【Pytorch】常用层的说明(4)

目录

一、卷积层

二、最大池化层

三、非线性激活

四、线性层及其他层介绍

五、搭建一个小网络

六、Sequential的使用

---

一、卷积层

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

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

torch.nn.Conv2d(in_channels, # 输入图像的通道数
out_channels, # 输出的通道数，如下图，有2个卷积核，产生output通道2个
kernel_size,  # 卷积核
stride=1,  # 步长
padding=0, 
dilation=1, 
groups=1, 
bias=True, 
padding_mode='zeros', 
device=None, 
dtype=None)

# -*- coding: utf-8 -*-
# 作者：小土堆
# 公众号：土堆碎念
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

# 将图片数据转为tensor格式，torchvision.transforms.ToTensor()
dataset = 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__() # 完成父类的初始化
        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

# 初始化这个网络
tudui = Tudui()
# 打印网络结构
print(tudui)


# 可视化
writer = SummaryWriter("../logs")

step = 0
for data in dataloader:
    imgs, targets = data
    output = tudui(imgs) # 模型输出
    print(imgs.shape) # torch.Size([64, 3, 32, 32])
    print(output.shape) # torch.Size([64, 6, 30, 30])
    
    writer.add_images("input", imgs, step)
    # torch.Size([64, 6, 30, 30])  -> [xxx, 3, 30, 30]

    # 不严谨，为了可视化，转为3个通道。多余的数放到batchsize里
    output = torch.reshape(output, (-1, 3, 30, 30))
    writer.add_images("output", output, step)

    step = step + 1

tensorboard的指令 

% tensorboard --logdir=logs

二、最大池化层

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

torch.nn.MaxPool2d(kernel_size, 
stride=None, 
padding=0, 
dilation=1, 
return_indices=False, 
ceil_mode=False)

import torch
import torch.nn.functional as F

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)) # batchsize,channel,h,w
kernel = torch.reshape(kernel, (1, 1, 3, 3))

print(input.shape) # torch.Size([1, 1, 5, 5])
print(kernel.shape) # torch.Size([1, 1, 3, 3])

output = F.conv2d(input, kernel, stride=1)
print(output)
# tensor([[[[10, 12, 12],
#           [18, 16, 16],
#           [13,  9,  3]]]])

output2 = F.conv2d(input, kernel, stride=2)
print(output2)
# tensor([[[[10, 12],
#           [13,  3]]]])

output3 = F.conv2d(input, kernel, stride=1, padding=1)
print(output3)
# 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]]]])

完整读取代码 

# -*- coding: utf-8 -*-
# 作者：小土堆
# 公众号：土堆碎念

import torch
import torchvision
from torch import nn
from torch.nn import MaxPool2d
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

# 使用测试集train=False
dataset = torchvision.datasets.CIFAR10("../data", train=False, download=True,
                                       transform=torchvision.transforms.ToTensor())

dataloader = DataLoader(dataset, batch_size=64)

class Tudui(nn.Module):
    # 模型初始化
    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 output

tudui = Tudui()

writer = SummaryWriter("../logs_maxpool")
step = 0

for data in dataloader:
    imgs, targets = data
    # writer.add_images("input", imgs, step)
    output = tudui(imgs) # model输入
    # writer.add_images("output", output, step)
    # step = step + 1
    print(output.shape)

# writer.close()

三、非线性激活

https://pytorch.org/docs/stable/nn.html#non-linear-activations-weighted-sum-nonlinearity

sigmoid使用如下，

>>> m = nn.Sigmoid()
>>> input = torch.randn(2)
>>> output = m(input)

 完整代码如下，

# -*- coding: utf-8 -*-
# 作者：小土堆
# 公众号：土堆碎念
import torch
import torchvision
from torch import nn
from torch.nn import ReLU, Sigmoid
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter

input = torch.tensor([[1, -0.5],
                      [-1, 3]])
print(input.shape) # torch.Size([2, 2])

# 因为relu的输入需要(N,*), 要batchsize
input = torch.reshape(input, (-1, 1, 2, 2))
# print(input.shape) # torch.Size([1, 1, 2, 2])
dataset = torchvision.datasets.CIFAR10("../data", train=False, download=True,
                                       transform=torchvision.transforms.ToTensor())

dataloader = DataLoader(dataset, batch_size=64)

class Tudui(nn.Module):
    def __init__(self):
        super(Tudui, self).__init__()
        self.relu1 = ReLU()
        self.sigmoid1 = Sigmoid()

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

# 初始化网络
tudui = Tudui()
output = tudui(input)
print(output) 
# tensor([[[[0.7311, 0.3775],
#           [0.2689, 0.9526]]]])


writer = SummaryWriter("../logs_relu")
step = 0
for data in dataloader:
    imgs, targets = data
    writer.add_images("input", imgs, global_step=step)
    output = tudui(imgs)
    writer.add_images("output", output, step)
    step += 1

writer.close()

四、线性层及其他层介绍

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

import torch
import torchvision
from torch import nn
from torch.nn import Linear
from torch.utils.data import DataLoader

dataset = 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.linear1 = Linear(196608, 10)

    def forward(self, input):
        output = self.linear1(input)
        return output

tudui = Tudui()

for data in dataloader:
    imgs, targets = data
    print(imgs.shape) # torch.Size([196608])
    output = torch.flatten(imgs)
    print(output.shape) # torch.Size([10])
    output = tudui(output)
    print(output.shape) # torch.Size([64, 3, 32, 32])

五、搭建一个小网络

搭建CIFAR10的模型如下：

根据模型结构，首先写  def __init__(self):

每个层的参数在这一步就写好了，

__init__写完接着写forward()。就是把上述层走一遍。

然后就可以初始化网络了。之后对输入输出进行验证。

测试通过就ok啦。

六、Sequential的使用

把单个层组合起来，使模型结构更简单。

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

对比一下

import torch
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear, Sequential
from torch.utils.tensorboard import SummaryWriter


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(), # 展平，输入第一个线性层
            Linear(1024, 64),
            Linear(64, 10) # 从第二个线性层输出
        )

    def forward(self, x):
        x = self.model1(x)
        return x

tudui = Tudui()
print(tudui)
input = torch.ones((64, 3, 32, 32))
output = tudui(input)
# 可视化方式
print(output.shape) #

writer = SummaryWriter("../logs_seq")
writer.add_graph(tudui, input)  # 通过 tensorboard 查看图结构
writer.close()