深度学习

前些天发现了一个巨牛的人工智能学习网站 通俗易懂 风趣幽默 忍不住分享一下给大家。点击跳转到网站。

LeNet模型是在1998年提出的一种图像分类模型 应用于支票或邮件编码上的手写数字的识别 也被认为是最早的卷积神经网络(CNN) 为后续CNN的发展奠定了基础 作者LeCun Y也被誉为卷积神经网络之父。LeNet之后一直直到2012年的AlexNet模型在ImageNet比赛上表现优秀 使得沉寂了14年的卷积神经网络再次成为研究热点。

LeCun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.

LeNet模型结构如下

使用torchversion内置的MNIST数据集 训练集大小60000 测试集大小10000 图像大小是1×28×28 包括数字0~9共10个类。官网 http://yann.lecun.com/exdb/mnist/

from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
from torchvision import transforms
import torchvision
mnist_train torchvision.datasets.MNIST(root ./datasets/ ,
 train True, download True, transform transforms.ToTensor())
mnist_test torchvision.datasets.MNIST(root ./datasets/ ,
 train False, download True, transform transforms.ToTensor())
print(len(mnist_train), len(mnist_test)) # 打印训练/测试集大小
feature, label mnist_train[0]
print(feature.shape, label) # 打印图像大小和标签
dataloader DataLoader(mnist_test, batch_size 64, num_workers 0) # 每次批量加载64张
step 0
writer SummaryWriter(log_dir runs/mnist ) # 可视化
for data in dataloader:
 features, labels data
 writer.add_images(tag train , img_tensor features, global_step step)
 step 1
writer.close()

可视化部分可参考我这篇博客 深度学习-Tensorboard可视化面板

此外 还可以使用torchversion内置的FashionMNIST数据集 包括衣服、包等10类图像 也是1×28×28 各60000、10000张。

使用Pytoch进行搭建和测试。

在第一个卷积层C1设置padding为2 因为数据集是28×28大小 原模型是32×32大小。

import torch
from torch import nn, optim

 self.model nn.Sequential( # (-1,1,28,28)
 nn.Conv2d(in_channels 1, out_channels 6, kernel_size 5, padding 2), # (-1,6,28,28)
 nn.Sigmoid(),
 nn.AvgPool2d(kernel_size 2, stride 2), # (-1,6,14,14)
 nn.Conv2d(in_channels 6, out_channels 16, kernel_size 5), # (-1,16,10,10)
 nn.Sigmoid(),
 nn.AvgPool2d(kernel_size 2, stride 2), # (-1,16,5,5)
 nn.Flatten(),
 nn.Linear(in_features 16 * 5 * 5, out_features 120), # (-1,120)
 nn.Sigmoid(),
 nn.Linear(120, 84), # (-1,84)
 nn.Sigmoid(),
 nn.Linear(in_features 84, out_features 10) # (-1,10)
 def forward(self, x):
 return self.model(x)

import torch
import torchvision
from torch.utils.data import DataLoader
from torchvision import transforms
from torch import nn
from torch.utils.tensorboard import SummaryWriter

 self.model nn.Sequential( # (-1,1,28,28)
 nn.Conv2d(in_channels 1, out_channels 6, kernel_size 5, padding 2), # (-1,6,28,28)
 nn.Sigmoid(),
 nn.AvgPool2d(kernel_size 2, stride 2), # (-1,6,14,14)
 nn.Conv2d(in_channels 6, out_channels 16, kernel_size 5), # (-1,16,10,10)
 nn.Sigmoid(),
 nn.AvgPool2d(kernel_size 2, stride 2), # (-1,16,5,5)
 nn.Flatten(),
 nn.Linear(in_features 16 * 5 * 5, out_features 120), # (-1,120)
 nn.Sigmoid(),
 nn.Linear(120, 84), # (-1,84)
 nn.Sigmoid(),
 nn.Linear(in_features 84, out_features 10) # (-1,10)
 def forward(self, x):
 return self.model(x)

device torch.device( cuda if torch.cuda.is_available() else cpu )
leNet leNet.to(device) # 若支持GPU加速
# 损失函数
loss_fn nn.CrossEntropyLoss()
loss_fn loss_fn.to(device)
# 优化器
learning_rate 1e-2
optimizer torch.optim.Adam(leNet.parameters(), lr learning_rate)
total_train_step 0 # 总训练次数
epoch 10 # 训练轮数
writer SummaryWriter(log_dir ./runs/LeNet/ )
mnist_train torchvision.datasets.MNIST(root ./datasets/ ,
 train True, download True, transform transforms.ToTensor())
mnist_test torchvision.datasets.MNIST(root ./datasets/ ,
 train False, download True, transform transforms.ToTensor())
dataloader_train DataLoader(mnist_train, batch_size 64, num_workers 0) # 每次批量加载64张
dataloader_test DataLoader(mnist_test, batch_size 64, num_workers 0) # 每次批量加载64张
for i in range(epoch):
 print( -----第{}轮训练开始----- .format(i 1))
 leNet.train() # 训练模式
 train_loss 0
 for data in dataloader_train:
 imgs, labels data
 imgs imgs.to(device) # 适配GPU/CPU
 labels labels.to(device)
 outputs leNet(imgs)
 loss loss_fn(outputs, labels)
 optimizer.zero_grad() # 清空之前梯度
 loss.backward() # 反向传播
 optimizer.step() # 更新参数
 total_train_step 1 # 更新步数
 train_loss loss.item()
 writer.add_scalar( train_loss_detail , loss.item(), total_train_step)
 writer.add_scalar( train_loss_total , train_loss, i 1)
torch.save(leNet, ./models/LeNet.pkl ) # 保存模型
#leNet torch.load( ./models/LeNet ) 加载模型
writer.close()

