LeNet-5
LeNet-5是一个较简单的卷积神经网络。输入的二维图像，先经过两次卷积层到池化层，再经过全连接层，最后使用softmax分类作为输出层。
1、INPUT层-输入层
输入图像的尺寸统一归一化为32*32。
2、C1层-卷积层
3、S2层-池化层（下采样层）
采样方式：4个输入相加，乘以一个可训练参数，再加上一个可训练偏置。结果通过sigmoid
4、C3层-卷积层
第二次卷积的输出是C3，16个10x10的特征图，卷积核大小是 5*5.
C3与S2中前3个图相连的卷积结构如图所示：
采用上述这样的组合了？论文中说有两个原因：1）减少参数，2）这种不对称的组合连接的方式有利于提取多种组合特征。
5、S4层-池化层（下采样层）
S4是pooling层，窗口大小仍然是2*2，C3层的16个10x10的图分别进行以2x2为单位的池化得到16个5x5的特征图。有5x5x5x16=2000个连接。连接的方式与S2层类似。
6、C5层-卷积层
7、F6层-全连接层
8、Output层-全连接层
采用的是径向基函数（RBF）的网络连接方式
环境配置
anaconda配置python3.6环境
数据准备
import torchvision.datasets as datasets
root='data', # 表示数据的加载的根目录
train=True, # True表示加载数据库的训练集，false加载测试集
transform=torchvision.transform.Totensor()) # 表示对数据进行预处理转换为Totensor类型，none为不进行预处理
download=True, # True表示自动下载数据集
完整代码 如下（Lenet-5网络测试MNIST数据集）
import torch
import torch.nn as nn
import torchvision
from setuptools import dist
from torch.nn import Sequential, Conv2d, BatchNorm2d, ReLU, MaxPool2d
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
import time
#定义训练的设备
device = torch.device("cuda:0")
#准备数据集
train_data = torchvision.datasets.MNIST(root='Mnist',train=True,transform=torchvision.transforms.ToTensor(),
download=True) #训练数据集
test_data = torchvision.datasets.MNIST(root='./mnist/', train=False, transform=torchvision.transforms.ToTensor(),
download=True) #测试数据集
# length 长度
train_data_size = len(train_data)
test_data_size = len(test_data)
print("训练数据集的长度为：{}".format(train_data_size))
print("测试数据集的长度为：{}".format(test_data_size))
# 利用 DataLoader 来加载数据集
train_dataloader = DataLoader(train_data, batch_size=64)
test_dataloader = DataLoader(test_data, batch_size=64)
# 搭建神经网络
class LetNet5(nn.Module):
def __init__(self):
super(LetNet5, self).__init__()
self.model1 = Sequential(
Conv2d(1, 6, 5, 1, padding=2),
BatchNorm2d(6),
ReLU(),
MaxPool2d(kernel_size=2, stride=2),
Conv2d(6, 16, 5),
BatchNorm2d(16),
ReLU(),
MaxPool2d(kernel_size=2, stride=2),
Conv2d(16, 120, 5),
BatchNorm2d(120),
ReLU()
)
self.model2 = Sequential(
nn.Linear(120, 84),
nn.ReLU(),
nn.Linear(84, 10),
nn.LogSoftmax()
)
def forward(self, x):
x = self.model1(x)
x = x.reshape(x.size(0), -1) # 降维
x = self.model2(x)
return x
# 搭建网络模型
model = LetNet5()
model = model.to(device)
# 损失函数
criterion = nn.CrossEntropyLoss()
criterion = criterion.to(device)
# 优化器
learning_rate = 1e-3
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
# 添加tensorboard
writer = SummaryWriter('logs_LeNet')
# 测试的总次数
total_step = len(train_dataloader)
# 记录训练的次数
total_train_step = 0
# 记录测试的次数
total_test_step = 0
# 训练的轮数
epoch = 50
start_time = time.time() #记录开始时间
for i in range(epoch):
print("-----第 {} 次训练开始-----".format(i+1))
# 训练步骤开始
model.train()
for data in train_dataloader:
imgs, targets = data
imgs = imgs.to(device)
targets = targets.to(device)
outputs = model(imgs)
loss = criterion(outputs, targets)
# 优化器优化模型
optimizer.zero_grad()
loss.backward()
optimizer.step()
