实例化 class 报错： NotImplementedError

这是我定义的模型

class CNN(nn.Module): def __init__(self): super(CNNcpl, self).__init__() self.conv1 = nn.Conv1d(20, 64, 5) self.pool1 = nn.AvgPool1d(4, 4) self.conv2 = nn.Conv1d(64, 128, 5) self.pool2 = nn.AvgPool1d(4, 4) self.conv3 = nn.Conv1d(128, 256, 5) self.pool3 = nn.AvgPool1d(4, 4) self.fc1 = nn.Linear(256*29, 64) self.fc2 = nn.Linear(64, 2) def forword(self, x): x = self.pool1(F.relu(self.conv1(x))) x = self.pool2(F.relu(self.conv2(x))) x = self.pool3(F.relu(self.conv3(x))) x = x.reshape(256*29) x = F.relu(self.fc1(x)) x = F.softmax(self.fc2(x), dim = 1 ) return x 

当我运行下面的代码时

cnn = CNN() cnn(x) # x 是一个 20*2000 的 tensor 

报错

~/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs) 1100 if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks 1101 or _global_forward_hooks or _global_forward_pre_hooks): -> 1102 return forward_call(*input, **kwargs) 1103 # Do not call functions when jit is used 1104 full_backward_hooks, non_full_backward_hooks = [], [] ~/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py in _forward_unimplemented(self, *input) 199 registered hooks while the latter silently ignores them. 200 """ --> 201 raise NotImplementedError 202 203 NotImplementedError: 

这个类定义的有问题吗？我刚刚接触深度学习和 Python 不久，请各位大佬指教。