softmax的输入不需要再做非线性变换,即softmax之前不再需要激活函数(relu)。
softmax两个作用:
1、如果在进行softmax前的input有负数,通过指数变换,得到正数。
2、使所有类的概率求和为1。
在多分类问题中,标签y的类型是LongTensor。比如说手写字符0-9分类问题,如果y = torch.LongTensor([3]),对应的one-hot是[0,0,0,1,0,0,0,0,0,0].(这里要注意,如果使用了one-hot,标签y的类型是LongTensor,糖尿病数据集中的target的类型是FloatTensor)
''' 手写字符识别pytorch实现 '''
import torch
from torchvision import transforms, datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F
from tqdm import tqdm
#定义一个cpu
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
# prepare dataset
batch_size = 64
# 图像预处理
transform = transforms.Compose([transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))]) #归一化,两个值是均值和方差
train_dataset = datasets.MNIST(root = 'dataset/mnist/', train = True, download = True, transform = transform)
train_loader = DataLoader(train_dataset, shuffle = True, batch_size = batch_size)
test_dataset = datasets.MNIST(root = 'dataset/mnist/', train = False, download = True, transform = transform)
test_loader = DataLoader(test_dataset, shuffle = False, batch_size = batch_size)
# design model using class
class Net(torch.nn.Module):
def __init__(self):
super(Net, self).__init__()
self.l1 = torch.nn.Linear(28*28, 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):
x = x.view(-1, 784) #将N*1*28*28的图片转换成N*1*784,-1代表N的值,即自动获取mini_batch
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) # 最后一层不做激活,直接接到softmax
model = Net()
model.to(device)
# construct loss and optimizer
criterion = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr = 0.01, momentum = 0.5)
# training cycle forward, backward, update
def train(epoch):
running_loss = 0.0
for batch_idx, data in enumerate(tqdm(train_loader), 0):
inputs, labels = data[0].to(device), data[1].to(device) # 使用gpu训练
optimizer.zero_grad()
#forward + backward + optimize
# 获得模型预测结果(64, 10)
outputs = model(inputs)
# 交叉熵代价函数outputs(64,10),target(64)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
running_loss += loss.item()
if batch_idx % 300 == 299: # 输出每次的平均loss
print('\n [%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[0].to(device), data[1].to(device)
outputs = model(images)
_, predicted = torch.max(outputs.data, dim = 1) #并不关心最大值是多少,用下划线来存,需要在意的是index,
#dim=1表示输出所在行的最大值,若改写成dim=0则输出所在列的最大值。
total += labels.size(0) # N*1
correct += (predicted == labels).sum().item() # 张量之间的比较运算
print('accuracy on test set: %d %% ' % (100*correct/total))
if __name__ == '__main__':
for epoch in range(10):
train(epoch)
test()
参考博客https://blog.csdn.net/bit452/article/details/109686936