import torch import os import torch.nn as nn import torch.optim as optim import numpy as np import random class Net(nn.Module): def init(self): super(Net, self).init() self.conv1 = nn.Conv2d(1, 16, kernel_size=3,stride=1) self.pool = nn.MaxPool2d(kernel_size=2,stride=2) self.conv2 = nn.Conv2d(16, 32, kernel_size=3,stride=1) self.fc1 = nn.Linear(32 * 9 * 9, 120) self.fc2 = nn.Linear(120, 84) self.fc3 = nn.Linear(84, 2) def forward(self, x): x = self.pool(nn.functional.relu(self.conv1(x))) x = self.pool(nn.functional.relu(self.conv2(x))) x = x.view(-1, 32 * 9 * 9) x = nn.functional.relu(self.fc1(x)) x = nn.functional.relu(self.fc2(x)) x = self.fc3(x) return x net = Net() criterion = nn.CrossEntropyLoss() optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9) folder_path = 'random_matrices2' # 创建空的tensor x = torch.empty((40, 1, 42, 42)) # 遍历文件夹内的文件，将每个矩阵转化为tensor并存储 for j in range(40): for j in range(40): file_name = 'matrix_{}.npy'.format(j) file_path = os.path.join(folder_path, file_name) matrix = np.load(file_path) x[j] = torch.from_numpy(matrix).unsqueeze(0) #y = torch.cat((torch.zeros(20), torch.ones(20))) #y = torch.cat((torch.zeros(20, dtype=torch.long), torch.ones(20, dtype=torch.long))) y = torch.cat((torch.zeros(20, dtype=torch.long), torch.ones(20, dtype=torch.long)), dim=0) for epoch in range(10): running_loss = 0.0 for i in range(40): inputs = x[i] labels = y[i] optimizer.zero_grad() outputs = net(inputs) #loss = criterion(outputs, labels) loss = criterion(outputs.unsqueeze(0), labels) loss.backward() optimizer.step() running_loss += loss.item() print('[%d] loss: %.3f' % (epoch + 1, running_loss / 40)) print('Finished Training') 报错：ValueError: Expected input batch_size (1) to match target batch_size (0). 怎么修改？

在这段代码中，你的标签 `y` 的形状是 `(batch_size,)`，其中 `batch_size=40`。然而，在训练时，你使用了 `labels = y[i]`，这将返回一个标量张量，而不是形状为 `(1,)` 的张量。这是 `nn.CrossEntropyLoss` 期望的标签形状。

解决方法是将 `labels` 转换为形状为 `(1,)` 的张量。你可以使用 `labels.unsqueeze(0)` 来实现这一点。这将在第0维添加一个额外的维度，将形状从 `(batch_size,)` 变为 `(1, batch_size)`。

以下是修改后的代码：

for epoch in range(10):
    running_loss = 0.0
    for i in range(40):
        inputs = x[i]
        labels = y[i]
        optimizer.zero_grad()
        outputs = net(inputs)
        loss = criterion(outputs.unsqueeze(0), labels.unsqueeze(0))
        loss.backward()
        optimizer.step()
        running_loss += loss.item()
    print('[%d] loss: %.3f' % (epoch + 1, running_loss / 40))

print('Finished Training')