TypeError: linear(): argument 'input' (position 1) must be Tensor, not Dropout pytorch

Question

我在 torch 中有一个自动编码器，我想在解码器中添加一个 dropout 层。（我不确定应该在哪里添加辍学）。在下面，我添加了一个输入数据和 decorder 函数的小例子。老实说，我不知道该怎么做才能修复错误。你能帮我吗？

d_input   = torch.nn.Conv1d(1, 33, 10, stride=10)
mu_d      = nn.Linear(1485, 28)
log_var_d = nn.Linear(1485, 28)

def decode(self, z, y):

        indata     = torch.cat((z,y), 1) #shape: [batchsize, 451
        indata     = torch.reshape(indata, (-1, 1, 451))
        hidden     = torch.flatten(relu(d_input(indata)), start_dim = 1) #shape [batch_size, 1485]
        hidden     = nn.Dropout(p=0.5) 
        par_mu     = self.mu_d(hidden)
        par_log_var= self.log_var_d(hidden)
        return par_mu, par_log_var

Answer 1

torch.nn.Dropout 是一个模块。您需要先实例化它，然后才能通过它传递变量。

d_input   = torch.nn.Conv1d(1, 33, 10, stride=10)
mu_d      = nn.Linear(1485, 28)
log_var_d = nn.Linear(1485, 28)
dropout = nn.Dropout(p=0.5)

def decode(self, z, y):

        indata     = torch.cat((z,y), 1) #shape: [batchsize, 451
        indata     = torch.reshape(indata, (-1, 1, 451))
        hidden     = torch.flatten(relu(d_input(indata)), start_dim = 1) #shape [batch_size, 1485]
        hidden     = dropout(hidden)
        par_mu     = self.mu_d(hidden)
        par_log_var= self.log_var_d(hidden)
        return par_mu, par_log_var

TypeError: linear(): argument 'input' (position 1) must be Tensor, not Dropout pytorch

TypeError: linear(): argument 'input' (position 1) must be Tensor, not Dropout pytorch

python

machine-learning

deep-learning

torch