(1)在处理手写数字识别时,要把所有数据集分为10类,这10类的概率之和为1,每一类的概率值大等0,为满足上述条件,引入softmax函数,因为softmax函数可以输出一个分布,每个输出值都大等0,输出值和为1
(2)处理多分类问题时,前面所有激活函数用sigmoid函数,最后一层用softmax函数
softmax函数:指数的幂运算结果大于0,k个分类的值输出为1
(3)多分类问题用NLLLoss损失函数,在softmax层输出后做log计算,然后进入损失函数-ylogy^,损失函数中的log不做计算
(4)交叉熵损失和NLLLoss的区别:
(5)神经网络最后一层不做激活,因为损失函数torch.nn.CrossEntropyLoss中包含了softmax
(6)softmax函数处理手写数字识别的代码如下:
#1、prepare dataset
import torch
from torchvision import transforms
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F
import torch.optim as optim
batch_size = 64
#读图像时用pil,神经网络希望输入的数值比较小,在[-1,1]之间,遵循正态分布
#把[0.255]转变为[0,1]
#R、G、B各是一个通道channel用c表示通道
#图像张量一般是WxHxC,在pytorch中需要转为CxWxH
transform = transforms.Compose([
# convert the PIL Image to tensor,单通道变为多通道
transforms.ToTensor(),
#数据标准化,切换到(0.1)分布,均值mean和标准差std,对MNIST所有像素值计算的结果
transforms.Normalize((0.1307, ), (0.3081, ))
])
train_dataset = datasets.MNIST(root='./mnist/',
train=True,
download=True,
transform=transform)
train_loader = DataLoader(dataset=train_dataset,
shuffle=True,
batch_size=batch_size)
test_dataset = datasets.MNIST(root='./mnist/',
train=False,
download=True,
transform=transform)
test_loader = DataLoader(dataset=test_dataset,
shuffle=False,
batch_size=batch_size
)
#2、Design model using Class
#激活层用Relu
class Net(torch.nn.Module):
def __init__(self):
super(Net, self).__init__()
self.l1 = torch.nn.Linear(784, 512)
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):
# view改变张量的形状
x = x.view(-1, 784)#-1自动计算N,N是有多少个样本,Nx784的矩阵
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)
model = Net()
#最后一层不做激活
#3、construct loss and optimizer
criterion = torch.nn.CrossEntropyLoss()
#带冲量的梯度下降,冲量可以优化训练过程
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)
#4、Training and Test
def train(epoch):
running_loss = 0.0
for batch_idx, data in enumerate(train_loader, 0):
inputs, target = data
optimizer.zero_grad()
outputs = model(inputs)
loss = criterion(outputs, target)
loss.backward()
optimizer.step()
running_loss += loss.item()
if batch_idx % 300 == 299:
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():
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()
输出结果: