python - IndexError : Dimension out of range - PyTorch dimension expected to be in range of [-1, 0]，但得到 1

Question

尽管已经有很多关于这个主题的答案，但在下面的例子中没有看到(摘自 https://gist.github.com/lirnli/c16ef186c75588e705d9864fb816a13c on Variational Recurrent Networks)是哪个输入和输出维度触发了错误。
试图在 torch.cat 中更改尺寸并抑制对 squeeze() 的调用，错误仍然存​​在，

<ipython-input-51-cdc928891ad7> in generate(self, hidden, temperature)
     56         x_sample = x = x_out.div(temperature).exp().multinomial(1).squeeze()
     57         x = self.phi_x(x)
---> 58         tc = torch.cat([x,z], dim=1)
     59 
     60         hidden_next = self.rnn(tc,hidden)

IndexError: Dimension out of range (expected to be in range of [-1, 0], but got 1)

因此如何塑造 x 中的尺寸和 z在 tc = torch.cat([x,z], dim=1) ?
注意代码如下，

import torch
from torch import nn, optim
from torch.autograd import Variable

class VRNNCell(nn.Module):
    def __init__(self):
        super(VRNNCell,self).__init__()
        self.phi_x = nn.Sequential(nn.Embedding(128,64), nn.Linear(64,64), nn.ELU())
        self.encoder = nn.Linear(128,64*2) # output hyperparameters
        self.phi_z = nn.Sequential(nn.Linear(64,64), nn.ELU())
        self.decoder = nn.Linear(128,128) # logits
        self.prior = nn.Linear(64,64*2) # output hyperparameters
        self.rnn = nn.GRUCell(128,64)

    def forward(self, x, hidden):
        x = self.phi_x(x)
        # 1. h => z
        z_prior = self.prior(hidden)
        # 2. x + h => z
        z_infer = self.encoder(torch.cat([x,hidden], dim=1))
        # sampling
        z = Variable(torch.randn(x.size(0),64))*z_infer[:,64:].exp()+z_infer[:,:64]
        z = self.phi_z(z)
        # 3. h + z => x
        x_out = self.decoder(torch.cat([hidden, z], dim=1))
        # 4. x + z => h
        hidden_next = self.rnn(torch.cat([x,z], dim=1),hidden)
        return x_out, hidden_next, z_prior, z_infer

    def calculate_loss(self, x, hidden):
        x_out, hidden_next, z_prior, z_infer = self.forward(x, hidden)
        # 1. logistic regression loss
        loss1 = nn.functional.cross_entropy(x_out, x) 
        # 2. KL Divergence between Multivariate Gaussian
        mu_infer, log_sigma_infer = z_infer[:,:64], z_infer[:,64:]
        mu_prior, log_sigma_prior = z_prior[:,:64], z_prior[:,64:]
        loss2 = (2*(log_sigma_infer-log_sigma_prior)).exp() \
                + ((mu_infer-mu_prior)/log_sigma_prior.exp())**2 \
                - 2*(log_sigma_infer-log_sigma_prior) - 1
        loss2 = 0.5*loss2.sum(dim=1).mean()
        return loss1, loss2, hidden_next
    
    def generate(self, hidden=None, temperature=None):
        if hidden is None:
            hidden=Variable(torch.zeros(1,64))
        if temperature is None:
            temperature = 0.8
        # 1. h => z
        z_prior = self.prior(hidden)
        # sampling
        z = Variable(torch.randn(z_prior.size(0),64))*z_prior[:,64:].exp()+z_prior[:,:64]
        z = self.phi_z(z)
        # 2. h + z => x
        x_out = self.decoder(torch.cat([hidden, z], dim=1))
        # sampling
        x_sample = x = x_out.div(temperature).exp().multinomial(1).squeeze()
        x = self.phi_x(x)
        # 3. x + z => h
        # hidden_next = self.rnn(torch.cat([x,z], dim=1),hidden)
        tc = torch.cat([x,z], dim=1)
        hidden_next = self.rnn(tc,hidden)
        return x_sample, hidden_next
    
    def generate_text(self, hidden=None,temperature=None, n=100):
        res = []
        hidden = None
        for _ in range(n):
            x_sample, hidden = self.generate(hidden,temperature)
            res.append(chr(x_sample.data[0]))
        return "".join(res)
        

