pytorch深度学习——神经网络卷积层Conv2d

torn.nn.Conv2d

在官方文档可以查看参数

代码示例：

import torch
import torchvision
from torch import nn
from torch.nn import Conv2d
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

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

dataloader = DataLoader(dataset, 64)

class MyMoudle(nn.Module):
   def __init__(self):
       super(MyMoudle, self).__init__()
       self.conv1 = Conv2d(3, 6, 3, stride=1, padding=0)

   def forward(self, x):
       x = self.conv1(x)
       return x

Myconv = MyMoudle()#神经网络

writer = SummaryWriter("logs")
step = 0
for data in dataloader:
    imgs, target = data
    output = Myconv(imgs)
    writer.add_images("input", imgs, step)
    output = torch.reshape(output, (-1, 3, 30, 30))#因为原来是(XX, 6, 30, 30)6个channel会报错
    writer.add_images("output", output, step)

writer.close()

输出：