Neural network convolution layer

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("CIFAR10",train=False,transform=torchvision.transforms.ToTensor(),download=True)
#  Be careful dataset in transform The parameter receives an object , So we need to add parentheses , In addition, when using neural network for operation, the data type required is tensor type , therefore transforms Parameters to add .
dataloader = DataLoader(dataset,batch_size=64)

#  Build a simple network 
class Booze(nn.Module):

    #  Inherit nn.Module The initialization 
    def __init__(self):
        super().__init__()
        #  Note that here is to create a global variable, so we need to add a self  When out_channels Far greater than in_channels The original image needs to be expanded , That is to say padding The value of cannot be set to 0 了 , According to the formula 
        
        self.conv1 = Conv2d(in_channels=3,out_channels=6,kernel_size=(3),stride=1,padding=0)

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


#  Initialize the network 
obj = Booze()
#  Check out the Internet 
print(obj)
''' Booze( (conv1): Conv2d(3, 6, kernel_size=(3, 3), stride=(1, 1)) ) '''

writer = SummaryWriter("logs")
step = 0

for data in dataloader:
    imgs,targets = data
    output = obj(imgs)
    # torch.Size([64, 3, 32, 32]) 64 Zhang 3 passageway 32X32 Pictures of the 
    print(imgs.shape)
    # torch.Size([64, 6, 30, 30]) 64 Zhang 6 passageway 30X30 Pictures of the 
    print(output.shape)

    #  Use tensorboard visualization   Note that multiple images are to be used add_images instead of add_image
    writer.add_images("input",imgs,step)

    #  because output yes 6 The number of channels cannot be displayed , Direct visualization will report an error , So we need to deal with output Conduct reshape reshape When a number is unknown in the second parameter of , You can fill in -1, He will automatically help you calculate , Why is it unknown ？ Because I just don't know how much to fill , fill 64 I'm sure not , Then changing the number of channels is equivalent to cutting out the extra pixels 
    torch.reshape(output,(-1,3,30,30))
    writer.add_images("output",output,step)
    step+=1

writer.close()

Points in the code that need attention and explanation ：

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

Be careful dataset in transform The parameter receives an object , So we need to add parentheses , In addition, when using neural network for operation, the data type required is tensor type , therefore transforms Parameters to add .

#  Build a simple network 
class Booze(nn.Module):

    #  Inherit nn.Module The initialization 
    def __init__(self):
        super().__init__()
        #  Note that here is to create a global variable, so we need to add a self  When out_channels Far greater than in_channels The original image needs to be expanded , That is to say padding The value of cannot be set to 0 了 , According to the formula 

        self.conv1 = Conv2d(in_channels=3,out_channels=6,kernel_size=(3),stride=1,padding=0)

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

In building neural network inheritance nn.Module When initializing , Creating variables creates global variables , So you need to add a before the variable self.

self.conv1 = Conv2d(in_channels=3,out_channels=6,kernel_size=(3),stride=1,padding=0)

Be careful When out_channels Far greater than in_channels The original image needs to be expanded , That is to say padding The value of cannot be set to 0 了 , It needs to be calculated according to the formula , The formula as follows ：

Above picture input The meaning of the four elements in the following tuple ：

• The first element represents batch_size
• The second element represents the number of image channels
• The third element represents the height of the image matrix
• The fourth element represents the width of the image matrix

for data in dataloader:
    imgs,targets = data
    output = obj(imgs)
    # torch.Size([64, 3, 32, 32]) 64 Zhang 3 passageway 32X32 Pictures of the 
    print(imgs.shape)
    # torch.Size([64, 6, 30, 30]) 64 Zhang 6 passageway 30X30 Pictures of the 
    print(output.shape)

    #  Use tensorboard visualization   Note that multiple images are to be used add_images instead of add_image
    writer.add_images("input",imgs,step)

    torch.reshape(output,(-1,3,30,30))
    writer.add_images("output",output,step)
    step+=1

writer.close()

In the above code writer.add_images("output",output,step) Before running, you need to output Reduce the number of channels . because output yes 6 The number of channels cannot be displayed , Direct visualization will report an error , So we need to deal with output Conduct reshape .
torch.reshape(output,(-1,3,30,30))reshape When a number is unknown in the second parameter of , You can fill in -1, He will automatically help you calculate , Why is it unknown ？ Because I just don't know how much to fill , fill 64 I'm sure not , Then changing the number of channels is equivalent to cutting out the extra pixels .

Use... After the above code is run tensorboard See the effect ：

As can be seen from the picture above output Every step More pictures than input Every step Number of pictures , The reason is that 6 Number of channels picture reshape become 3 The number of channels is caused by pictures batch_size An increase in .