RuntimeError：预期 1D 目标张量，不支持多目标 Pytorch

Question

我最近从 keras 转移到了 pytorch，但我仍在努力了解这一切是如何工作的。下面是我为使用简单的 MLP 对 mnist 数据集进行分类而实现的代码。就像我以前在 keras 中所做的那样，我将每个 28x28 图像展平为 784 的向量，并且我还为我的标签创建了一个单热表示。 在模型中，我希望给定一个 784 的向量，模型会输出一个带有概率的单热向量，但是一旦我的代码达到计算损失，我就会得到以下错误：

RuntimeError: 1D target tensor expected, multi-target not supported

下面是我的代码：

    import numpy as np
import matplotlib.pyplot as plt
import torch
import time
from torch import nn, optim
from keras.datasets import mnist
from torch.utils.data import Dataset, DataLoader

RANDOM_SEED = 42
np.random.seed(RANDOM_SEED)
torch.manual_seed(RANDOM_SEED)


# ----------------------------------------------------

class MnistDataset(Dataset):

    def __init__(self, data_size=0):

        (x, y), (_, _) = mnist.load_data()

        x = [i.flatten() for i in x]
        x = np.array(x, dtype=np.float32)

        if data_size < 0 or data_size > len(y):
            assert ("Data size should be between 0 to number of files in the dataset")

        if data_size == 0:
            data_size = len(y)

        self.data_size = data_size

        # picking 'data_size' random samples
        self.x = x[:data_size]
        self.y = y[:data_size]

        # scaling between 0-1
        self.x = (self.x / 255)

        # Creating one-hot representation of target
        y_encoded = []
        for label in y:
            encoded = np.zeros(10)
            encoded[label] = 1
            y_encoded.append(encoded)

        self.y = np.array(y_encoded)

    def __len__(self):
        return self.data_size

    def __getitem__(self, index):

        x_sample = self.x[index]
        label = self.y[index]

        return x_sample, label


# ----------------------------------------------------

num_train_samples = 10000
num_test_samples = 2000

# Each generator returns a single
# sample & its label on each iteration.
mnist_train = MnistDataset(data_size=num_train_samples)
mnist_test = MnistDataset(data_size=num_test_samples)

# Each generator returns a batch of samples on each iteration.
train_loader = DataLoader(mnist_train, batch_size=128, shuffle=True)  # 79 batches
test_loader = DataLoader(mnist_test, batch_size=128, shuffle=True)  # 16 batches


# ----------------------------------------------------

# Defining the Model Architecture

class MLP(nn.Module):

    def __init__(self):
        super().__init__()

        self.fc1 = nn.Linear(28 * 28, 100)
        self.act1 = nn.ReLU()
        self.fc2 = nn.Linear(100, 50)
        self.act2 = nn.ReLU()
        self.fc3 = nn.Linear(50, 10)
        self.act3 = nn.Sigmoid()

    def forward(self, x):
        x = self.act1(self.fc1(x))
        x = self.act2(self.fc2(x))
        output = self.act3(self.fc3(x))

        return output


# ----------------------------------------------------

model = MLP()

# Defining optimizer and loss function
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.1, momentum=0.9)

# ----------------------------------------------------

# Training the model

epochs = 10

print("Training Started...")

for epoch in range(epochs):
    for batch_index, (inputs, targets) in enumerate(train_loader):

        optimizer.zero_grad()  # Zero the gradients
        outputs = model(inputs)  # Forward pass
        loss = criterion(outputs, targets)  # Compute the Loss
        loss.backward()  # Compute the Gradients
        optimizer.step()  # Update the parameters

        # Evaluating the model
        total = 0
        correct = 0
        with torch.no_grad():
            for batch_idx, (inputs, targets) in enumerate(test_loader):
                outputs = model(inputs)
                _, predicted = torch.max(outputs.data, 1)
                total += targets.size(0)
                correct += predicted.eq(targets.data).cpu().sum()
            print('Epoch : {} Test Acc : {}'.format(epoch, (100. * correct / total)))

print("Training Completed Sucessfully")

# ----------------------------------------------------

我还阅读了一些与同一问题相关的其他帖子，其中大多数人说目标的 CrossEntropy 损失必须是一个数字，这完全超出了我的想象。有人可以解释一下解决方案吗。谢谢。

Answer 1

对于nn.CrossEntropyLoss，你不需要标签的one-hot表示，你只需要传递预测的logit，它的形状是(batch_size, n_class)，和一个目标向量(batch_size,)

所以只需传入标签索引向量 y 而不是 one-hot 向量。

修正了你的代码：

class MnistDataset(Dataset):

    def __init__(self, data_size=0):

        (x, y), (_, _) = mnist.load_data()

        x = [i.flatten() for i in x]
        x = np.array(x, dtype=np.float32)

        if data_size < 0 or data_size > len(y):
            assert ("Data size should be between 0 to number of files in the dataset")

        if data_size == 0:
            data_size = len(y)

        self.data_size = data_size

        # picking 'data_size' random samples
        self.x = x[:data_size]
        self.y = y[:data_size]

        # scaling between 0-1
        self.x = (self.x / 255)

        self.y = y # <--

    def __len__(self):
        return self.data_size

    def __getitem__(self, index):

        x_sample = self.x[index]
        label = self.y[index]

        return x_sample, label

查看 Pytorch 示例以获取更多详细信息： https://pytorch.org/docs/stable/generated/torch.nn.CrossEntropyLoss.html