sunpongber

神经网络-卷积层

Convolution Layers->Conv2d

Conv2d

torch.nn.Conv2d(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True, padding_mode='zeros', device=None, dtype=None)

Convolution arithmetic

kernel_size定义了一个卷积核的大小，在搭建卷积层的时候，只需要定义kernel_size的大小尺寸
kernel_size=3时，生成一个3×3的卷积核，卷积核的参数是从分布中进行一个采样得到的
可以想象它满足一个分布，这个数取多少都无所谓，因为实际训练神经网络的过程中，其实就是对kernel_size中的一些参数不断调整

in_channels=1, out_channels=2
这时会有两个卷积核，卷积后的输出叠加作为输出

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(root="P18_nn_conv2d/dataset", train=False, transform=torchvision.transforms.ToTensor(), download=True)

dataLoader = DataLoader(dataset, batch_size=64)

class nn_conv2d(nn.Module):
    def __init__(self):
        super(nn_conv2d, self).__init__()
        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 x

nn_conv2d_nn = nn_conv2d()
print(nn_conv2d_nn)

writer = SummaryWriter(log_dir="logs")

step = 0
for data in dataLoader:
    imgs, targets = data
    output = nn_conv2d_nn(imgs)
    print(imgs.shape)
    print(output.shape)

    writer.add_images("input", imgs, step)

    output = torch.reshape(output, (-1, 3, 30, 30))

    writer.add_images("output", output, step)

    step += 1

返回：

nn_conv2d(
  (conv1): Conv2d(3, 6, kernel_size=(3, 3), stride=(1, 1))
)
torch.Size([64, 3, 32, 32])
torch.Size([64, 6, 30, 30])
...
torch.Size([64, 3, 32, 32])
torch.Size([64, 6, 30, 30])
torch.Size([16, 3, 32, 32])
torch.Size([16, 6, 30, 30])

原始资料地址：
神经网络-卷积层
如有侵权联系删除 仅供学习交流使用