RuntimeError: Expected 4-dimensional input for 4-dimensional weight [32, 1, 5, 5]

痛定思痛。 2023-01-17 08:50 317阅读 0赞

### 文章目录 ###

*  1. 问题引入
 *  2. 运行报错
 *  3. 代码
 *  4. 分析原因
 *  5.解决办法
 *  6. 完整代码
 *  7. 参考文献

# 1. 问题引入 #

今天在使用pytorch训练一个模型的，数据集的读取是使用pytorch自带的函数来进行读取和预处理的，网络使用的是自定义的CNN，然后在运行的时候出现了如标题所示的这种小错误。

# 2. 运行报错 #

如下所示：

RuntimeError: Expected 4-dimensional input for 4-dimensional weight [32, 1, 5, 5], but got 2-dimensional input of size [32, 784] instead

# 3. 代码 #

首先是我自己自定义的CNN网络如下所示：

class MNIST_Model(nn.Module):
        def __init__(self, n_in):
            super(MNIST_Model, self).__init__()
    
            self.conv1 = nn.Sequential(
                nn.Conv2d(in_channels=n_in,
                          out_channels=32,
                          kernel_size=(5, 5),
                          padding=2,
                          stride=1),
            )
    
            self.maxp1 = nn.MaxPool2d(
                           kernel_size=(2, 2))
    
            self.conv2 = nn.Sequential(
                nn.Conv2d(in_channels=32,
                          out_channels=64,
                          kernel_size=(5, 5),
                          padding=0,
                          stride=1),
            )
    
            self.maxp2 = nn.MaxPool2d(kernel_size=(2, 2))
            
            self.fc1 = nn.Sequential(
                nn.Linear(in_features=64 * 5 * 5, out_features=200)  # Mnist
            )
    
            self.fc2 = nn.Sequential(
                nn.Linear(in_features=200, out_features=10),
                nn.ReLU()
            )
    
    
        def forward(self, x):
            x = self.conv1(x)
            x = self.maxp1(x)
            x = self.conv2(x)
            x = self.maxp2(x)
            x = x.contiguous().view(x.size(0), -1)
            x = self.fc1(x)
            x = self.fc2(x)
            return x

然后是在训练模型的代码

#实例化网络，只考虑使用CPU
    model = model.MNIST_Model(1)
    net = model.to(device)
    #定义损失函数和优化器
    criterion = nn.CrossEntropyLoss()
    #momentum:动量因子有什么用处？
    optimizer = optim.SGD(model.parameters(),lr=lr,momentum=momentum)
    
    
    #开始训练 先定义存储损失函数和准确率的数组
    losses = []
    acces = []
    #测试用
    eval_losses = []
    eval_acces = []
    
    for epoch in range(nums_epoches):
        #每次训练先清零
        train_loss = 0
        train_acc = 0
        #将模型设置为训练模式
        model.train()
        #动态学习率
        if epoch%5 == 0:
            optimizer.param_groups[0]['lr'] *= 0.1
        for img,label in train_loader:
            #前向传播，将图片数据传入模型中
            # out输出10维，分别是各数字的概率，即每个类别的得分
            out = model(img)
            #这里注意参数out是64*10，label是一维的64
            loss = criterion(out,label)
            #反向传播
            #optimizer.zero_grad()意思是把梯度置零，也就是把loss关于weight的导数变成0
            optimizer.zero_grad()
            loss.backward()
            #这个方法会更新所有的参数，一旦梯度被如backward()之类的函数计算好后，我们就可以调用这个函数
            optimizer.step()
            
            #记录误差 
            train_loss += loss.item()
            
            #计算分类的准确率,找到概率最大的下标
            _,pred = out.max(1)
            num_correct = (pred == label).sum().item()#记录标签正确的个数
            acc = num_correct/img.shape[0]
            train_acc += acc
        losses.append(train_loss/len(train_loader))
        acces.append(train_acc/len(train_loader))
        
        eval_loss = 0
        eval_acc = 0
        model.eval()
        for img,label in test_loader:
            img = img.view(img.size(0),-1)
            
            out = model(img)
            loss = criterion(out,label)
            
            optimizer.zero_grad()
            loss.backward()
            optimizer.step()
            
            eval_loss += loss.item()
            
