文章目录

• 四、Neural Network 神经网络
• • 1、Containers - Module
  • 2、Convolution Layers - functional.conv2d
  • • 2.1 stride
    • 2.2 padding
  • 3、Convolution Layers - Conv2d
  • • 3.1 in_channels out_channels
  • 4、Pooling layers - MaxPool2d
  • • 4.1 ceil_mode
    • 4.2 TensorBoard
  • 5、Non-linear Activations
  • • 5.1 ReLU
    • 5.2 Sigmoid
  • 6、Linear Layers - Linear
  • • 6.1 flatten
  • 7、CIFAR 10 Model and Sequential
  • 8、Loss Functions
  • • 8.1 L1Loss
    • 8.2 MSELoss
    • 8.3 CrossEntropyLoss
    • 8.4 Sequential
    • 8.5 backward

四、Neural Network 神经网络

参考文档：https://pytorch.org/docs/stable/nn.html

1、Containers - Module

参考文档：https://pytorch.org/docs/stable/generated/torch.nn.Module.html#torch.nn.Module

import torch
from torch import nnclass Tudui(nn.Module):def __init__(self):super().__init__()def forward(self, input):output = input + 1return outputtudui = Tudui()
x = torch.tensor(1.0)
output = tudui(x)
print(output)

tensor(2.)

2、Convolution Layers - functional.conv2d

参考文档：https://pytorch.org/docs/stable/generated/torch.nn.functional.conv2d.html#torch.nn.functional.conv2d

2.1 stride

import torch
import torch.nn.functional as Finput = 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]
])kernel = torch.tensor([[1, 2, 1],[0, 1, 0],[2, 1, 0]
])input = torch.reshape(input, (1, 1, 5, 5))  # torch.Size([1, 1, 5, 5])
kernel = torch.reshape(kernel, (1, 1, 3, 3))  # torch.Size([1, 1, 3, 3])output1 = F.conv2d(input, kernel, stride=1)
print(output1)output2 = F.conv2d(input, kernel, stride=2)
print(output2)

tensor([[[[10, 12, 12],[18, 16, 16],[13,  9,  3]]]])
tensor([[[[10, 12],[13,  3]]]])

2.2 padding

import torch
import torch.nn.functional as Finput = 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]
])kernel = torch.tensor([[1, 2, 1],[0, 1, 0],[2, 1, 0]
])input = torch.reshape(input, (1, 1, 5, 5))  # torch.Size([1, 1, 5, 5])
kernel = torch.reshape(kernel, (1, 1, 3, 3))  # torch.Size([1, 1, 3, 3])output1 = F.conv2d(input, kernel, stride=1, padding=1)
print(output1)output2 = F.conv2d(input, kernel, stride=2, padding=1)
print(output2)

tensor([[[[ 1,  3,  4, 10,  8],[ 5, 10, 12, 12,  6],[ 7, 18, 16, 16,  8],[11, 13,  9,  3,  4],[14, 13,  9,  7,  4]]]])
tensor([[[[ 1,  4,  8],[ 7, 16,  8],[14,  9,  4]]]])

3、Convolution Layers - Conv2d

参考文档：https://pytorch.org/docs/stable/generated/torch.nn.Conv2d.html#torch.nn.Conv2d

动画实现：https://github.com/vdumoulin/conv_arithmetic/blob/master/README.md

3.1 in_channels out_channels

import torchvision
from torch import nn
from torch.nn import Conv2d
from torch.utils.data import DataLoaderdataset = torchvision.datasets.CIFAR10("../data", train=False, transform=torchvision.transforms.ToTensor(),download=True)dataloader = DataLoader(dataset, batch_size=64)class Tudui(nn.Module):def __init__(self):super(Tudui, 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 xtudui = Tudui()for data in dataloader:imgs, targets = dataoutput = tudui(imgs)print(imgs.shape)print(output.shape)

Files already downloaded and verified
torch.Size([64, 3, 32, 32]) # in_channels=3
torch.Size([64, 6, 30, 30]) # out_channels=6 卷积之后 32 -> 30
...

