《PyTorch深度学习实践》P9多分类问题（softmax）

全部代码在最后面。
softmax：处理多分类
①概率和为1
②各个概率都＞=0

softmax例子：
softmax对应的损失函数：

code：

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)

效果图：

torch里面有：交叉熵损失，包含了softmax，loss

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)

效果图：

样例：

code：

import torch

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

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, 2.1, 0.5]])

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

图像处理：


code：

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
# 拿到一个图像，先ToTensor变为张量，做一个normalize把它变为0-1分布，然后再用神经网络
transforms = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.1307, ), (0.3081, )) # 第一个(0.1307, )是均值，第二个是标准差
])

train_dataset = datasets.MNIST(root='../dataset/mnist',
                               train=True,
                               download=True,
                               transform=transforms)
train_loader = DataLoader(train_dataset,
                          shuffle=True,
                          batch_size=batch_size)

test_dataset = datasets.MNIST(root='../dataset/mnist',
                              train=False,
                              download=True,
                              transform=transforms)
test_loader = DataLoader(test_dataset,
                         shuffle=False,
                         batch_size=batch_size)

模型图：
# 交叉熵损失，经过softmax

code：

criterion = torch.nn.CrossEntropyLoss()

train部分：
train把一轮循环封装为函数
test部分：

总的code：

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
# 拿到一个图像，先ToTensor变为张量，做一个normalize把它变为0-1分布，然后再用神经网络
transforms = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.1307, ), (0.3081, )) # 第一个(0.1307, )是均值，第二个是标准差
])

train_dataset = datasets.MNIST(root='../dataset/mnist',
                               train=True,
                               download=True,
                               transform=transforms)
train_loader = DataLoader(train_dataset,
                          shuffle=True,
                          batch_size=batch_size)

test_dataset = datasets.MNIST(root='../dataset/mnist',
                              train=False,
                              download=True,
                              transform=transforms)
test_loader = DataLoader(test_dataset,
                         shuffle=False,
                         batch_size=batch_size)

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) # 把图片变为矩阵
        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()
# 交叉熵损失，经过softmax
criterion = torch.nn.CrossEntropyLoss()
# 模型有点大，所以用带有冲量（momentum）的
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)

# train把一轮循环封装为函数

def train(epoch):
    running_loss = 0.0
    for batch_idx, data in enumerate(train_loader, 0):
#        X:inputs,Y:target
        inputs, target = data
        optimizer.zero_grad()

        # 前向+反向+更新
        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
# test 不用算梯度 with torch.no_grad():
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) # 算每一行最大值的下标是多少，其实也代表了每一行的分类 / max返回 每一行最大值是多少，每一行最大值的下标是多少
            total += labels.size(0)
            correct += (predicted == labels).sum().item() # ==预测的和原来的作比较，真为1，假为0，再总的加起来，求和后再把这个标量提出来
    print('Accuracy on test set: %d %%' % (100 * correct / total))

if __name__ == '__main__':
    for epoch in range(10):
    # 一轮训练一轮测试
        train(epoch)
        test()

效果图: