深度学习之神经网络框架搭建及模型优化
神经网络框架搭建及模型优化1 数据及配置
1.1 配置
需要安装PyTorch,下载安装torch、torchvision、torchaudio,GPU需下载cuda版本,CPU可直接下载
cuda版本较大,最后通过控制面板pip install +存储地址离线下载,
CPU版本需再下载安装VC_redist.x64.exe,可下载上述三个后运行,通过报错网址直接下载安装
1.2 数据
利用的是 torchvision.datasets.MNIST的手写数据,包括特征数据和结果种别
1.3 函数导入
import torch
from torch import nn
from torch.utils.data import DataLoader
from torchvision import datasets
from torchvision.transforms import ToTensor
1.4 数据函数
train_data = datasets.MNIST(
root='data', # 数据集存储的根目录
train=True, # 加载训练集
download=True, # 如果数据集不存在,自动下载
transform=ToTensor() # 将图像转换为张量
)
[*]root 指定数据集存储的根目录。假如数据集不存在,会自动下载到这个目录。
[*]train 决定加载训练集还是测试集。True 表示加载训练集,False 表示加载测试集。
[*]download 假如数据集不在 root 指定的目录中,是否自动下载数据集。True 表示自动下载。
[*]transform 对加载的数据举行预处理或转换。通常用于将数据转换为模型所需的格式,如将图像转换为张量。
1.5 数据打包
train_dataloader = DataLoader(train_data, batch_size=64)
[*]train_data, 打包数据
[*]batch_size=64,打包个数
代码展示:
import torchprint(torch.__version__)import torch
from torch import nn
from torch.utils.data import DataLoader
from torchvision import datasets
from torchvision.transforms import ToTensor
train_data = datasets.MNIST( root = 'data', train = True, download = True, transform = ToTensor())test_data = datasets.MNIST( root = 'data', train = False, download = True, transform = ToTensor())print(len(train_data))print(len(test_data))from matplotlib import pyplot as pltfigure = plt.figure()for i in range(9): img,label = train_data figure.add_subplot(3,3,i+1) plt.title(label) plt.axis('off') plt.imshow(img.squeeze(),cmap='gray') a = img.squeeze()plt.show()train_dataloader = DataLoader(train_data, batch_size=64)test_dataloader= DataLoader(test_data, batch_size=64) 运行结果:
https://i-blog.csdnimg.cn/direct/2a084c335be24946b1394194ec62c679.png
https://i-blog.csdnimg.cn/direct/ccaf5443fd784879b61dea4869e99d8d.png
调试查看:
https://i-blog.csdnimg.cn/direct/19a7a479a3dc45f3a8d723657a652899.png
https://i-blog.csdnimg.cn/direct/6119a39500f6473d951fb08c270591c2.png
2 神经网络框架搭建
2.1 框架确认
在搭建神经网络框架前,需先确认创建怎样的框架,现在并没有理论的指导,凭履历创建框架如下:
输入层:输入的图像数据(28*28)个神经元。
中间层1:全连接层,128个神经元,
中间层2:全连接层,256个神经元,
输出层:全连接层,10个神经元,对应10个种别。
需注意,中间层需利用鼓励函数激活,对累加数举行非线性的映射,以及forward前向流传过程的函数名不可更改,
2.2 函数搭建
[*]nn.Flatten() , 将输入展平为一维向量
[*]nn.Linear(28*28, 128) ,全连接层,需注意每个连接层的输入输出需前后对应
[*]torch.sigmoid(x),对中间层的输出应用Sigmoid激活函数
# 定义一个神经网络类,继承自 nn.Module
class NeuralNetwork(nn.Module):
def __init__(self):
super().__init__()# 调用父类 nn.Module 的构造函数
# 定义网络层
self.flatten = nn.Flatten()# 将输入展平为一维向量,适用于将图像数据(如28x28)展平为784维
self.hidden1 = nn.Linear(28*28, 128)# 第一个全连接层,输入维度为784(28*28),输出维度为128
self.hidden2 = nn.Linear(128, 256) # 第二个全连接层,输入维度为128,输出维度为256
self.out = nn.Linear(256, 10) # 输出层,输入维度为256,输出维度为10(对应10个类别)
# 定义前向传播过程
def forward(self, x):
x = self.flatten(x) # 将输入数据展平
x = self.hidden1(x) # 通过第一个全连接层
x = torch.sigmoid(x) # 对第一个全连接层的输出应用Sigmoid激活函数
x = self.hidden2(x) # 通过第二个全连接层
x = torch.sigmoid(x) # 对第二个全连接层的输出应用Sigmoid激活函数
x = self.out(x) # 通过输出层
return x # 返回最终的输出
2.3 框架上传
[*]device = ‘cuda’ if torch.cuda.is_available() else ‘mps’ if torch.backends.mps.is_available() else ‘cpu’,确认设备, 检查是否有可用的GPU设备,假如有则利用GPU,否则利用CPU
[*]model = NeuralNetwork().to(device),框架上传到GPU/CPU
模型输出展示:
https://i-blog.csdnimg.cn/direct/822b50eed477488b91d874e5f9c01c87.png
3 模型优化
3.1 函数明白
[*]optimizer = torch.optim.Adam(model.parameters(), lr=0.001),定义优化器:
[*]Adam()利用Adam优化算法,也可为SGD等优化算法