# Test
net = VRNNCell()
x = Variable(torch.LongTensor([12,13,14]))
hidden = Variable(torch.rand(3,64))
output, hidden_next, z_infer, z_prior = net(x, hidden)
loss1, loss2, _ = net.calculate_loss(x, hidden)
loss1, loss2

hidden = Variable(torch.zeros(1,64))
net.generate_text()

Answer 1

错误

IndexError: Dimension out of range (expected to be in range of [-1, 0], but got 1)

意味着您正在尝试访问张量中不存在的索引。例如，以下代码将导致相同的 IndexError你正在经历。

# sample input tensors
In [210]: x = torch.arange(4)
In [211]: z = torch.arange(6)

# trying to concatenate along the second dimension 
# but the tensors have only one dimension (i.e., `0`).

In [212]: torch.cat([x, z], dim=1)

因此，克服这个问题的一种方法是在串联之前将张量提升到更高的维度，如果这是您需要的。

# promoting tensors to 2D before concatenation
In [216]: torch.cat([x[None, :], z[None, :]], dim=1)
Out[216]: tensor([[0, 1, 2, 3, 0, 1, 2, 3, 4, 5]])

因此，就您而言，您必须分析和了解 x 所需的形状。以便它可以与 z 连接沿着维度 1，然后是 tc作为输入传递给 self.rnn()连同 hidden .
据我所知， x[None, :] , z[None, :]应该管用。

成功训练的调试
您发布的代码是为 PyTorch 编写的 v0.4.1 .从那时起，PyTorch Python API 发生了很多变化，但代码没有更新。
以下是使代码成功运行和训练所需的更改。复制以下函数并将其粘贴到代码中的适当位置。

def generate(self, hidden=None, temperature=None):
        if hidden is None:
            hidden=Variable(torch.zeros(1,64))
        if temperature is None:
            temperature = 0.8
        # 1. h => z
        z_prior = self.prior(hidden)
        # sampling
        z = Variable(torch.randn(z_prior.size(0),64))*z_prior[:,64:].exp()+z_prior[:,:64]
        z = self.phi_z(z)
        # 2. h + z => x
        x_out = self.decoder(torch.cat([hidden, z], dim=1))
        # sampling
        x_sample = x = x_out.div(temperature).exp().multinomial(1).squeeze()
        x = self.phi_x(x)
        # 3. x + z => h
        x = x[None, ...]   # changed here
        xz = torch.cat([x,z], dim=1)  # changed here
        hidden_next = self.rnn(xz,hidden) # changed here
        return x_sample, hidden_next

def generate_text(self, hidden=None,temperature=None, n=100):
        res = []
        hidden = None
        for _ in range(n):
            x_sample, hidden = self.generate(hidden,temperature)
            res.append(chr(x_sample.data))      # changed here
        return "".join(res)

for epoch in range(max_epoch):
    batch = next(g)
    loss_seq = 0
    loss1_seq, loss2_seq = 0, 0
    optimizer.zero_grad()
    for x in batch:
        loss1, loss2, hidden = net.calculate_loss(Variable(x),hidden)
        loss1_seq += loss1.data  # changed here
        loss2_seq += loss2.data  # changed here
        loss_seq = loss_seq + loss1+loss2
    loss_seq.backward()
    optimizer.step()
    hidden.detach_()
    if epoch%100==0:
        print('>> epoch {}, loss {:12.4f}, decoder loss {:12.4f}, latent loss {:12.4f}'.format(epoch, loss_seq.data, loss1_seq, loss2_seq))  # changed here
        print(net.generate_text())
        print()

备注 :经过这些更改后，我最后的训练循环在 PyTorch v1.7.1 上没有任何错误。 .看看评论 # changed here了解变化。