TensorBoard展示：

import torch
import torchvision
from torch import nn
from torch.nn import Conv2d
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriterdataset = torchvision.datasets.CIFAR10("../data", train=False, transform=torchvision.transforms.ToTensor(),download=True)dataloader = DataLoader(dataset, batch_size=64)class Tudui(nn.Module):def __init__(self):super(Tudui, 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 xtudui = Tudui()writer = SummaryWriter("logs")step = 0
for data in dataloader:imgs, targets = dataoutput = tudui(imgs)print(imgs.shape)  # torch.Size([64, 3, 32, 32])print(output.shape)  # torch.Size([64, 6, 30, 30])writer.add_images("input", imgs, step)output = torch.reshape(output, (-1, 3, 30, 30))  # -> [xxx, 3, 30, 30]writer.add_images("output", output, step)print(output.shape)  # torch.Size([128, 3, 30, 30])step += 1writer.close()

4、Pooling layers - MaxPool2d

参考文档：https://pytorch.org/docs/stable/generated/torch.nn.MaxPool2d.html#torch.nn.MaxPool2d

4.1 ceil_mode

import torch
from torch import nn
from torch.nn import MaxPool2dinput = 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],
])input = torch.reshape(input, (-1, 1, 5, 5))  # torch.Size([1, 1, 5, 5])class Tudui(nn.Module):def __init__(self):super(Tudui, self).__init__()self.maxpool1 = MaxPool2d(kernel_size=3, ceil_mode=True)def forward(self, input):output = self.maxpool1(input)return outputtudui = Tudui()
output = tudui(input)
print(output)

tensor([[[[2., 3.],[5., 1.]]]])

4.2 TensorBoard

import torchvision
from torch import nn
from torch.nn import MaxPool2d
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriterdataset = torchvision.datasets.CIFAR10("../data", train=False, transform=torchvision.transforms.ToTensor(),download=True)dataloader = DataLoader(dataset, batch_size=64)class Tudui(nn.Module):def __init__(self):super(Tudui, self).__init__()self.maxpool1 = MaxPool2d(kernel_size=3, ceil_mode=False)def forward(self, input):output = self.maxpool1(input)return outputtudui = Tudui()writer = SummaryWriter("../logs")
step = 0
for data in dataloader:imgs, targets = datawriter.add_images("input", imgs, step)output = tudui(imgs)writer.add_images("output", output, step)step += 1writer.close()

5、Non-linear Activations

5.1 ReLU

参考文档：https://pytorch.org/docs/stable/generated/torch.nn.ReLU.html#torch.nn.ReLU

inplace说明：

①input = -1 – ReLU(input, inplace = True) – input = 0

②input = -1 – output = ReLU(input, inplace = True) – input = -1 output = 0

import torch
from torch import nn
from torch.nn import ReLUinput = torch.Tensor([[1, -0.5], [-1, 3]])  # torch.Size([2, 2])input = torch.reshape(input, (-1, 1, 2, 2))  # torch.Size([1, 1, 2, 2])class Tudui(nn.Module):def __init__(self):super(Tudui, self).__init__()self.relu1 = ReLU()def forward(self, input):output = self.relu1(input)return outputtudui = Tudui()
output = tudui(input)
print(output)  # torch.Size([1, 1, 2, 2])

tensor([[[[1., 0.],[0., 3.]]]])

