0

我正在研究 GRU，当我尝试进行预测时，我收到一个错误，表明我需要为 forward() 定义 h。在谷歌搜索和搜索堆栈溢出数小时后，我尝试了几件事并失去了耐心。

这是课程：

class GRUNet(nn.Module):
    def __init__(self, input_dim, hidden_dim, output_dim, n_layers, drop_prob = 0.2):
        super(GRUNet, self).__init__()
        self.hidden_dim = hidden_dim
        self.n_layers = n_layers
        
        self.gru = nn.GRU(input_dim, hidden_dim, n_layers, batch_first=True, dropout=drop_prob)
        self.fc = nn.Linear(hidden_dim, output_dim)
        self.relu = nn.ReLU()
    
    def forward(self, x, h):
        out, h = self.gru(x,h)
        out = self.fc(self.relu(out[:,-1]))
        return out, h
    
    def init_hidden(self, batch_size):
        weight = next(self.parameters()).data
        hidden = weight.new(self.n_layers, batch_size, self.hidden_dim).zero_().to(device)
        return hidden

然后这是我加载模型并尝试进行预测的地方。这两个都在同一个脚本中。

inputs = np.load('.//Pred//input_list.npy')  
print(inputs.ndim, inputs.shape)
Gmodel = GRUNet(24,256,1,2)
Gmodel = torch.load('.//GRU//GRU_1028_48.pkl')
Gmodel.eval()
pred = Gmodel(inputs)

没有 Gmodel 的任何其他参数，我得到以下信息：

Traceback (most recent call last):
  File ".\grunet.py", line 136, in <module>
    pred = Gmodel(inputs)
  File "C:\Users\ryang\Anaconda-3\envs\tf-gpu\lib\site-packages\torch\nn\modules\module.py", line 547, in __call__
    result = self.forward(*input, **kwargs)
TypeError: forward() missing 1 required positional argument: 'h'
4

1 回答 1

0

您还需要提供隐藏状态，通常最初都是零或简单None！
那就是您需要明确提供这样的一个：

hidden_state = torch.zeros(size=(num_layers*direction, batch_size, hidden_dim)).to(device)
pred = Gmodel(inputs, hidden_state)

或者干脆做：

hidden_state = None 
pred = Gmodel(inputs, hidden_state)
于 2020-10-29T08:58:07.067 回答