Pytorch学习--神经网络--搭建小实战(手撕CIFAR 10 model structure)和 Sequential 的使用

一、Sequential 的使用方法

在手撕代码中进一步体现
torch.nn.Sequential

二、手撕 CIFAR 10 model structure

手撕代码:

python 复制代码
import torch
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear
from torch.utils.tensorboard import SummaryWriter


class Mary(nn.Module):
    def __init__(self):
        super(Mary,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
Yorelee = Mary()
print(Yorelee)
# 检测
input = torch.ones((64,3,32,32))
output = Yorelee(input)
print(output.shape)  #如果是[64,10]即为正确

#用Tensorboard去检测
writer = SummaryWriter("logs")
writer.add_graph(Yorelee,input)
writer.close()

Tensorboard 输出:

使用nn.Sequential的代码:

python 复制代码
import torch
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear
from torch.utils.tensorboard import SummaryWriter


class Mary(nn.Module):
    def __init__(self):
        super(Mary,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)
        self.model1 = nn.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.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)
        x = self.model1(x)
        return x
Yorelee = Mary()
print(Yorelee)
# 检测
input = torch.ones((64,3,32,32))
output = Yorelee(input)
print(output.shape)  #如果是[64,10]即为正确

#用Tensorboard去检测
writer = SummaryWriter("logs")
writer.add_graph(Yorelee,input)
writer.close()
相关推荐
AKAMAI27 分钟前
跳过复杂环节:Akamai应用平台让Kubernetes生产就绪——现已正式发布
人工智能·云原生·云计算
databook2 小时前
Manim实现闪光轨迹特效
后端·python·动效
新智元2 小时前
阿里王牌 Agent 横扫 SOTA,全栈开源力压 OpenAI!博士级难题一键搞定
人工智能·openai
新智元2 小时前
刚刚,OpenAI/Gemini 共斩 ICPC 2025 金牌!OpenAI 满分碾压横扫全场
人工智能·openai
机器之心2 小时前
OneSearch,揭开快手电商搜索「一步到位」的秘技
人工智能·openai
阿里云大数据AI技术2 小时前
2025云栖大会·大数据AI参会攻略请查收!
大数据·人工智能
Juchecar3 小时前
解惑:NumPy 中 ndarray.ndim 到底是什么?
python
YourKing3 小时前
yolov11n.onnx格式模型转换与图像推理
人工智能
sans_3 小时前
NCCL的用户缓冲区注册
人工智能
sans_3 小时前
三种视角下的Symmetric Memory,下一代HPC内存模型
人工智能