[*]model.parameters()为优化模型的参数,
[*]lr为学习率/梯度下降步长为0.001
[*]loss_fn = nn.CrossEntropyLoss(pre,y),定义丧失函数,利用交织熵丧失函数,适用于分类任务
[*]pre,猜测结果
[*]y,真实结果
[*]loss_fn.item(),当前丧失值
[*]model.train() ,将模型设置为训练模式,模型参数是可变的
[*]x, y = x.to(device), y.to(device),将数据移动到指定设备(GPU或CPU)
[*]反向流传:清零梯度,计算梯度,更新模型参数
[*]optimizer.zero_grad() ,清零梯度缓存
loss.backward(), 计算梯度
optimizer.step() , 更新模型参数
[*]model.eval(),将模型设置为评估模式,模型参数是不可变
[*]with torch.no_grad(),禁用梯度计算,在测试过程中不需要计算梯度
3.2 训练模型和测试模型代码
optimizer = torch.optim.Adam(model.parameters(),lr=0.001)
loss_fn = nn.CrossEntropyLoss()
def train(dataloader,model,loss_fn,optimizer):
model.train()
batch_size_num = 1
for x,y in dataloader:
x,y = x.to(device),y.to(device)
pred = model.forward(x)
loss = loss_fn(pred,y)
optimizer.zero_grad()
loss.backward()
optimizer.step()
loss_value = loss.item()
if batch_size_num %100 ==0:
print(f'loss: {loss_value:>7f}')
batch_size_num +=1
train(train_dataloader,model,loss_fn,optimizer)
def test(dataloader,model,loss_fn):
size = len(dataloader.dataset)
num_batches = len(dataloader)
model.eval()
test_loss,correct = 0,0
with torch.no_grad():
for x,y in dataloader:
x,y = x.to(device),y.to(device)
pred = model.forward(x)
test_loss += loss_fn(pred,y).item()
correct +=(pred.argmax(1) == y).type(torch.float).sum().item()
a = (pred.argmax(1)==y)
b = (pred.argmax(1)==y).type(torch.float)
test_loss /=num_batches
correct /= size
print(f'test result: \n Accuracy: {(100*correct)}%, Avg loss:{test_loss}')
4 最终代码测试
4.1 SGD优化算法
torch.optim.SGD(model.parameters(),lr=0.01)
代码展示:
import torchprint(torch.__version__)import torch
from torch import nn
from torch.utils.data import DataLoader
from torchvision import datasets
from torchvision.transforms import ToTensor
train_data = datasets.MNIST( root = 'data', train = True, download = True, transform = ToTensor())test_data = datasets.MNIST( root = 'data', train = False, download = True, transform = ToTensor())print(len(train_data))print(len(test_data))from matplotlib import pyplot as pltfigure = plt.figure()for i in range(9): img,label = train_data figure.add_subplot(3,3,i+1) plt.title(label) plt.axis('off') plt.imshow(img.squeeze(),cmap='gray') a = img.squeeze()plt.show()train_dataloader = DataLoader(train_data, batch_size=64)test_dataloader= DataLoader(test_data, batch_size=64)device = 'cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu'print(f'Using {device} device')class NeuralNetwork(nn.Module): def __init__(self): super().__init__() self.flatten = nn.Flatten() self.hidden1 = nn.Linear(28*28,128) self.hidden2 = nn.Linear(128, 256) self.out = nn.Linear(256,10) def forward(self,x): x = self.flatten(x) x = self.hidden1(x) x = torch.sigmoid(x) x = self.hidden2(x) x = torch.sigmoid(x) x = self.out(x) return xmodel = NeuralNetwork().to(device)#print(model)optimizer = torch.optim.SGD(model.parameters(),lr=0.01)loss_fn = nn.CrossEntropyLoss()def train(dataloader,model,loss_fn,optimizer): model.train() batch_size_num = 1 for x,y in dataloader: x,y = x.to(device),y.to(device) pred = model.forward(x) loss = loss_fn(pred,y) optimizer.zero_grad() loss.backward() optimizer.step() loss_value = loss.item() if batch_size_num %100 ==0: print(f'loss: {loss_value:>7f}') batch_size_num +=1def test(dataloader,model,loss_fn): size = len(dataloader.dataset) num_batches = len(dataloader) model.eval() test_loss,correct = 0,0 with torch.no_grad(): for x,y in dataloader: x,y = x.to(device),y.to(device) pred = model.forward(x) test_loss += loss_fn(pred,y).item() correct +=(pred.argmax(1) == y).type(torch.float).sum().item() a = (pred.argmax(1)==y) b = (pred.argmax(1)==y).type(torch.float) test_loss /=num_batches correct /= size print(f'test result: \n Accuracy: {(100*correct)}%, Avg loss:{test_loss}')#train(train_dataloader,model,loss_fn,optimizer)test(test_dataloader,model,loss_fn) 运行结果:
