import torch import os import torch.nn as nn import torch.optim as optim import numpy as np import random import matplotlib.pyplot as plt 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_path1 = '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(i) file_path1 = os.path.join(folder_path1, file_name) matrix1 = np.load(file_path1) x[j] = torch.from_numpy(matrix1).unsqueeze(0) folder_path2 = 'random_label2' y = torch.empty((40, )) for k in range(40): for k in range(40): file_name = 'label_{}.npy'.format(i) file_path2 = os.path.join(folder_path2, file_name) matrix2 = np.load(file_path2) y[k] = torch.from_numpy(matrix2) losses = [] for epoch in range(10): running_loss = 0.0 for i in range(40): inputs, labels = x[i], y[i] optimizer.zero_grad() outputs = net(inputs) loss = criterion(outputs, labels) loss.backward() optimizer.step() running_loss += loss.item() losses.append(running_loss / 40) print('[%d] loss: %.3f' % (epoch + 1, running_loss / 40)) print('Finished Training') plt.plot(losses) plt.xlabel('Epoch') plt.ylabel('Loss') plt.show() 报错：ValueError: Expected input batch_size (1) to match target batch_size (0). 不改变y的形状，改变输出，怎么修改？

你可以在创建空的tensor y 时，指定数据类型为 long 并且指定 y 的维度为 (40,1)，然后在读取标签文件时，先将 numpy 数组转换为 torch tensor，并且使用 squeeze() 方法将维度为 1 的维度去掉，最后使用 view() 方法将维度转换为 (1, )。修改后的代码如下：

import torch 
import os 
import torch.nn as nn 
import torch.optim as optim 
import numpy as np 
import random 
import matplotlib.pyplot as plt 

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_path1 = '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):
    file_name = 'matrix_{}.npy'.format(j)
    file_path1 = os.path.join(folder_path1, file_name)
    matrix1 = np.load(file_path1)
    x[j] = torch.from_numpy(matrix1).unsqueeze(0)

folder_path2 = 'random_label2'
# 创建空的tensor
y = torch.empty((40, 1), dtype=torch.long)

# 遍历文件夹内的文件，将每个标签转化为tensor并存储
for k in range(40):
    file_name = 'label_{}.npy'.format(k)
    file_path2 = os.path.join(folder_path2, file_name)
    matrix2 = np.load(file_path2)
    y[k] = torch.from_numpy(matrix2).squeeze().view(1)

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

print('Finished Training')
plt.plot(losses)
plt.xlabel('Epoch')
plt.ylabel('Loss')
plt.show()