total_train_step = total_train_step + 1
if total_train_step % 100 == 0:
end_time = time.time() #记录结束时间
print('训练的时间： ' + str(end_time - start_time))
print("训练次数： {}， loss： {}".format(total_train_step, loss.item()))
writer.add_scalar("train_loss", loss.item(), total_train_step)
# 测试步骤开始
model.eval()
total_test_loss = 0
total_accuracy = 0
with torch.no_grad():
for data in test_dataloader:
imgs, targets = data
imgs = imgs.to(device)
targets = targets.to(device)
outputs = model(imgs)
loss = criterion(outputs, targets)
total_test_loss = total_test_loss + loss.item()
accuracy = (outputs.argmax(1) == targets).sum()
total_accuracy = total_accuracy + accuracy
print("整体测试集上的loss： {}".format(total_test_loss))
print("整体测试集上的正确率： {}".format(total_accuracy/test_data_size))
writer.add_scalar("test_loss", total_test_loss, total_test_step)
writer.add_scalar("test_accuracy", total_accuracy/test_data_size, total_test_step)
total_test_step = total_test_step + 1
torch.save(model, "img_{}.pth".format(i))
print("模型已保存")
writer.close()
VGG网络训练cifar10数据集
import torchvision
import torch
from torch.nn import Sequential, Conv2d, MaxPool2d, Flatten, Linear
from torch.utils.data import DataLoader
import torch.nn.functional as F
from torch import nn
from torch.utils.tensorboard import SummaryWriter
#定义训练的设备
device = torch.device("cuda:0")
#准备数据集
train_data = torchvision.datasets.CIFAR10(root= "data", train=True, transform=torchvision.transforms.ToTensor(),
download=True) #训练数据集
test_data = torchvision.datasets.CIFAR10(root="data", train=False, transform=torchvision.transforms.ToTensor(),
download=True) #测试数据集
# length 长度
train_data_size = len(train_data)
test_data_size = len(test_data)
print("训练数据集的长度为：{}".format(train_data_size))
print("测试数据集的长度为：{}".format(test_data_size))
# 利用 DataLoader 来加载数据集
train_dataloader = DataLoader(train_data, batch_size=64)
test_dataloader = DataLoader(test_data, batch_size=64)
# 搭建神经网络
class Img_clarrification(nn.Module):
def __init__(self):
super(Img_clarrification,self).__init__()
self.conv1 = nn.Conv2d(3,64,3,padding=1)
self.conv2 = nn.Conv2d(64,64,3,padding=1)
self.pool1 = nn.MaxPool2d(2, 2)
self.bn1 = nn.BatchNorm2d(64)
self.relu1 = nn.ReLU()
self.conv3 = nn.Conv2d(64,128,3,padding=1)
self.conv4 = nn.Conv2d(128, 128, 3,padding=1)
self.pool2 = nn.MaxPool2d(2, 2, padding=1)
self.bn2 = nn.BatchNorm2d(128)
self.relu2 = nn.ReLU()
self.conv5 = nn.Conv2d(128,128, 3,padding=1)
self.conv6 = nn.Conv2d(128, 128, 3,padding=1)
self.conv7 = nn.Conv2d(128, 128, 1,padding=1)
self.pool3 = nn.MaxPool2d(2, 2, padding=1)
self.bn3 = nn.BatchNorm2d(128)
self.relu3 = nn.ReLU()
self.conv8 = nn.Conv2d(128, 256, 3,padding=1)
self.conv9 = nn.Conv2d(256, 256, 3, padding=1)
self.conv10 = nn.Conv2d(256, 256, 1, padding=1)
self.pool4 = nn.MaxPool2d(2, 2, padding=1)
self.bn4 = nn.BatchNorm2d(256)
self.relu4 = nn.ReLU()