5.2 Sigmoid

参考文档：https://pytorch.org/docs/stable/generated/torch.nn.Sigmoid.html#torch.nn.Sigmoid

import torchvision
from torch import nn
from torch.nn import ReLU, Sigmoid
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriterdataset = torchvision.datasets.CIFAR10("../data", train=False, transform=torchvision.transforms.ToTensor(),download=True)
dataloader = DataLoader(dataset, batch_size=64)class Tudui(nn.Module):def __init__(self):super(Tudui, self).__init__()self.sigmoid1 = Sigmoid()def forward(self, input):output = self.sigmoid1(input)return outputtudui = Tudui()writer = SummaryWriter("../logs")step = 0
for data in dataloader:imgs, targets = datawriter.add_images("input", imgs, global_step=step)output = tudui(imgs)writer.add_images("output", output, global_step=step)step += 1writer.close()

6、Linear Layers - Linear

参考文档：https://pytorch.org/docs/stable/generated/torch.nn.Linear.html#torch.nn.Linear

import torch
import torchvision
from torch import nn
from torch.nn import Linear
from torch.utils.data import DataLoaderdataset = torchvision.datasets.CIFAR10("../data", train=False, transform=torchvision.transforms.ToTensor(),download=True)
dataloader = DataLoader(dataset, batch_size=64)class Tudui(nn.Module):def __init__(self):super(Tudui, self).__init__()self.liner1 = Linear(in_features=196608, out_features=10)def forward(self, input):output = self.liner1(input)return outputtudui = Tudui()for data in dataloader:imgs, targets = dataprint(imgs.shape)  # torch.Size([64, 3, 32, 32])output = torch.reshape(imgs, (1, 1, 1, -1))print(output.shape)  # torch.Size([1, 1, 1, 196608])output = tudui(output)print(output.shape)  # torch.Size([1, 1, 1, 10])

Files already downloaded and verified
torch.Size([64, 3, 32, 32])
torch.Size([1, 1, 1, 196608])
torch.Size([1, 1, 1, 10])
...

6.1 flatten

参考文档：https://pytorch.org/docs/stable/generated/torch.flatten.html?highlight=flatten#torch.flatten

output = torch.reshape(imgs, (1, 1, 1, -1))
print(output.shape)  # torch.Size([1, 1, 1, 196608])改为output = torch.flatten(imgs)
print(output.shape)  # torch.Size([196608]) output --> torch.Size([10])

7、CIFAR 10 Model and Sequential

CIFAR 10：https://www.cs.toronto.edu/~kriz/cifar.html

import torch
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linearclass Tudui(nn.Module):def __init__(self):super(Tudui, self).__init__()self.conv1 = Conv2d(in_channels=3, out_channels=32, kernel_size=5, padding=2)self.maxpool1 = MaxPool2d(kernel_size=2)self.conv2 = Conv2d(in_channels=32, out_channels=32, kernel_size=5, padding=2)self.maxpool2 = MaxPool2d(kernel_size=2)self.conv3 = Conv2d(in_channels=32, out_channels=64, kernel_size=5, padding=2)self.maxpool3 = MaxPool2d(kernel_size=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 xtudui = Tudui()
print(tudui)
input = torch.ones((64, 3, 32, 32))
output = tudui(input)
print(output.shape)

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)(conv2): 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)
)
torch.Size([64, 10])

Sequential：https://pytorch.org/docs/stable/generated/torch.nn.Sequential.html#torch.nn.Sequential

import torch
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential
from torch.utils.tensorboard import SummaryWriterclass 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 xtudui = Tudui()
print(tudui)
input = torch.ones((64, 3, 32, 32))
output = tudui(input)
print(output.shape)writer = SummaryWriter("../logs")
writer.add_graph(tudui, input)
writer.close()

Tudui((model1): Sequential((0): Conv2d(3, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))(1): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)(2): Conv2d(32, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))(3): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)(4): Conv2d(32, 64, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))(5): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)(6): Flatten(start_dim=1, end_dim=-1)(7): Linear(in_features=1024, out_features=64, bias=True)(8): Linear(in_features=64, out_features=10, bias=True))
)
torch.Size([64, 10])