https://i-blog.csdnimg.cn/direct/686694dcb53a4ef49b21f8737d84c10e.png
4.2 Adam优化算法
自适应算法,torch.optim.Adam(model.parameters(),lr=0.01)
运行结果:
https://i-blog.csdnimg.cn/direct/b585e1221fcb4164af8d50e6999d2695.png
4.3 多次迭代
代码展示:
import torchprint(torch.__version__)import torch
from torch import nn
from torch.utils.data import DataLoader
from torchvision import datasets
from torchvision.transforms import ToTensor
train_data = datasets.MNIST( root = 'data', train = True, download = True, transform = ToTensor())test_data = datasets.MNIST( root = 'data', train = False, download = True, transform = ToTensor())print(len(train_data))print(len(test_data))from matplotlib import pyplot as pltfigure = plt.figure()for i in range(9): img,label = train_data figure.add_subplot(3,3,i+1) plt.title(label) plt.axis('off') plt.imshow(img.squeeze(),cmap='gray') a = img.squeeze()plt.show()train_dataloader = DataLoader(train_data, batch_size=64)test_dataloader= DataLoader(test_data, batch_size=64)device = 'cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu'print(f'Using {device} device')class NeuralNetwork(nn.Module): def __init__(self): super().__init__() self.flatten = nn.Flatten() self.hidden1 = nn.Linear(28*28,128) self.hidden2 = nn.Linear(128, 256) self.out = nn.Linear(256,10) def forward(self,x): x = self.flatten(x) x = self.hidden1(x) x = torch.sigmoid(x) x = self.hidden2(x) x = torch.sigmoid(x) x = self.out(x) return xmodel = NeuralNetwork().to(device)#print(model)optimizer = torch.optim.Adam(model.parameters(),lr=0.01)loss_fn = nn.CrossEntropyLoss()def train(dataloader,model,loss_fn,optimizer): model.train() batch_size_num = 1 for x,y in dataloader: x,y = x.to(device),y.to(device) pred = model.forward(x) loss = loss_fn(pred,y) optimizer.zero_grad() loss.backward() optimizer.step() loss_value = loss.item() if batch_size_num %100 ==0: print(f'loss: {loss_value:>7f}') batch_size_num +=1def test(dataloader,model,loss_fn): size = len(dataloader.dataset) num_batches = len(dataloader) model.eval() test_loss,correct = 0,0 with torch.no_grad(): for x,y in dataloader: x,y = x.to(device),y.to(device) pred = model.forward(x) test_loss += loss_fn(pred,y).item() correct +=(pred.argmax(1) == y).type(torch.float).sum().item() a = (pred.argmax(1)==y) b = (pred.argmax(1)==y).type(torch.float) test_loss /=num_batches correct /= size print(f'test result: \n Accuracy: {(100*correct)}%, Avg loss:{test_loss}')#train(train_dataloader,model,loss_fn,optimizer)test(test_dataloader,model,loss_fn)#e = 30for i in range(e): print(f'e: {i+1}\n------------------') train(train_dataloader, model, loss_fn, optimizer)print('done')test(test_dataloader, model, loss_fn) 运行结果:
https://i-blog.csdnimg.cn/direct/1fabc8943d61496ebd4e02ebbcdbe09c.png
免责声明:如果侵犯了您的权益,请联系站长,我们会及时删除侵权内容,谢谢合作!更多信息从访问主页:qidao123.com:ToB企服之家,中国第一个企服评测及商务社交产业平台。
页:
[1]