【PyTorch深度学习实践】第9讲 多分类问题

处理多分类问题，在神经网络前面的层用Sigmod
在输出层用Sofetmax，可以输出分布，满足输出值大于等于零、和等于一。

如何变成正值且和为1？

NLLLoss

import numpy as np
y = np.array([1, 0, 0])
z = np.array([[0.2, 0.1, -0.1]])
y_pred = np.exp(z)/np.exp(z).sum()
loss = (-y * np.log(y_pred)).sum()
print(loss)

输出结果：0.9729189131256584

CrossEntropyLoss交叉熵损失
LongTensor 长整型张量

import torch
y = torch.LongTensor([0])
z = torch.Tensor([[0.2, 0.1, -0.1]])
criterion = torch.nn.CrossEntropyLoss()
loss = criterion(z, y)
print(loss)

criterion = torch.nn.CrossEntropyLoss()
Y = torch.LongTensor([2, 1, 0])

Y_pred1 = torch.Tensor([[0.1, 0.2, 0.9],
                        [1.1, 0.1, 0.2],
                        [0.2, 2.1, 0.1]])
Y_pred2 = torch.Tensor([[0.8, 0.2, 0.3],
                        [0.2, 0.3, 0.5],
                        [0.2, 0.2, 0.5]])

l1 = criterion(Y_pred1, Y)
l2 = criterion(Y_pred2, Y)
print("Batch Loss1 = ", l1.data, "\nBatch Loss2=", l2.data)

out:
Batch Loss1 = tensor(1.4633)
Batch Loss2= tensor(1.2056)

CrossEntropyLoss <==> LogSoftmax + NLLLoss

数据处理的工具
relu()作为激活函数

0-255 压缩到 0-1
由单通道变成多通道
view()转变成一阶张量
最后一层不做激活

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
# convert the pillow image to tensor
# 神经网络训练时希望输入的数值为比较小 0-1之间 正态分布
transform = transforms.Compose([
    transforms.ToTensor(),
    # 标准化 第一个是均值mean 第二个是标准差std
    transforms.Normalize((0.1307,), (0.3081,))
])
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)


# desigen model
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):
        # -1是自动获取mini_batch
        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)


model = Net()
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)


# train and test
def train(epoch):
    running_loss = 0.0
    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:
        print('[%d, %5d] loss: %.3f' % (epoch + 1, batch_idx + 1, running_loss / 300))
    running_loss = 0.0


def test():
    correct = 0
    total = 0
    # 不会再计算梯度
    with torch.no_grad():
        for data in test_loader:
            images, labels = data
            outputs = model(images)
            # 沿着第一维度最大值及下标
            _, predicted = torch.max(outputs.data, dim=1)
            total += labels.size(0)
            # 张量间的比较运算 求和
            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()