Pytorch-MLP-CIFAR10

文章目录

model.py

py 复制代码
import torch.nn as nn
import torch.nn.functional as F
import torch.nn.init as init

class MLP_cls(nn.Module):
    def __init__(self,in_dim=3*32*32):
        super(MLP_cls,self).__init__()
        self.lin1 = nn.Linear(in_dim,128)
        self.lin2 = nn.Linear(128,64)
        self.lin3 = nn.Linear(64,10)
        self.relu = nn.ReLU()
        init.xavier_uniform_(self.lin1.weight)
        init.xavier_uniform_(self.lin2.weight)
        init.xavier_uniform_(self.lin3.weight)

    def forward(self,x):
        x = x.view(-1,3*32*32)
        x = self.lin1(x)
        x = self.relu(x)
        x = self.lin2(x)
        x = self.relu(x)
        x = self.lin3(x)
        x = self.relu(x)
        return x

main.py

py 复制代码
import torch
import torch.nn as nn
import torchvision
from torch.utils.data import DataLoader
import torch.optim as optim
from model import MLP_cls,CNN_cls


seed = 42
torch.manual_seed(seed)
batch_size_train = 64
batch_size_test  = 64
epochs = 10
learning_rate = 0.01
momentum = 0.5
net = MLP_cls()

train_loader = torch.utils.data.DataLoader(
    torchvision.datasets.CIFAR10('./data/', train=True, download=True,
                               transform=torchvision.transforms.Compose([
                                   torchvision.transforms.ToTensor(),
                                   torchvision.transforms.Normalize(
                                       (0.5,), (0.5,))
                               ])),
    batch_size=batch_size_train, shuffle=True)
test_loader = torch.utils.data.DataLoader(
    torchvision.datasets.CIFAR10('./data/', train=False, download=True,
                               transform=torchvision.transforms.Compose([
                                   torchvision.transforms.ToTensor(),
                                   torchvision.transforms.Normalize(
                                       (0.5,), (0.5,))
                               ])),
    batch_size=batch_size_test, shuffle=True)

optimizer = optim.SGD(net.parameters(), lr=learning_rate,momentum=momentum)
criterion = nn.CrossEntropyLoss()

print("****************Begin Training****************")
net.train()
for epoch in range(epochs):
    run_loss = 0
    correct_num = 0
    for batch_idx, (data, target) in enumerate(train_loader):
        out = net(data)
        _,pred = torch.max(out,dim=1)
        optimizer.zero_grad()
        loss = criterion(out,target)
        loss.backward()
        run_loss += loss
        optimizer.step()
        correct_num  += torch.sum(pred==target)
    print('epoch',epoch,'loss {:.2f}'.format(run_loss.item()/len(train_loader)),'accuracy {:.2f}'.format(correct_num.item()/(len(train_loader)*batch_size_train)))



print("****************Begin Testing****************")
net.eval()
test_loss = 0
test_correct_num = 0
for batch_idx, (data, target) in enumerate(test_loader):
    out = net(data)
    _,pred = torch.max(out,dim=1)
    test_loss += criterion(out,target)
    test_correct_num  += torch.sum(pred==target)
print('loss {:.2f}'.format(test_loss.item()/len(test_loader)),'accuracy {:.2f}'.format(test_correct_num.item()/(len(test_loader)*batch_size_test)))

参数设置

bash 复制代码
'./data/' #数据保存路径
seed = 42 #随机种子
batch_size_train = 64
batch_size_test  = 64
epochs = 10

optim --> SGD
learning_rate = 0.01
momentum = 0.5

注意事项

CIFAR10是彩色图像,单个大小为3*32*32。所以view的时候后面展平。

运行图

相关推荐
移远通信3 分钟前
2025上海车展 | 移远通信全栈车载智能解决方案重磅亮相,重构“全域智能”出行新范式
人工智能
蹦蹦跳跳真可爱5893 小时前
Python----深度学习(基于深度学习Pytroch簇分类,圆环分类,月牙分类)
人工智能·pytorch·python·深度学习·分类
蚂蚁20144 小时前
卷积神经网络(二)
人工智能·计算机视觉
z_mazin6 小时前
反爬虫机制中的验证码识别:类型、技术难点与应对策略
人工智能·计算机视觉·目标跟踪
lixy5797 小时前
深度学习3.7 softmax回归的简洁实现
人工智能·深度学习·回归
youhebuke2257 小时前
利用deepseek快速生成甘特图
人工智能·甘特图·deepseek
訾博ZiBo7 小时前
AI日报 - 2025年04月26日
人工智能
郭不耐7 小时前
DeepSeek智能时空数据分析(三):专业级地理数据可视化赏析-《杭州市国土空间总体规划(2021-2035年)》
人工智能·信息可视化·数据分析·毕业设计·数据可视化·城市规划
AI军哥8 小时前
MySQL8的安装方法
人工智能·mysql·yolo·机器学习·deepseek
余弦的倒数8 小时前
知识蒸馏和迁移学习的区别
人工智能·机器学习·迁移学习