7.1 Neural Network
① The advantage of putting the network structure in Sequential is that the code is more concise and easy to understand.
② According to the size of each layer of the neural network, the parameters in the neural network can be calculated according to the formula in the figure below.
7.2 Build neural network
import torch
import torchvision
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear
class Tudui(nn.Module):
def __init__(self):
super(Tudui, self).__init__()
self.conv1 = Conv2d(3,32,5,padding=2)
self.maxpool1 = MaxPool2d(2)
self.cov2 = Conv2d(32,32,5,padding=2)
self.maxpool2 = MaxPool2d(2)
self.conv3 = Conv2d(32,64,5,padding=2)
self.maxpool3 = MaxPool2d(2)
self.flatten = Flatten()
self.linear1 = Linear(1024,64)
self.Linear2 = Linear(64,10)
def forward(self, x):
x = self.conv1(x)
x = self.maxpool1(x)
x = self.conv2(x)
x = self.maxpool2(x)
x = self.conv3(x)
x = self.maxpool3(x)
x = self.flatten(x)
x = self.linear1(x)
x = self.Linear2(x)
return x
tudui = Tudui()
print(tudui)
result:
Tudui ( (conv1): Conv2d(3, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2)) (maxpool1): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False) (cov2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2)) (maxpool2): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False) (conv3): Conv2d(32, 64, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2)) (maxpool3): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False) (flatten): Flatten(start_dim=1, end_dim=-1) (linear1): Linear(in_features=1024, out_features=64, bias=True) (Linear2): Linear(in_features=64, out_features=10, bias=True) )
7.3 Neural Network Input Data
import torch
import torchvision
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear
class Tudui(nn.Module):
def __init__(self):
super(Tudui, self).__init__()
self.conv1 = Conv2d(3,32,5,padding=2)
self.maxpool1 = MaxPool2d(2)
self.conv2 = Conv2d(32,32,5,padding=2)
self.maxpool2 = MaxPool2d(2)
self.conv3 = Conv2d(32,64,5,padding=2)
self.maxpool3 = MaxPool2d(2)
self.flatten = Flatten()
self.linear1 = Linear(1024,64)
self.Linear2 = Linear(64,10)
def forward(self, x):
x = self.conv1(x)
x = self.maxpool1(x)
x = self.conv2(x)
x = self.maxpool2(x)
x = self.conv3(x)
x = self.maxpool3(x)
x = self.flatten(x)
x = self.linear1(x)
x = self.Linear2(x)
return x
tudui = Tudui()
input = torch.ones((64,3,32,32))
output = tudui(input)
print(output.shape)
result:
torch.Size([64, 10])
7.4 Sequential neural network
import torch
import torchvision
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential
class Tudui(nn.Module):
def __init__(self):
super(Tudui, self).__init__()
self.model1 = Sequential(
Conv2d(3,32,5,padding=2),
MaxPool2d(2),
Conv2d(32,32,5,padding=2),
MaxPool2d(2),
Conv2d(32,64,5,padding=2),
MaxPool2d(2),
Flatten(),
Linear(1024,64),
Linear(64,10)
)
def forward(self, x):
x = self.model1(x)
return x
tudui = Tudui()
input = torch.ones((64,3,32,32))
output = tudui(input)
print(output.shape)
result:
torch.Size([64, 10])
7.4 Tensorboard display network
import torch
import torchvision
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
dataset = torchvision.datasets.CIFAR10("./dataset",train=False,transform=torchvision.transforms.ToTensor(),download=True)
dataloader = DataLoader(dataset, batch_size=64,drop_last=True)
class Tudui(nn.Module):
def __init__(self):
super(Tudui, self).__init__()
self.model1 = Sequential(
Conv2d(3,32,5,padding=2),
MaxPool2d(2),
Conv2d(32,32,5,padding=2),
MaxPool2d(2),
Conv2d(32,64,5,padding=2),
MaxPool2d(2),
Flatten(),
Linear(1024,64),
Linear(64,10)
)
def forward(self, x):
x = self.model1(x)
return x
tudui = Tudui()
writer = SummaryWriter("logs")
tudui = Tudui()
input = torch.ones((64,3,32,32))
output = tudui(input)
print(output.shape)
writer.add_graph(tudui, input)
writer.close()
result:
Files already downloaded and verified torch.Size([64, 10])
operate:
① In the Anaconda terminal, activate the py3.6.3 environment, then enter the tensorboard --logdir=C:\Users\wangy\Desktop\03CV\logs command, assign the URL to the browser's URL bar, and press Enter to view the tensorboard display. Log status.
result: