多分类和交叉熵:(前面层还是用sigmoid,最后一层用softmax)
-
softmax分类器
-
多分类问题需要满足的条件(离散分类):第一概率要大于0;第二和为1
-
使用交叉熵损失时,神经网络的最后一层是不需要激活的
-
拿到一个图片后,分两步操作:第一步先用transforms.ToTensor():方法将图片转换成PyTorch里的张量;第二步用transforms.Normalize()把其切换到0~1分布,供神经网络进行训练
-
因为神经网络模型比较大了,所以要用更好一点的优化算法,比如说带冲量的momentum=0.5
-
torch.max函数中的dim表示维度:dim=0表示行(矩阵从上到下),dim=1表示列(矩阵从左到右)
import torch
from torchvision import transforms
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F
# 准备数据
batch_size = 64
# 两步走:第一步将训练的图片转换成PyTorch中的张量;第二步转换成0-1分布,供神经网络训练使用
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))])
train_dataset = datasets.MNIST(root='./data/mnist/', train=True, download=False, transform=transform)
train_dataloder = DataLoader(dataset=train_dataset, shuffle=True, batch_size=batch_size)
test_dataset = datasets.MNIST(root='./data/mnist/', train=False, download=False, transform=transform)
test_dataloder = DataLoader(dataset=test_dataset, shuffle=False, batch_size=batch_size)
# 构建模型
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):
x = x.view(-1, 784) # 将矩阵拉直成一个一行的向量,总共有784列;-1表示动态调整元素个数
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) # 前四层需要激活,最后一层不需要激活
# 实例化
model = Net()
# 损失和优化器
criterion = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=0.01, momentum=0.5)
# 封装训练方法和测试方法
def train(epoc):
running_loss = 0.0
for batch_index, data in enumerate(train_dataloder, 0):
inputs, target = data
y_pred = model(inputs)
loss = criterion(y_pred, target)
optimizer.zero_grad()
loss.backward()
optimizer.step()
running_loss += loss.item()
if batch_index % 300 == 299:
print('[%d,%5d] loss: %.3f' % (epoc + 1, batch_index + 1, running_loss / 300))
running_loss = 0.0
def test():
correct = 0
total = 0
with torch.no_grad():
for data in test_dataloder:
images, labels = data
outputs = model(images)
# 求出每一行最大值的下标
_, predicted = torch.max(outputs.data, dim=1) # dim=0表示行(矩阵从上到下),dim=1表示列(矩阵从左到右)
total += labels.size(0) # labels是一个(N,1)的元组
correct += (predicted == labels).sum().item()
print('Accuracy on testset %d %%' % (100 * correct / total))
if __name__ == '__main__':
for epoc in range(10):
train(epoc)
test()