Pytorch学习11_神经网络-卷积层

1.创建神经网络实例

import torch
import torchvision
from torch import nn
from torch.nn import Conv2d
from torch.utils.data import DataLoaderdataset=torchvision.datasets.CIFAR10("../dataset_cov2d",train=False,transform=torchvision.transforms.ToTensor(),download=True)
dataloader=DataLoader(dataset,batch_size=64)
class Xuexu(nn.Module):def __init__(self):super(Xuexu, self).__init__()self.conv1=Conv2d(in_channels=3,out_channels=6,kernel_size=3,stride=1,padding=0)def forward(self,x):self.conv1(x)return xxuexu=Xuexu()
print(xuexu)

2.观察输出

输出图像的形状信息，以便检查输入和输出的张量形状是否符合预期。在深度学习中，了解输入和输出的形状对于调试和确保网络结构正确连接非常重要

import torch
import torchvision
from torch import nn
from torch.nn import Conv2d
from torch.utils.data import DataLoader# 加载 CIFAR-10 数据集
from torch.utils.tensorboard import SummaryWriterdataset=torchvision.datasets.CIFAR10("../dataset_cov2d",train=False,transform=torchvision.transforms.ToTensor(),download=True)
dataloader=DataLoader(dataset,batch_size=64)# 创建数据加载器# 定义神经网络模型
class Xuexu(nn.Module):def __init__(self):super(Xuexu, self).__init__()# 定义卷积层self.conv1=Conv2d(in_channels=3,out_channels=6,kernel_size=3,stride=1,padding=0)def forward(self, x):x=self.conv1(x)return xxuexu=Xuexu()
# writer=SummaryWriter("./logs")
step=0
for data in dataloader:imgs,target=dataoutput=xuexu(imgs)print(f"imgs:{imgs.shape}")print(f"output:{output.shape}")# writer.add_images("input",imgs,step)# writer.add_images("output",output,step)# step+=1

3.修改输出

import torch
import torchvision
from torch import nn
from torch.nn import Conv2d
from torch.utils.data import DataLoader# 加载 CIFAR-10 数据集
from torch.utils.tensorboard import SummaryWriterdataset=torchvision.datasets.CIFAR10("../dataset_cov2d",train=False,transform=torchvision.transforms.ToTensor(),download=True)
dataloader=DataLoader(dataset,batch_size=64)# 创建数据加载器# 定义神经网络模型
class Xuexu(nn.Module):def __init__(self):super(Xuexu, self).__init__()# 定义卷积层self.conv1=Conv2d(in_channels=3,out_channels=6,kernel_size=3,stride=1,padding=0)def forward(self, x):x=self.conv1(x)# 调用卷积层，并将输出赋给 xreturn xxuexu=Xuexu()
writer=SummaryWriter("./logs")
step=0
for data in dataloader:imgs,target=dataoutput=xuexu(imgs)# print(f"imgs:{imgs.shape}")# print(f"output:{output.shape}")# imgs:torch.Size([64, 3, 32, 32])writer.add_images("input",imgs,step)# output:torch.Size([64, 6, 30, 30])->[xxx,3,30,30]output=torch.reshape(output,(-1,3,30,30))writer.add_images("output",output,step)step+=1

终端运行

tensorboard --logdir="logs"

点击蓝色链接进入tensorboard网页

可以看到图片经过卷积之后得到的输出

参考

【PyTorch深度学习快速入门教程（绝对通俗易懂！）【小土堆】】 https://www.bilibili.com/video/BV1hE411t7RN/?p=18&share_source=copy_web&vd_source=be33b1553b08cc7b94afdd6c8a50dc5a