self.conv11 = nn.Conv2d(256, 512, 3, padding=1)
self.conv12 = nn.Conv2d(512, 512, 3, padding=1)
self.conv13 = nn.Conv2d(512, 512, 1, padding=1)
self.pool5 = nn.MaxPool2d(2, 2, padding=1)
self.bn5 = nn.BatchNorm2d(512)
self.relu5 = nn.ReLU()
self.fc14 = nn.Linear(512*4*4,1024)
self.drop1 = nn.Dropout2d()
self.fc15 = nn.Linear(1024,1024)
self.drop2 = nn.Dropout2d()
self.fc16 = nn.Linear(1024,10)
def forward(self,x):
x = self.conv1(x)
x = self.conv2(x)
x = self.pool1(x)
x = self.bn1(x)
x = self.relu1(x)
x = self.conv3(x)
x = self.conv4(x)
x = self.pool2(x)
x = self.bn2(x)
x = self.relu2(x)
x = self.conv5(x)
x = self.conv6(x)
x = self.conv7(x)
x = self.pool3(x)
x = self.bn3(x)
x = self.relu3(x)
x = self.conv8(x)
x = self.conv9(x)
x = self.conv10(x)
x = self.pool4(x)
x = self.bn4(x)
x = self.relu4(x)
x = self.conv11(x)
x = self.conv12(x)
x = self.conv13(x)
x = self.pool5(x)
x = self.bn5(x)
x = self.relu5(x)
x = x.view(-1,512*4*4)
x = F.relu(self.fc14(x))
x = self.drop1(x)
x = F.relu(self.fc15(x))
x = self.drop2(x)
x = self.fc16(x)
return x
# 搭建网络模型
img_clarrification = Img_clarrification()
img_clarrification = img_clarrification.to(device)
# 损失函数
loss_fn = nn.CrossEntropyLoss()
loss_fn = loss_fn.to(device)
# 优化器
learning_rate = 1e-2
optimizer = torch.optim.SGD(img_clarrification.parameters(), lr=learning_rate)
# 设置训练网络的一些参数
# 记录训练的次数
total_train_step = 0
# 记录测试的次数
total_test_step = 0
# 训练的轮数
epoch = 25
# 添加tensorboard
writer = SummaryWriter("logs_vggnet")
for i in range(epoch):
print("-----第 {} 次训练开始-----".format(i+1))
# 训练步骤开始
img_clarrification.train()
for data in train_dataloader:
imgs, targets = data
imgs = imgs.to(device)
targets = targets.to(device)
outputs = img_clarrification(imgs)
loss = loss_fn(outputs, targets)
# 优化器优化模型
optimizer.zero_grad()
loss.backward()
optimizer.step()
total_train_step = total_train_step + 1
if total_train_step % 100 == 0:
print("训练次数： {}， loss： {}".format(total_train_step, loss.item()))
writer.add_scalar("train_loss", loss.item(), total_train_step)
# 测试步骤开始
img_clarrification.eval()
total_test_loss = 0
total_accuracy = 0
with torch.no_grad():
for data in test_dataloader:
imgs, targets = data
imgs = imgs.to(device)
targets = targets.to(device)
outputs = img_clarrification(imgs)
loss = loss_fn(outputs, targets)
total_test_loss = total_test_loss + loss.item()
accuracy = (outputs.argmax(1) == targets).sum()
total_accuracy = total_accuracy + accuracy
print("整体测试集上的loss： {}".format(total_test_loss))
print("整体测试集上的正确率： {}".format(total_accuracy/test_data_size))
writer.add_scalar("test_loss", total_test_loss, total_test_step)
writer.add_scalar("test_accuracy", total_accuracy/test_data_size, total_test_step)
total_test_step = total_test_step + 1
torch.save(img_clarrification, "img_{}.pth".format(i))
print("模型已保存")
writer.close()
516
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
