B站 刘二大人 传送门 多分类问题
本节使用的数据集是mnist数据集,可根据代码下载,也可自行下载,我开始运行代码下载总是中断,应该是网络问题,看有些同学下了几十次才成功,我试了几次不行就自己百度下载了。只是要用datasets函数处理的话要放到相应目录上。
这里放MNIST数据集介绍及读取,文中是用TensorFlow写的,如果想用Pytorch简单可以简单看一下数据介绍。
上面是mnist数据集截图,手写数字图像的分类数据。每张图片大小都是28*28,本节采用的方法是把像素点平铺成一维,然后用线性+激活+全连接的简单网络进行分类。
import torch
from torch.utils.data import DataLoader
from torchvision import transforms
from torchvision import datasets
import torch.nn.functional as F
batch_size =64
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307, ), (0.3081, ))])
#将原始像素数据归一到(0,1)中 并基于均值0.1307和标准差0.3081来对数据进行标准化处理
train_dataset = datasets.MNIST(root='D:\Code\Pytorch exercise/dataset/mnist', train=True, download=True,transform=transform)
train_loader = DataLoader(train_dataset, shuffle=True,batch_size=batch_size)
#(下载)加载训练集,之后进行batch分组
test_dataset = datasets.MNIST(root='D:\Code\Pytorch exercise/dataset/mnist', train=False,download=True,transform=transform)
test_loader = DataLoader(test_dataset,shuffle=False ,batch_size=batch_size)
#测试集
class Net(torch.nn.Module):
def __init__(self):
super(Net, self).__init__()
self.l1 = torch.nn.Linear(784, 512) #784 = 28 x 28 ,像素点平铺后的大小
self.l2 = torch.nn.Linear(512, 256)
self.l3 = torch.nn.Linear(256, 128)
self.l4 = torch.nn.Linear(128, 64)
self.l5 = torch.nn.Linear(64, 10)
def forward(self, x):
x = x.view(-1, 784)
x = F.relu(self.l1(x))
x = F.relu(self.l2(x))
x = F.relu(self.l3(x))
x = F.relu(self.l4(x))
return self.l5(x) #后面交叉熵计算会有激活的步骤,所以这里直接传线性计算的结果
model = Net()
#---计算损失和更新
criterion = torch.nn.CrossEntropyLoss()#交叉熵 size_average=False
optimizer = torch.optim.SGD(model.parameters(), lr = 0.01, momentum=0.5)
#---计算损失和更新
def train(epoch):
running_loss = 0.0 #计算loss的累积
for batch_idx, data in enumerate(train_loader, 0):
inputs, target = data
optimizer.zero_grad()
#forward + backward + update
outputs = model(inputs)
loss = criterion(outputs, target)
loss.backward()
optimizer.step()
running_loss += loss.item()
if batch_idx % 300 == 299:#每训练300个数据输出一次
print('[%d, %5d] loss: %.3f' % (epoch + 1, batch_idx + 1, running_loss / 300))
running_loss = 0.0
def test():
correct = 0
total = 0
with torch.no_grad():#不计算梯度
for data in test_loader:
images, labels = data
outputs = model(images)
_, predicted = torch.max(outputs.data, dim=1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print('Accuracy on test set: %d %%' % (100 * correct / total))
if __name__ == '__main__':
for epoch in range(10):
train(epoch)
test()