IndexError：维度超出范围 - PyTorch 维度预计在 [-1, 0] 范围内，但得到 1 成功训练的调试

如何解决IndexError：维度超出范围 - PyTorch 维度预计在 [-1, 0] 范围内，但得到 1 成功训练的调试

尽管已经有很多关于这个主题的答案，但在下面的示例（从变分循环网络上的 https://gist.github.com/lirnli/c16ef186c75588e705d9864fb816a13c 摘录）中没有看到哪个输入和输出维度触发了错误。

尝试更改 torch.cat 中的维度并抑制对 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中的维度和z中的tc = torch.cat([x,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,nn.ELU())
        self.encoder = nn.Linear(128,64*2) # output hyperparameters
        self.phi_z = nn.Sequential(nn.Linear(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,dim=1))
        # 4. x + z => h
        hidden_next = self.rnn(torch.cat([x,dim=1),hidden)
        return x_out,hidden_next,z_prior,z_infer

    def calculate_loss(self,hidden):
        x_out,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[:,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,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,hidden)
        tc = torch.cat([x,dim=1)
        hidden_next = self.rnn(tc,hidden)
        return x_sample,hidden_next
    
    def generate_text(self,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,z_infer,z_prior = net(x,hidden)
loss1,_ = net.calculate_loss(x,loss2

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

解决方法

错误

IndexError: Dimension out of range（预计在 [-1,0] 范围内，但得到 1）

表示您正在尝试访问张量中不存在的索引。例如，以下代码会导致您遇到相同的 IndexError。

# 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，如果这是您需要的话。

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

因此，在您的情况下，您必须分析和了解 x 需要什么形状，以便它可以沿维度 1 与 z 连接，然后通过 tc作为 self.rnn() 和 hidden 的输入。

据我所知， x[None,:] 、 z[None,:] 应该可以工作。

---

成功训练的调试

您发布的代码是为 PyTorch v0.4.1 编写的。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,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,dim=1)  # changed here
        hidden_next = self.rnn(xz,hidden) # changed here
        return x_sample,hidden_next

---

def generate_text(self,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()

---

注意：在这些更改之后，我最后的训练循环在 PyTorch v1.7.1 上没有任何错误。查看带有 # changed here 的评论以了解更改。