8、Loss Functions

8.1 L1Loss

参考文档：https://pytorch.org/docs/stable/generated/torch.nn.L1Loss.html#torch.nn.L1Loss

import torch
from torch.nn import L1Lossinput = torch.tensor([1, 2, 3], dtype=torch.float32)  # torch.Size([3])
target = torch.tensor([1, 2, 5], dtype=torch.float32)  # torch.Size([3])input = torch.reshape(input, (1, 1, 1, 3))  # torch.Size([1, 1, 1, 3])
target = torch.reshape(target, (1, 1, 1, 3))  # torch.Size([1, 1, 1, 3])loss1 = L1Loss(reduction='mean')  # 默认为mean
result = loss1(input, target)
print(result)loss2 = L1Loss(reduction='sum')  # sum
result = loss2(input, target)
print(result)

tensor(0.6667)
tensor(2.)

8.2 MSELoss

参考文档：https://pytorch.org/docs/stable/generated/torch.nn.MSELoss.html#torch.nn.MSELoss

import torch
from torch.nn import MSELossinput = torch.tensor([1, 2, 3], dtype=torch.float32)
target = torch.tensor([1, 2, 5], dtype=torch.float32)input = torch.reshape(input, (1, 1, 1, 3))
target = torch.reshape(target, (1, 1, 1, 3))loss = MSELoss()
result = loss(input, target)
print(result)

tensor(1.3333)

8.3 CrossEntropyLoss

参考文档：https://pytorch.org/docs/stable/generated/torch.nn.CrossEntropyLoss.html#torch.nn.CrossEntropyLoss

计算公式：

import torch
from torch.nn import CrossEntropyLossinput = torch.tensor([0.1, 0.2, 0.3])
target = torch.tensor([1])input = torch.reshape(input, (1, 3))cross = CrossEntropyLoss()
result = cross(input, target)
print(result)

tensor(1.1019)

8.4 Sequential

import torchvision
from torch import nn
from torch.nn import Sequential, Conv2d, MaxPool2d, Flatten, Linear
from torch.utils.data import DataLoaderdataset = torchvision.datasets.CIFAR10("../data", train=False, transform=torchvision.transforms.ToTensor(),download=True)dataloader = DataLoader(dataset, batch_size=1)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 xtudui = Tudui()for data in dataloader:imgs, targets = dataoutput = tudui(imgs)print(output)print(targets)

Files already downloaded and verified
tensor([[-0.0715,  0.0221, -0.0562, -0.0901,  0.0627, -0.0606,  0.0137,  0.0783,-0.0951, -0.1070]], grad_fn=)
tensor([3])
tensor([[-0.0715,  0.0304, -0.0729, -0.0767,  0.0554, -0.0834, -0.0089,  0.0624,-0.0777, -0.0848]], grad_fn=)
tensor([8])
...

加入Loss Functions：

import torchvision
from torch import nn
from torch.nn import Sequential, Conv2d, MaxPool2d, Flatten, Linear, CrossEntropyLoss
from torch.utils.data import DataLoaderdataset = torchvision.datasets.CIFAR10("../data", train=False, transform=torchvision.transforms.ToTensor(),download=True)dataloader = DataLoader(dataset, batch_size=1)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 xloss = CrossEntropyLoss()tudui = Tudui()for data in dataloader:imgs, targets = dataoutput = tudui(imgs)result_loss = loss(output, targets)print(result_loss)

Files already downloaded and verified
tensor(2.3437, grad_fn=)
tensor(2.3600, grad_fn=)
tensor(2.3680, grad_fn=)
...

8.5 backward

import torchvision
from torch import nn
from torch.nn import Sequential, Conv2d, MaxPool2d, Flatten, Linear, CrossEntropyLoss
from torch.utils.data import DataLoaderdataset = torchvision.datasets.CIFAR10("../data", train=False, transform=torchvision.transforms.ToTensor(),download=True)dataloader = DataLoader(dataset, batch_size=1)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 xloss = CrossEntropyLoss()tudui = Tudui()for data in dataloader:imgs, targets = dataoutput = tudui(imgs)result_loss = loss(output, targets)result_loss.backward()  # 反向传播print("OK")