使用pytorch tensorDataset类时的“一维目标张量期望”误差

Question

我想知道为什么会出现这个错误。我的直觉告诉我，tensorDataset将最后一列读入为标签，但我不知道如果我为标签输入单独的数据集作为第二个参数，它为什么会这样。另外，有人能解释一下单一热编码是如何工作的吗?我如何解决这个问题，因为我只需要每个项目一个标签？

Error: return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index)
RuntimeError: 1D target tensor expected, multi-target not supported

代码：

if __name__ == '__main__':

inputs_file = pd.read_csv('dataset.csv')
targets_file = pd.read_csv('labels.csv')

inputs = inputs_file.iloc[1:1001].values
targets = targets_file.iloc[1:1001].values

inputs = torch.tensor(inputs, dtype=torch.float32)
targets = torch.tensor(targets)

dataset = TensorDataset(inputs, targets)

val_size = 200
test_size = 100
train_size = len(dataset) - (val_size + test_size)

# Divide dataset into 3 unique random subsets
training_data, validation_data, test_data = random_split(dataset, [train_size, val_size, test_size])

batch_size = 50

train_loader = DataLoader(training_data, batch_size, shuffle=True, num_workers=4, pin_memory=True)
valid_loader = DataLoader(validation_data, batch_size*2, num_workers=4, pin_memory=True)

Answer 1

根据我从评论讨论中收集到的信息，错误由以下内容再现。

import torch
from torch import nn
from torch.utils.data import DataLoader, TensorDataset, random_split

inputs = torch.randn(999, 11, dtype=torch.float32)
targets = torch.randint(5, (999, 1), dtype=torch.long)

# you need this to adapt from pandas, but not for this example code
# inputs = torch.tensor(inputs, dtype=torch.float32)
# targets = torch.tensor(targets)

dataset = TensorDataset(inputs, targets)

val_size = 200
test_size = 100
train_size = len(dataset) - (val_size + test_size)

# Divide dataset into 3 unique random subsets
training_data, validation_data, test_data = random_split(dataset, [train_size, val_size, test_size])

batch_size = 50

train_loader = DataLoader(training_data, batch_size, shuffle=True, num_workers=4, pin_memory=True)
valid_loader = DataLoader(validation_data, batch_size*2, num_workers=4, pin_memory=True)

# guess model. More on this in a moment
model = nn.Sequential(
    nn.Linear(11, 8),
    nn.Linear(8, 5),
)

loss_func = nn.CrossEntropyLoss()

for features, labels in train_loader:
    out = model(features)
    loss = loss_func(out, labels)
    print(f"{loss = }")
    break

解决方案1

将labels.squeeze(-1)添加到循环体a la中

for features, labels in train_loader:
    out = model(features)
    labels = labels.squeeze()
    loss = loss_func(out, labels)
    print(f"{loss = }")
    break

解决方案2

将你的目标首先用

targets = torch.tensor(targets[:, 0])

为了回应

现在我得到了一个错误: RuntimeError: mat1和mat2形状不能相乘(11x1和11x8)，我还应该添加一个8大小的隐藏层，我有5个类

我的架构是猜测您在使用什么，但是由于上面的代码是通过目标重组来解决的，我需要更多的帮助。

CrossEntropyLoss示例代码显示了目标的预期形状是N，而不是N, 1或N, classes。