如何解决Conv1d CNN模型输入尺寸不匹配引发的Runtime Error？

我正在使用包含4000个半简单随机点的合成数据集训练CNN模型，每个样本有2个特征，每类对应一个聚类。输入数据x的形状为[4000,2]，标签y的形状为[4000]。

我清楚原始输入张量形状为[4000,2]（4000为样本总数，2为特征数），Conv1d层需要输入[batch_size,1,2]的3D张量（1为输入通道数，2为序列长度），但经过DataLoader和训练函数处理后，输入变为[1,50,2]，引发维度不匹配问题。

CNN模型定义 #

import torch
import torch.nn as nn
from torch.utils.data import DataLoader

class Net(nn.Module):
    def __init__(self, Bias):
        super(Net, self).__init__()
        self.conv1 = nn.Conv1d(1, 1, kernel_size=1, stride=1) 
        self.relu = nn.ReLU()                                  
        self.fc1 = nn.Linear(2, 20, bias = False)            
        self.fc2 = nn.Linear(20, 2, bias = False)
    def forward(self, x):
        x = self.relu(self.conv1(x))
        x = x.reshape(x.size(0), -1)
        x = self.relu(self.fc1(x))
        x = self.fc2(x)
        return x

epochs = 50
alpha = 1e-2
batch_size = 50
criterion = nn.CrossEntropyLoss()
# 假设biases是已定义的变量
model = Net(biases).to(device)
model = train(model.to(device),criterion,x,y,alpha,epochs,batch_size)

训练函数 #

def train(model,criterion, x, y, alpha, epochs, batchsize):
    costs = []
    optimizer = torch.optim.SGD(model.parameters(), lr=alpha)    
    trainx, trainy, testx, testy= dataloader(x,y)
    x=trainx.float()
    y=trainy.float()
    data_train = torch.cat((x, y), dim=1)
    data_train_loader = DataLoader(data_train, batch_size=batchsize, shuffle=True)
    model.train()
    j = 0
    for i in range(epochs):
        for index,samples in enumerate(data_train_loader):
            j += 1
            x1 = samples[:,0:2]
            y1 = samples[:,2].long().reshape(-1,1)
            if (j%50 == 0):
                model.eval()
                acc = accuracy(model,testx,testy)
                print(f'Test accuracy is #{acc:.2f} , Iteration number is = {j}')
                model.train()
            cost = criterion(model(x1), y1.squeeze())
            optimizer.zero_grad()
            cost.backward()
            optimizer.step()        
            costs.append(float(cost))
    return model

错误信息 #

RuntimeError                              Traceback (most recent call last)
Cell In[17], line 7
      5 criterion = nn.CrossEntropyLoss()
      6 model = Net(biases).to(device)
----> 7 model=train(model.to(device),criterion,x,y,alpha,epochs,batch_size)
Cell In[15], line 40, in train(model, criterion, x, y, alpha, epochs, batchsize)
     38     print(f'Test accuracy is #{acc:.2f} , Iteration number is = {j}')
     39     model.train()
---> 40 cost = criterion(model(x1), y1.squeeze())
Cell In[16], line 11, in Net.forward(self, x)
     10 def forward(self, x):
---> 11     x = self.relu(self.conv1(x))

RuntimeError: Given groups=1, weight of size [1, 1, 1], expected input[1, 50, 2] to have 1 channels, but got 50 channels instead

错误核心是Conv1d的输入维度不匹配：PyTorch中Conv1d要求输入格式为[batch_size, in_channels, sequence_length]，但当前传入的x1形状是[batch_size, 2]（或错误的[1,50,2]，本质是通道维度缺失/位置错误），可以通过以下两种方式修复：

方法1：在训练函数中调整输入维度 #

在获取x1后，添加通道维度，将形状从[batch_size, 2]转为[batch_size, 1, 2]：

x1 = samples[:,0:2]
# 添加这一行
x1 = x1.unsqueeze(1)  # 形状变为[50,1,2]，符合Conv1d要求

方法2：在模型forward方法中调整输入维度 #

如果不想修改训练函数，可在模型的forward开头添加维度调整，确保输入符合要求：

def forward(self, x):
    # 添加这一行：如果输入是[batch_size,2]，转为[batch_size,1,2]
    x = x.unsqueeze(1)
    x = self.relu(self.conv1(x))
    x = x.reshape(x.size(0), -1)
    x = self.relu(self.fc1(x))
    x = self.fc2(x)
    return x

额外说明 #

• 你的模型中fc1层的输入维度设置正确：Conv1d输出形状为[batch_size,1,2]，经过reshape(x.size(0), -1)后变为[batch_size,2]，与fc1(in_features=2)匹配。
• 注意代码中biases变量需要提前定义，否则会引发未定义错误。

内容的提问来源于stack exchange，提问作者jerry gill