学习地址

PyTorch深度学习快速入门教程【小土堆】.

主要内容

一、CIFAR-10 model结构介绍

1. input : 3@32x323通道32x32的图片 --> 特征图(Feature maps) : 32@32x32
   即经过32个3@5x5的卷积层输出尺寸没有变化有x个特征图即有x个卷积核。卷积核的通道数与输入的通道数相等即3@5x5。
   两种方法推导出padding = 2、stride = 1的值
   • 公式法
     
     
     • 理论法为保持输出尺寸不变padding都是卷积核大小的一半应该padding=kernel_size/2奇数卷积核把中心格子对准图片第一个格子卷积核在格子外有两层就padding=2。
2. input : 32@32x32 --> output : 32@16x16
   即经过2x2的最大池化层stride = 2池化层的步长为池化核的尺寸padding = 0特征图尺寸减小一半。
   3.input : 32@16x16 --> output : 32@16x16
   即即经过32个3@5x5的卷积层输出尺寸没有变化。padding = 2、stride = 1。
   4.input : 32@16x16 --> output : 32@8x8
   即经过2x2的最大池化层stride = 2padding = 0通道数不变特征图尺寸减小一半。
   5.input : 32@8x8 --> output : 64@8x8
   即即经过64个3@5x5的卷积层输出尺寸没有变化。padding = 2、stride = 1。
   6.input : 64@8x8 --> output : 64@4x4
   即经过2x2的最大池化层stride = 2padding = 0通道数不变特征图尺寸减小一半。

二、代码实现

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


class Model(nn.Module):
    def __init__(self) -> None:
        super().__init__()  # 初始化父类属性
        # 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()  # 展平为1维向量torch.reshape()一样效果
        # # 若是想检验1024是否正确可以先写前面的层看样例的输出大小即可得到1024
        # self.linear1 = Linear(in_features=1024, out_features=64)
        # self.linear2 = Linear(in_features=64, out_features=10)

        # sequential可以替代前面备注掉的代码段
        self.model1 = Sequential(
            Conv2d(3, 32, 5, stride=1, 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.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)

        #代替以上代码段
        x = self.model1(x)
        return x


model = Model()  # 创建一个实例
print(model)  # 打印模型结构

# 测试模型样例也可以测试各层的输出是否正确
input = torch.ones((64, 3, 32, 32))
print(input.shape)  # torch.Size([64, 3, 32, 32])
output = model(input)
print(output.shape)  # torch.Size([64, 10])batch_size=6410个参数

writer = SummaryWriter("./logs_seq")  # 创建一个实例
writer.add_graph(model, input)  # 显示模型结构
writer.close()

# tensorboard命令tensorboard --logdir=logs_seq --port=6007

输出

Model(
  (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, 3, 32, 32])
torch.Size([64, 10])

TensorBoard输出