李沐-softmax+损失函数+图片分类数据集

softmax

分类 vs 回归
一位有效编码：one-hot

softmax

交叉熵
交叉熵用来衡量两个概率的区别


总结

损失函数

L2Loss均方损失
当y=0时，蓝色线表示函数曲线，橙色表梯度线，不同的地方梯度的值不同，更新的速度也不同

L1Loss

huber loss

图像分类数据集

transforms.ToTensor()将图片转为torch的tensor格式
download从网上下载
train是否为训练集
mnist_train[0][0].shape#torch.Size([1,28,28])
#第一个0是example，第二个0是第一张图片
加载小批量数据

测试一下时间，这一部分会产生性能瓶颈

数据读取

softmax从零开始实现

0. 先得到dataloader（加载batch_size)个数据

import torch
from IPython import display
from d2l import torch as d2l

batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)

1. 初始化模型参数

num_inputs = 784 #28*28*1
num_outputs = 10#10分类

W = torch.normal(0, 0.01, size=(num_inputs, num_outputs), requires_grad=True)
b = torch.zeros(num_outputs, requires_grad=True)

2. 定义softmax操作
   
   二维数组，一行代表一个样本，每一行的数据代表结果为不同分类的概率，即每一行的结果和为1

def softmax(X):
    X_exp = torch.exp(X)
    partition = X_exp.sum(1, keepdim=True)
    return X_exp / partition  # 这里应用了广播机制

3. 定义模型

def net(X):
    return softmax(torch.matmul(X.reshape((-1, W.shape[0])), W) + b)

4. 定义损失函数
   demo

y = torch.tensor([0, 2])
y_hat = torch.tensor([[0.1, 0.3, 0.6], [0.3, 0.2, 0.5]])
y_hat[[0, 1], y]

结果为：tensor([0.1000, 0.5000])

def cross_entropy(y_hat, y):
    return -torch.log(y_hat[range(len(y_hat)), y])

cross_entropy(y_hat, y)

交叉熵损失

5. 分类准确率定义

def accuracy(y_hat, y):  #@save
    """计算预测正确的数量。"""
    if len(y_hat.shape) > 1 and y_hat.shape[1] > 1:
        y_hat = y_hat.argmax(axis=1)
    cmp = y_hat.type(y.dtype) == y
    return float(cmp.type(y.dtype).sum())
    
def evaluate_accuracy(net, data_iter):  #@save
    """计算在指定数据集上模型的精度。"""
    if isinstance(net, torch.nn.Module):
        net.eval()  # 将模型设置为评估模式
    metric = d2l.Accumulator(2)  # 正确预测数、预测总数
    for X, y in data_iter:
        metric.add(accuracy(net(X), y), y.numel())
    return metric[0] / metric[1]

net.eval()评估模式，不格外算梯度之类的
Accumulator是d2l实现的累计类
6. 训练

def train_epoch_ch3(net, train_iter, loss, updater):  #@save
    """训练模型一个迭代周期（定义见第3章）。"""
    # 将模型设置为训练模式
    if isinstance(net, torch.nn.Module):
        net.train()
    # 训练损失总和、训练准确度总和、样本数
    metric = Accumulator(3)
    for X, y in train_iter:
        # 计算梯度并更新参数
        y_hat = net(X)
        l = loss(y_hat, y)
        if isinstance(updater, torch.optim.Optimizer):
            # 使用PyTorch内置的优化器和损失函数
            updater.zero_grad()
            l.backward()
            updater.step()
            metric.add(
                float(l) * len(y), accuracy(y_hat, y),
                y.size().numel())
        else:
            # 使用定制的优化器和损失函数
            l.sum().backward()
            updater(X.shape[0])
            metric.add(float(l.sum()), accuracy(y_hat, y), y.numel())
    # 返回训练损失和训练准确率
    return metric[0] / metric[2], metric[1] / metric[2]

def train_ch3(net, train_iter, test_iter, loss, num_epochs, updater):  #@save
    """训练模型（定义见第3章）。"""
    animator = Animator(xlabel='epoch', xlim=[1, num_epochs], ylim=[0.3, 0.9],
                        legend=['train loss', 'train acc', 'test acc'])
    for epoch in range(num_epochs):
        train_metrics = train_epoch_ch3(net, train_iter, loss, updater)
        test_acc = evaluate_accuracy(net, test_iter)
        animator.add(epoch + 1, train_metrics + (test_acc,))
    train_loss, train_acc = train_metrics
    assert train_loss < 0.5, train_loss
    assert train_acc <= 1 and train_acc > 0.7, train_acc
    assert test_acc <= 1 and test_acc > 0.7, test_acc

7. 优化器

lr = 0.1

def updater(batch_size):
    return d2l.sgd([W, b], lr, batch_size)
   

def sgd(params, lr, batch_size):  #@save
    """小批量随机梯度下降。"""
    with torch.no_grad():
        for param in params:
            param -= lr * param.grad / batch_size
            param.grad.zero_()

num_epochs = 10
train_ch3(net, train_iter, test_iter, cross_entropy, num_epochs, updater)

8. 预测

def predict_ch3(net, test_iter, n=6):  #@save
    """预测标签（定义见第3章）。"""
    for X, y in test_iter:
        break
    trues = d2l.get_fashion_mnist_labels(y)
    preds = d2l.get_fashion_mnist_labels(net(X).argmax(axis=1))
    titles = [true + '\n' + pred for true, pred in zip(trues, preds)]
    d2l.show_images(X[0:n].reshape((n, 28, 28)), 1, n, titles=titles[0:n])

predict_ch3(net, test_iter)

api调用

import torch
from torch import nn
from d2l import torch as d2l

batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)

注意

train_iter是将dataset的数据（整个数据集）以每batch_size个放到dataloader中了
1.初始化模型参数

# PyTorch不会隐式地调整输入的形状。因此，
# 我们在线性层前定义了展平层（flatten），来调整网络输入的形状
net = nn.Sequential(nn.Flatten(), nn.Linear(784, 10))

def init_weights(m):
    if type(m) == nn.Linear:
        nn.init.normal_(m.weight, std=0.01)

net.apply(init_weights);

2.softmax、交叉熵损失
将softmax和交叉熵结合在一起

loss = nn.CrossEntropyLoss()

3.优化算法

trainer = torch.optim.SGD(net.parameters(), lr=0.1)

4.训练

num_epochs = 10
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, trainer)