            _,pred = out.max(1)
            num_correct = (pred == label).sum().item()
            acc = num_correct/img.shape[0]
            eval_acc += acc
        eval_losses.append(eval_loss/len(test_loader))
        eval_acces.append(eval_acc/len(test_loader))
        
    
        print('epoch:{},Train Loss:{:.4f},Train Acc:{:.4f},Test Loss:{:.4f},Test Acc:{:.4f}'
                 .format(epoch,train_loss/len(train_loader),train_acc/len(train_loader),
                        eval_loss/len(test_loader),eval_acc/len(test_loader)))

# 4. 分析原因 #

定位出错位置

Traceback (most recent call last):
      File "train.py", line 73, in <module>
        out = model(img)
      File "/home/gzdx/anaconda3/envs/Torch/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
        result = self.forward(*input, **kwargs)
      File "/home/gzdx/wyf/PARAD/model.py", line 48, in forward
        x = self.conv1(x)
      File "/home/gzdx/anaconda3/envs/Torch/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
        result = self.forward(*input, **kwargs)
      File "/home/gzdx/anaconda3/envs/Torch/lib/python3.7/site-packages/torch/nn/modules/container.py", line 119, in forward
        input = module(input)
      File "/home/gzdx/anaconda3/envs/Torch/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
        result = self.forward(*input, **kwargs)
      File "/home/gzdx/anaconda3/envs/Torch/lib/python3.7/site-packages/torch/nn/modules/conv.py", line 399, in forward
        return self._conv_forward(input, self.weight, self.bias)
      File "/home/gzdx/anaconda3/envs/Torch/lib/python3.7/site-packages/torch/nn/modules/conv.py", line 396, in _conv_forward
        self.padding, self.dilation, self.groups)
    RuntimeError: Expected 4-dimensional input for 4-dimensional weight [32, 1, 5, 5], but got 2-dimensional input of size [32, 784] instead

可以看到这句提示，大致就是我们传入的数据输入到CNN网络，然后由于维度不同导致的。因为我们输入的是四维，但是得到的却是二维。

File "train.py", line 73, in <module>
        out = model(img)

# 5.解决办法 #

对于这种问题网上给出了很多中不同的方案，这个哦个人也是参考我网上别人给出的一点想法然后自己修改了下，错误就解决了，如下所示：

for i,data in enumerate(train_loader):
            #前向传播，将图片数据传入模型中
            # out输出10维，分别是各数字的概率，即每个类别的得分
            inputs, labels = data
            inputs,labels = data[0].to(device), data[1].to(device)
            # inputs torch.Size([32, 1, 28, 28])
            out = model(inputs)

解决办法也是很简单，就是将上面训练开始阶段将数据按照这种读取方式来赋值，然后在传入到model里面就不会出现上面那种错误了。

# 6. 完整代码 #

import numpy as np
    import model
    import torch
    
    #导入PyTorch内置的mnist数据
    from torchvision.datasets import mnist
    
    #导入预处理模块
    from torchvision import transforms
    from torch.utils.data import DataLoader
    
    #导入神经网络工具
    import torch.nn as nn
    import torch.nn.functional as F
    import torch.optim as optim
    
    #定义后面要用到的超参数
    train_batch_size = 32
    test_batch_size = 32
    
    #学习率与训练次数
    learning_rate = 0.01
    nums_epoches = 50
    
    #优化器的时候使用的参数
    lr = 0.1
    momentum = 0.5
    
    #用compose来定意预处理函数
    transform = transforms.Compose([transforms.ToTensor(),transforms.Normalize([0.5],[0.5])])
    
    #下载数据，在工程文件夹里新建一个data文件夹储存下载的数据
    train_dataset = mnist.MNIST('./data', train=True, transform=transform, target_transform=None, download=False)
    test_dataset = mnist.MNIST('./data', train=False, transform=transform, target_transform=None, download=False)
    