插播反爬信息 博主CSDN地址 https://wzlodq.blog.csdn.net/

由于打印了每轮各个批次64张图的损失 不同批次损失不同 所以上下震荡大 但总体仍是减少收敛的。

leNet.eval() # 测试模式
 total_test_loss 0 # 当前轮次模型测试所得损失
 total_accuracy 0 # 当前轮次精确率
 with torch.no_grad(): # 关闭梯度反向传播
 for data in dataloader_test:
 imgs, targets data
 imgs imgs.to(device)
 targets targets.to(device)
 outputs leNet(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
 writer.add_scalar( test_loss , total_test_loss, i 1)
 writer.add_scalar( test_accuracy , total_accuracy/len(mnist_test), i 1)

随着训练轮数增加 对应模型测试的损失减少并收敛。

精确率在几轮后就趋于98%以上 就是说感受到了来自98年的科技~

最后 附完整代码

import torch
import torchvision
from torch.utils.data import DataLoader
from torchvision import transforms
from torch import nn
from torch.utils.tensorboard import SummaryWriter

 self.model nn.Sequential( # (-1,1,28,28)
 nn.Conv2d(in_channels 1, out_channels 6, kernel_size 5, padding 2), # (-1,6,28,28)
 nn.Sigmoid(),
 nn.AvgPool2d(kernel_size 2, stride 2), # (-1,6,14,14)
 nn.Conv2d(in_channels 6, out_channels 16, kernel_size 5), # (-1,16,10,10)
 nn.Sigmoid(),
 nn.AvgPool2d(kernel_size 2, stride 2), # (-1,16,5,5)
 nn.Flatten(),
 nn.Linear(in_features 16 * 5 * 5, out_features 120), # (-1,120)
 nn.Sigmoid(),
 nn.Linear(120, 84), # (-1,84)
 nn.Sigmoid(),
 nn.Linear(in_features 84, out_features 10) # (-1,10)
 def forward(self, x):
 return self.model(x)

device torch.device( cuda if torch.cuda.is_available() else cpu )
leNet leNet.to(device) # 若支持GPU加速
# 损失函数
loss_fn nn.CrossEntropyLoss()
loss_fn loss_fn.to(device)
# 优化器
learning_rate 1e-2
optimizer torch.optim.Adam(leNet.parameters(), lr learning_rate)
total_train_step 0 # 总训练次数
epoch 10 # 训练轮数
writer SummaryWriter(log_dir ./runs/LeNet/ )
mnist_train torchvision.datasets.MNIST(root ./datasets/ ,
 train True, download True, transform transforms.ToTensor())
mnist_test torchvision.datasets.MNIST(root ./datasets/ ,
 train False, download True, transform transforms.ToTensor())
dataloader_train DataLoader(mnist_train, batch_size 64, num_workers 0) # 每次批量加载64张
dataloader_test DataLoader(mnist_test, batch_size 64, num_workers 0) # 每次批量加载64张
for i in range(epoch):
 print( -----第{}轮训练开始----- .format(i 1))
 leNet.train() # 训练模式
 train_loss 0
 for data in dataloader_train:
 imgs, labels data
 imgs imgs.to(device) # 适配GPU/CPU
 labels labels.to(device)
 outputs leNet(imgs)
 loss loss_fn(outputs, labels)
 optimizer.zero_grad() # 清空之前梯度
 loss.backward() # 反向传播
 optimizer.step() # 更新参数
 total_train_step 1 # 更新步数
 train_loss loss.item()
 writer.add_scalar( train_loss , loss.item(), total_train_step)
 writer.add_scalar( train_loss , train_loss, i 1)
 leNet.eval() # 测试模式
 total_test_loss 0 # 当前轮次模型测试所得损失
 total_accuracy 0 # 当前轮次精确率
 with torch.no_grad(): # 关闭梯度反向传播
 for data in dataloader_test:
 imgs, targets data
 imgs imgs.to(device)
 targets targets.to(device)
 outputs leNet(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
 writer.add_scalar( test_loss , total_test_loss, i 1)
 writer.add_scalar( test_accuracy , total_accuracy/len(mnist_test), i 1)
torch.save(leNet, ./models/LeNet.pkl ) # 保存模型
#leNet torch.load( ./models/LeNet ) 加载模型
writer.close()

原创不易 请勿转载 本不富裕的访问量雪上加霜
博主首页 https://wzlodq.blog.csdn.net/
来都来了 不评论两句吗
如果文章对你有帮助 记得一键三连❤

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

更多文章请关注《万象专栏》