8.pytorch中卷积层、池化层、激活函数的搭建

最新推荐文章于 2022-09-01 17:08:01 发布

ruyingcai666666

最新推荐文章于 2022-09-01 17:08:01 发布

阅读量390

点赞数

文章标签：卷积深度学习

本文链接：https://blog.csdn.net/ruyingcai666666/article/details/119010727

版权

#卷积层
import torch
from torch.utils.data.dataloader import DataLoader
import torchvision
from torch import nn
from torch.nn import Conv2d
from torch.utils.tensorboard import SummaryWriter

data_set=torchvision.datasets.CIFAR10(root="./data_set",train=False,transform=torchvision.transforms.ToTensor(),download=True)
data_load = DataLoader(data_set,batch_size=64)

class Tudui(nn.Module):
    def __init__(self) -> None:
        super().__init__()    
        self.conv1=Conv2d(in_channels=3,out_channels=6,kernel_size=3,stride=1,padding=0)
        pass
    def forward(self,x):
        x=self.conv1(x)
        return x
        pass
    pass

tudui=Tudui()
# print(tudui)
writer=SummaryWriter("conv2d")
step=0
for data in data_load:
    # torch.Size([64, 3, 32, 32])
    imgs,targets=data
    # torch.Size([64, 6, 30, 30])
    output=tudui(imgs)
    # torch.Size([64, 6, 30, 30])-->torch.Size([128, 3, 30, 30])
    output=torch.reshape(output,(-1,3,30,30))
    writer.add_images("input",imgs,step)
    writer.add_images("output",output,step)
    step+=1
    # print(imgs.shape)
    # print(output.shape)

writer.close()

#池化层
import torchvision
from torch import nn
import torch
import torch.nn.functional as F
from torch.nn.modules import padding
from torch.nn import MaxPool2d
from torch.utils.data.dataloader import DataLoader
from torch.utils.tensorboard import SummaryWriter
data_set=torchvision.datasets.CIFAR10(root="./data_set",train=False,transform=torchvision.transforms.ToTensor(),download=True)
data_load = DataLoader(data_set,batch_size=64)
class Tudui(nn.Module):
    def __init__(self):
        super().__init__()
        self.maxpool1=MaxPool2d(kernel_size=3,ceil_mode=True)

        pass

    def forward(self,input):
        output=self.maxpool1(input)
        return output
        pass


# input = torch.tensor([[1,2,0,3,1],
#                       [0,1,2,3,1],
#                       [1,2,1,0,0],
#                       [5,2,3,1,1],
#                       [2,1,0,1,1]],dtype=torch.float32)

# kernel=torch.tensor([[1,2,1],
#                      [0,1,0],
#                      [2,1,0]])

# input=torch.reshape(input,(1,1,5,5))
# kernel=torch.reshape(kernel,(1,1,3,3))

# tudui=Tudui()
# output=tudui(input)
# print(output)


tudui=Tudui()
writer=SummaryWriter("pool")
step=0
for data in data_load:
    imgs,targets=data
    writer.add_images("input",imgs,step)
    output=tudui(imgs)
    writer.add_images("output",output,step)
    step+=1
    pass
writer.close()

#激活函数
import torchvision
from torch import nn
import torch
import torch.nn.functional as F
from torch.nn.modules import padding,ReLU,Sigmoid
from torch.nn import MaxPool2d
from torch.utils.data.dataloader import DataLoader
from torch.utils.tensorboard import SummaryWriter
data_set=torchvision.datasets.CIFAR10(root="./data_set",train=False,transform=torchvision.transforms.ToTensor(),download=True)
data_load = DataLoader(data_set,batch_size=64)
class Tudui(nn.Module):
    def __init__(self):
        super().__init__()
        self.relu1=ReLU()
        self.sigmoid1=Sigmoid()

        pass

    def forward(self,input):
        output=self.sigmoid1(input)
        return output
        pass


tudui=Tudui()
writer=SummaryWriter("activate")
step=0
for data in data_load:
    imgs,targets=data
    writer.add_images("input",imgs,step)
    output=tudui(imgs)
    writer.add_images("output",output,step)
    step+=1
    pass
writer.close()