    #数据加载器，组合数据集和采样器，并在数据集上提供单进程或多进程迭代器
    train_loader = DataLoader(train_dataset, batch_size=train_batch_size, shuffle=True, num_workers=0)
    test_loader = DataLoader(test_dataset, batch_size=test_batch_size, shuffle=False)
    
    device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
    
    #实例化网络，只考虑使用CPU
    model = model.MNIST_Model(1)
    net = model.to(device)
    #定义损失函数和优化器
    criterion = nn.CrossEntropyLoss()
    #momentum:动量因子有什么用处？
    optimizer = optim.SGD(model.parameters(),lr=lr,momentum=momentum)
    
    
    
    
    #开始训练 先定义存储损失函数和准确率的数组
    losses = []
    acces = []
    #测试用
    eval_losses = []
    eval_acces = []
    
    for epoch in range(nums_epoches):
        #每次训练先清零
        train_loss = 0
        train_acc = 0
        #将模型设置为训练模式
        model.train()
    
        #动态学习率
        if epoch%5 == 0:
            optimizer.param_groups[0]['lr'] *= 0.1
        for i,data in enumerate(train_loader):
            #前向传播，将图片数据传入模型中
            # out输出10维，分别是各数字的概率，即每个类别的得分
            inputs, labels = data
            inputs,labels = data[0].to(device), data[1].to(device)
            out = model(inputs)
            #这里注意参数out是64*10，label是一维的64
            loss = criterion(out,labels)
            #反向传播
            #optimizer.zero_grad()意思是把梯度置零，也就是把loss关于weight的导数变成0
            optimizer.zero_grad()
            loss.backward()
            #这个方法会更新所有的参数，一旦梯度被如backward()之类的函数计算好后，我们就可以调用这个函数
            optimizer.step()
            
            #记录误差 
            train_loss += loss.item()
            
            #计算分类的准确率,找到概率最大的下标
            _,pred = out.max(1)
            num_correct = (pred == labels).sum().item() #记录标签正确的个数
            acc = num_correct/inputs.shape[0]
            train_acc += acc
        losses.append(train_loss/len(train_loader))
        acces.append(train_acc/len(train_loader))
        print('Finished Training') 
    
        # 保存模型
        PATH = './model/mnist_net.pth'
        torch.save(net.state_dict(), PATH)
        
        eval_loss = 0
        eval_acc = 0
        model.eval()
        for i,data in enumerate(test_loader):
            inputs, labels = data
            inputs,labels = data[0].to(device), data[1].to(device)
            out = model(inputs)
            loss = criterion(out,labels)
            
            optimizer.zero_grad()
            loss.backward()
            optimizer.step()
            
            eval_loss += loss.item()
            
            _,pred = out.max(1)
            num_correct = (pred == labels).sum().item()
            acc = num_correct/inputs.shape[0]
            eval_acc += acc
        eval_losses.append(eval_loss/len(test_loader))
        eval_acces.append(eval_acc/len(test_loader))
        
    
        print('epoch:{},Train Loss:{:.4f},Train Acc:{:.4f},Test Loss:{:.4f},Test Acc:{:.4f}'
                 .format(epoch,train_loss/len(train_loader),train_acc/len(train_loader),
                        eval_loss/len(test_loader),eval_acc/len(test_loader)))

# 7. 参考文献 #

[1.pytorch学习笔记—搭建CNN识别MNIST][1.pytorch_CNN_MNIST]

[2.使用Pytorch框架的CNN网络实现手写数字（MNIST）识别][2._Pytorch_CNN_MNIST]

[1.pytorch_CNN_MNIST]: https://blog.csdn.net/qq_38308028/article/details/106419067?utm_medium=distribute.pc_relevant.none-task-blog-baidujs_title-0&spm=1001.2101.3001.4242
[2._Pytorch_CNN_MNIST]: https://bravey.github.io/2020-03-13-%E4%BD%BF%E7%94%A8Pytorch%E6%A1%86%E6%9E%B6%E7%9A%84CNN%E7%BD%91%E7%BB%9C%E5%AE%9E%E7%8E%B0%E6%89%8B%E5%86%99%E6%95%B0%E5%AD%97%EF%BC%88MNIST%EF%BC%89%E8%AF%86%E5%88%AB.html