RuntimeError: Given groups=1, weight of size [32, 3, 5, 5]

Question

python白 训练模型出现错误

RuntimeError: Given groups=1, weight of size [32, 3, 5, 5], expected input[1, 32, 16, 16] to have 3 channels, but got 32 channels instead

但是我输出图片格式显示

print(imgs.shape)

torch.Size([1, 3, 32, 32])

代码如下：

import torch
import torchvision
from torch import nn
from torch.nn import Sequential, Conv2d, MaxPool2d, Flatten, Linear
from torch.utils.data import DataLoader

dataset = torchvision.datasets.CIFAR10("./data",train=False,
                                       transform=torchvision.transforms.ToTensor(),download=True)
dataloader = DataLoader(dataset,batch_size=1)

class Seq(nn.Module):
    def __init__(self):
        super(Seq,self).__init__()
        self.model = Sequential(
            Conv2d(3, 32, 5, padding=2),
            MaxPool2d(2),
            Conv2d(3, 32, 5, padding=2),
            MaxPool2d(2),
            Conv2d(3, 32, 5, padding=2),
            MaxPool2d(2),
            Flatten(),
            Linear(1024, 64),
            Linear(64, 10)
        )
    def forward(self,x):
        x = self.model(x)
        return x

#loss = nn.CrossEntropyLoss()
seq = Seq()
for data in dataloader:
    imgs,targets = data
    #print(imgs.shape)
    output = seq(imgs)
    #result = loss(outputs,target)

Answer 1

chatgpt:参考一下，不喜勿喷
在构建Sequential模型时，第2、4、6层的输入通道数应该为32而不是3，因为输入图片是CIFAR-10数据集中的彩色图片，通道数是3。修改代码如下：

class Seq(nn.Module):
    def __init__(self):
        super(Seq,self).__init__()
        self.model = Sequential(
            Conv2d(3, 32, 5, padding=2),
            MaxPool2d(2),
            Conv2d(32, 32, 5, padding=2),
            MaxPool2d(2),
            Conv2d(32, 32, 5, padding=2),
            MaxPool2d(2),
            Flatten(),
            Linear(1024, 64),
            Linear(64, 10)
        )
    def forward(self,x):
        x = self.model(x)
        return x

这样修改后，第2、4、6层的输入通道数就是32，与imgs的通道数相匹配了，就不会出现输入输出通道数不匹配的错误了。