使用CIFAR-100训练PyTorch模型触发IndexError报错求助

问题描述 #

在CPU环境下基于PyTorch官方CIFAR-10教程修改代码，切换到CIFAR-100数据集训练时，执行loss = criterion(outputs, labels)触发IndexError: Target 32 is out of bounds（报错目标值每次不同），但使用CIFAR-10训练时一切正常，环境为Python 3.9+最新版PyTorch。

报错栈信息 #

Traceback (most recent call last):
  File "recog.py", line 68, in <module>
    loss = criterion(outputs, labels)
  File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 1102, in _call_impl
    return forward_call(*input, **kwargs)
  File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/loss.py", line 1152, in forward
    label_smoothing=self.label_smoothing)
  File "/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py", line 2846, in cross_entropy
    return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index, label_smoothing)
IndexError: Target 32 is out of bounds.

用户代码 #

import torch
import torchvision
import torchvision.transforms as transforms

transform = transforms.Compose(
    [transforms.ToTensor(),
     transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])

batch_size = 4

trainset = torchvision.datasets.CIFAR100(root='./dataone', train=True,
                                        download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=batch_size,
                                          shuffle=True, num_workers=2)

testset = torchvision.datasets.CIFAR100(root='./dataone', train=False,
                                       download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=batch_size,
                                         shuffle=False, num_workers=2)
classes = ('aquatic mammals','fish','flowers','food containers','fruit and vegetables','household electrical devices','household furniture','insects','large carnivores','large man-made outdoor things','large natural outdoor scenes','large omnivores and herbivores','medium-sized mammals','non-insect invertebrates','people','reptiles','small mammals','trees','vehicles 1','vehicles 2')

import torch.nn as nn
import torch.nn.functional as F


class Net(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(3, 6, 5)
        self.pool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1 = nn.Linear(16 * 5 * 5, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = torch.flatten(x, 1) # flatten all dimensions except batch
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x


net = Net()

import torch.optim as optim

#criterion = nn.CrossEntropyLoss()
#optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)import torch.optim as optim

criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)

for epoch in range(2):  # loop over the dataset multiple times

    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
        # get the inputs; data is a list of [inputs, labels]
        inputs, labels = data

        # zero the parameter gradients
        optimizer.zero_grad()

        # forward + backward + optimize
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        # print statistics
        running_loss += loss.item()
        if i % 2000 == 1999:    # print every 2000 mini-batches
            print(f'[{epoch + 1}, {i + 1:5d}] loss: {running_loss / 2000:.3f}')
            running_loss = 0.0

print('Finished Training')

问题原因 #

CIFAR-100包含100个细分类别，标签范围是0-99，但模型最后一层全连接层fc3的输出维度仍设置为10（对应CIFAR-10的10个类别）。当CrossEntropyLoss计算损失时，模型输出仅能对应0-9的标签，而CIFAR-100的标签（如32）超出该范围，因此触发IndexError。

解决方案 #

修改模型最后一层全连接层的输出维度为100，使其与CIFAR-100的类别数匹配：

修改后的模型代码 #

class Net(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(3, 6, 5)
        self.pool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1 = nn.Linear(16 * 5 * 5, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 100)  # 这里从10改为100

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = torch.flatten(x, 1) # flatten all dimensions except batch
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x

另外，用户定义的classes元组是CIFAR-100的20个超类，若需要对应100个细类的名称，可以替换为完整的CIFAR-100类别列表，但该修改不影响训练过程，仅影响后续测试时的分类名称显示。

内容的提问来源于stack exchange，提问作者emilmrcheat