pytorch下对各种超参调整效果

#GPU训练
import torch
from torch import nn
import torchvision
from torch.utils.tensorboard import SummaryWriter
from torch.utils.data import DataLoader#1.准备训练数据 测试数据
train_data = torchvision.datasets.CIFAR10(root="./",train=True,transform=torchvision.transforms.ToTensor(),download=True
)
test_data = torchvision.datasets.CIFAR10(root="./",train=False,transform=torchvision.transforms.ToTensor(),download=True
)
train_size = len(train_data)
test_size = len(test_data)
#加载数据集
train_dataloader = DataLoader(train_data, batch_size=64)
test_dataloader = DataLoader(test_data, batch_size=64)#2.创建神经网络
class Tudui(nn.Module):def __init__(self):super(Tudui, self).__init__()self.model = nn.Sequential(nn.Conv2d(3, 32, 5, 1, 2),nn.MaxPool2d(2),nn.Conv2d(32, 32, 5, 1, 2),nn.MaxPool2d(2),nn.Conv2d(32, 64, 5, 1, 2),nn.MaxPool2d(2),nn.Flatten(),nn.Linear(64*4*4, 64),nn.Linear(64, 10))def forward(self, x):x = self.model(x)return x#3.实例化模型
tudui = Tudui()
if torch.cuda.is_available():tudui = tudui.cuda()print("GPU训练")
else:print("CPU训练")#4.损失函数与优化器
loss_fn = nn.CrossEntropyLoss()
if torch.cuda.is_available():loss_fn = loss_fn.cuda()
learning_rate = 1e-2
optimizer = torch.optim.SGD(tudui.parameters(), lr= learning_rate)#5.训练与测试
epoch = 10
for i in range(epoch):acy = 0total_loss = 0tudui.train()for data in train_dataloader:imgs, targets = dataif torch.cuda.is_available():imgs, targets = imgs.cuda(), targets.cuda()outputs = tudui(imgs)acy_t = (outputs.argmax(1) == targets).sum()acy += acy_tloss = loss_fn(outputs, targets)optimizer.zero_grad()loss.backward()optimizer.step()total_loss+=loss.item()print("训练epoch:{}, loss:{} acy:{}".format(i+1, total_loss, acy/train_size))#6.测试
accuracy = 0
tudui.eval()
with torch.no_grad():for data in test_dataloader:imgs, targets = dataif torch.cuda.is_available():imgs, targets = imgs.cuda(), targets.cuda()outputs = tudui(imgs)accuracy_t = (outputs.argmax(1) == targets).sum()accuracy += accuracy_t
print("测试集合的正确率为:{}".format(accuracy/test_size))

以上代码，训练结果如下：

加入了归一化：

加入激活函数：

dropout()在各种参数下：

0.1
训练epoch:10, loss:391.0225857049227 acy:0.8289600014686584
测试集合的正确率为:0.70279997587203980.2
训练epoch:10, loss:439.34341555833817 acy:0.8060199618339539
测试集合的正确率为:0.67189997434616090.3
训练epoch:10, loss:478.8938387930393 acy:0.7883599996566772
测试集合的正确率为:0.6529999971389770.4
训练epoch:10, loss:537.8044945299625 acy:0.7644599676132202
测试集合的正确率为:0.71230000257492070.5
训练epoch:10, loss:594.5000147819519 acy:0.7396399974822998
测试集合的正确率为:0.67759996652603150.8
训练epoch:10, loss:904.8575140833855 acy:0.5776599645614624
测试集合的正确率为:0.538599967956543

以下也是0.4时：

优化器SGD()改为Adm()：

学习率从0.01改为0.001，改变不大

Batch_size从64到128

修改了以上各种参数的代码：

#GPU训练
import torch
from torch import nn
import torchvision
from torch.utils.tensorboard import SummaryWriter
from torch.utils.data import DataLoader#1.准备训练数据 测试数据
train_data = torchvision.datasets.CIFAR10(root="./",train=True,transform=torchvision.transforms.ToTensor(),download=True
)
test_data = torchvision.datasets.CIFAR10(root="./",train=False,transform=torchvision.transforms.ToTensor(),download=True
)
train_size = len(train_data)
test_size = len(test_data)
#加载数据集
train_dataloader = DataLoader(train_data, batch_size=128, shuffle=True)
test_dataloader = DataLoader(test_data, batch_size=128, shuffle=False)#2.创建神经网络
class Tudui(nn.Module):def __init__(self):super(Tudui, self).__init__()self.model = nn.Sequential(nn.Conv2d(3, 32, 5, 1, 2),nn.BatchNorm2d(32),nn.ReLU(),nn.MaxPool2d(2),nn.Conv2d(32, 32, 5, 1, 2),nn.BatchNorm2d(32),nn.ReLU(),nn.MaxPool2d(2),nn.Conv2d(32, 64, 5, 1, 2),nn.BatchNorm2d(64),nn.ReLU(),nn.MaxPool2d(2),nn.Flatten(),nn.Linear(64*4*4, 64),nn.BatchNorm1d(64),nn.ReLU(),nn.Dropout(0.4),nn.Linear(64, 10))def forward(self, x):x = self.model(x)return x#3.实例化模型
tudui = Tudui()
if torch.cuda.is_available():tudui = tudui.cuda()print("GPU训练")
else:print("CPU训练")#4.损失函数与优化器
loss_fn = nn.CrossEntropyLoss()
if torch.cuda.is_available():loss_fn = loss_fn.cuda()
learning_rate = 1e-3
optimizer = torch.optim.Adam(tudui.parameters(), lr= learning_rate)#5.训练与测试
epoch = 10
for i in range(epoch):acy = 0total_loss = 0tudui.train()for data in train_dataloader:imgs, targets = dataif torch.cuda.is_available():imgs, targets = imgs.cuda(), targets.cuda()outputs = tudui(imgs)acy_t = (outputs.argmax(1) == targets).sum()acy += acy_tloss = loss_fn(outputs, targets)print("this batch of loss:{}".format(loss.item()))optimizer.zero_grad()loss.backward()optimizer.step()total_loss+=loss.item()print("训练epoch:{}, loss:{} acy:{}".format(i+1, total_loss, acy/train_size))#6.测试
accuracy = 0
tudui.eval()
with torch.no_grad():for data in test_dataloader:imgs, targets = dataif torch.cuda.is_available():imgs, targets = imgs.cuda(), targets.cuda()outputs = tudui(imgs)accuracy_t = (outputs.argmax(1) == targets).sum()accuracy += accuracy_t
print("测试集合的正确率为:{}".format(accuracy/test_size))