CIFAR-10数据集由10个类的60000个32*32彩色图像组成,每个类由6000个图像。其中由50000个训练图像和10000个测试图像组成。
数据集分为五个训练批次和一个测试批次,下面采用卷积神经网络对数据集进行分类。
model.py
import torch.nn as nn
import torch.nn.functional as F"""
pytorch Tensor的通道排序:[batch,channel,height,width]
经过卷积后的尺寸大小计算公式:
N=(W-F+2P)/S + 1
(1)图片大小:w*w;
(2)卷积核大小:F*F;(3)步长:s;(4)padding
"""
class LeNet(nn.Module):
def __init__(self):
super(LeNet, self).__init__()
self.conv1 = nn.Conv2d(3,16,5)
self.pool1 = nn.MaxPool2d(2,2)
self.conv2 = nn.Conv2d(16,32,5)
self.pool2 = nn.MaxPool2d(2,2)
self.fc1 = nn.Linear(32*5*5,120)
self.fc2 = nn.Linear(120,84)
self.fc3 = nn.Linear(84,10) # 这次使用的训练集是一个只有十个分类的 分类任务所以这次就是10def forward(self,x):
x = F.relu(self.conv1(x)) # input(3,32,32) output(16,28,28)
x = self.pool1(x)# output(16,14,14)经过最大池化高度和宽度减为原来一半
x = F.relu(self.conv2(x)) # output(32,10,10)
x = self.pool2(x)# output(32,5,5)
x = x.view(-1,32*5*5)# 进行展平操作 output(32*5*5)
x = F.relu(self.fc1(x))#output(120)
x = F.relu(self.fc2(x))#output(84)
x = self.fc3(x)#output(10)
return x
train.py
import torch
import torchvision
import torch.nn as nn
from model import LeNet
import torch.optim as optim
import torchvision.transforms as transformsdef main():
# transform() 对图像进行预处理的函数
transform = transforms.Compose(
[transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])# 50000张训练图片
# 第一次使用时要将download设置为True才会自动去下载数据集
train_set = torchvision.datasets.CIFAR10(root='./cifar10-data', train=True,
download=False, transform=transform)
train_loader = torch.utils.data.DataLoader(train_set, batch_size=36,
shuffle=False, num_workers=0)# 10000张验证图片
# 第一次使用时要将download设置为True才会自动去下载数据集
val_set = torchvision.datasets.CIFAR10(root='./cifar10-data', train=False,
download=False, transform=transform)
val_loader = torch.utils.data.DataLoader(val_set, batch_size=5000,
shuffle=False, num_workers=0)val_data_iter = iter(val_loader)# iter 是转化为一个可以迭代的迭代器
val_image, val_label = val_data_iter.next()# classes = ('plane', 'car', 'bird', 'cat',
#'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
net = LeNet()
net = net.to(device)
loss_function = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=0.001)# 使用Adam优化器"""
标准化:output = (input-0.5)/0.5
反标准化:input = output*0.5+0.5=output/2+0.5
"""for epoch in range(5):# loop over the dataset multiple times;训练5轮running_loss = 0.0# 累加训练过程中的损失
for step, data in enumerate(train_loader, start=0):
# 不仅会返回data,还会返回data所对应的步数。
# get the inputs;
data is a list of [inputs, labels]
inputs, labels = data
inputs, labels = inputs.to(device), labels.to(device)# zero the parameter gradients
optimizer.zero_grad()
"""
为什么每次计算一个batch,就需要调用一次optimizer.zero_grad()?
如果不清除历史梯度,就会对计算的历史梯度进行累加,
"""
# forward + backward + optimize
outputs = net(inputs)
loss = loss_function(outputs, labels)
loss.backward()
optimizer.step()# print statistics
running_loss += loss.item()
if step % 500 == 499:# print every 500 mini-batches
# with是一个上下文管理器,with torch.no_grad(): 接下来的计算中不要计算每个节点的误差损失梯度。
with torch.no_grad():
val_image, val_label = val_image.to(device), val_label.to(device)
outputs = net(val_image)# [batch, 10]
predict_y = torch.max(outputs, dim=1)[1]
# predict_y, val_label).sum() 是一个rensor数据 .item() 获得这个数值
accuracy = torch.eq(predict_y, val_label).sum().item() / val_label.size(0)print('[%d, %5d] train_loss: %.3ftest_accuracy: %.3f' %
(epoch + 1, step + 1, running_loss / 500, accuracy))
running_loss = 0.0print('Finished Training')save_path = './Lenet.pth'
torch.save(net.state_dict(), save_path)if __name__ == '__main__':
main()
分类训练效果显示:
[1,500] train_loss: 1.770test_accuracy: 0.448
[1,1000] train_loss: 1.452test_accuracy: 0.515
[2,500] train_loss: 1.268test_accuracy: 0.564
[2,1000] train_loss: 1.172test_accuracy: 0.597
[3,500] train_loss: 1.063test_accuracy: 0.622
[3,1000] train_loss: 1.008test_accuracy: 0.635
[4,500] train_loss: 0.952test_accuracy: 0.645
[4,1000] train_loss: 0.910test_accuracy: 0.649
[5,500] train_loss: 0.871test_accuracy: 0.655
[5,1000] train_loss: 0.839test_accuracy: 0.668
【分类|LeNet网络模型——CIFAR-10数据集进行分类】最好的效果为:66.8%
推荐阅读
- 深度学习|【深度学习1】Anaconda3的安装和Jupyter的使用
- 自然语言处理|Python 文字转语音(TTS)
- 深度学习|【深度学习】吴恩达深度学习-Course1神经网络与深度学习-第四周深度神经网络的关键概念编程(上)——一步步建立深度神经网络
- 计算机视觉|10分钟学会使用YOLO及Opencv实现目标检测
- 物联网|分类问题的几个评价指标(Precision、Recall、F1-Score、Micro-F1、Macro-F1)
- 深度学习基础知识|深度学习的性能评价指标---图像分类的评价指标
- opencv|基于深度学习的口罩识别与检测PyTorch实现
- 自然语言处理|BERT(5)---实战[BERT+CNN文本分类]
- 智能汽车|三十四.智能驾驶之多传感器融合技术: F-PointNet融合方法