模块的输入存储的东西。在您的情况下，您的问题是您在 init_hidden() 而不是 Variable 实例中返回张量。因此，当 LSTM 运行时，它无法计算隐藏层的梯度，因为其初始输入不是反向传播图的一部分。

解决方案:

def init_hidden(self):
    h_0 = torch.randn(2,1,256) #layer * batch * input_dim
    c_0 = torch.randn(2,1,256)
    return Variable(h_0), Variable(c_0)

均值 0 和方差 1 作为 LSTM 隐藏状态的初始值也可能没有帮助。理想情况下，您也可以使初始状态可训练，例如:

h_0 = torch.zeros(2,1,256) # layer * batch * input_dim
c_0 = torch.zeros(2,1,256)
h_0_param = torch.nn.Parameter(h_0)
c_0_param = torch.nn.Parameter(c_0)

def init_hidden(self):
    return h_0_param, c_0_param

在这种情况下，网络可以了解最适合的初始状态。请注意，在这种情况下，无需将 h_0_param 包装在 Variable 中，因为 Parameter 本质上是一个 Variable与 require_grad=True。