卷积层
torch.nn.Conv2d(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True, padding_mode='zeros'
- in_channels:输入通道数(彩色图像3通道)
- out_channels:输出通道数=卷积核个数
- kernel_size:卷积核尺寸
- stride:卷积步长
- padding:对原始图像扩充边边
- dilation:卷积核对应位的距离
- groups:设置为1,几乎用不上
- bias:偏置,一直设置为True
- padding_mode:填充的模式
import torch
import torchvision
from torch import nn
from torch.nn import Conv2d
from torch.utils.data import DataLoader
# 数据
dataset = torchvision.datasets.CIFAR10("./dataset", train=False, transform=torchvision.transforms.ToTensor(),download=True)
dataloader = DataLoader(dataset, batch_size=64)
# 搭建神经网络
class Tudui(nn.Module):
# 初始化方法
def __init__(self):
# 父类初始化
super(Tudui, self).__init__()
# 定义卷积层(使用self,self后面的变量在其他函数中也可以使用)
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
tudui = Tudui()
print(tudui)
结果
对图片卷积
tudui = Tudui()
writer = SummaryWriter("logs")
step = 0
for data in dataloader:
imgs, target = data
output = tudui(imgs)
# torch.Size([64, 3, 32, 32])
writer.add_images("input", imgs, step)
# torch.Size([64, 6, 30, 30])
writer.add_images("output", output, step)
step += 1
- 这里会报错......因为output 是6通道的,tensorboard上彩色图像要3通道才可以显示。
- 通过 reshape 改变通道数。bachsize不知道是多少就设置为-1,它会自己计算。
tudui = Tudui()
writer = SummaryWriter("logs")
step = 0
for data in dataloader:
imgs, target = data
output = tudui(imgs)
# torch.Size([64, 3, 32, 32])
writer.add_images("input", imgs, step)
# 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
结果