李沐大神b站官方视频
08 softmax回归
1)从零实现:
import torch
from IPython import display
from d2l import torch as d2l
#实现softmax函数
def softmax(X):
X_exp = torch.exp(X)
partition = X_exp.sum(1, keepdim=True) #每一行加起来,再通过广播机制得到softmax结果
return X_exp / partition # 这里应用了广播机制
#定义输入如何通过网络映射到输出
def net(X):
#torch.matmul函数来对输入X与w进行矩阵乘法,并加上bias
#reshape中-1表示让函数帮忙计算此维度的大小(其实等于batch_size),W.shape[0] = 784
return softmax(torch.matmul(X.reshape((-1, W.shape[0])), W) + b)
#实现交叉熵损失函数
def cross_entropy(y_hat, y):
return - torch.log(y_hat[range(len(y_hat)), y])
#计算预测精度
def accuracy(y_hat, y):
"""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) #取出每个样本最大预测值的下标
cmp = y_hat.type(y.dtype) == y #通过比较得到矩阵
return float(cmp.type(y.dtype).sum()) #返回预测正确的总数
"""计算在指定数据集上模型的精度"""
def evaluate_accuracy(net, data_iter):
if isinstance(net, torch.nn.Module):
net.eval() # 将模型设置为评估模式
metric = Accumulator(2) # 正确预测数、预测总数
with torch.no_grad():
for X, y in data_iter: #通过累加器记录正确预测数和预测总数
metric.add(accuracy(net(X), y), y.numel())
return metric[0] / metric[1]
class Accumulator:
"""在n个变量上累加"""
def __init__(self, n):
self.data = [0.0] * n
def add(self, *args):
self.data = [a + float(b) for a, b in zip(self.data, args)]
def reset(self):
self.data = [0.0] * len(self.data)
def __getitem__(self, idx):
return self.data[idx]
class Animator:
"""在动画中绘制数据"""
def __init__(self, xlabel=None, ylabel=None, legend=None, xlim=None,
ylim=None, xscale='linear', yscale='linear',
fmts=('-', 'm--', 'g-.', 'r:'), nrows=1, ncols=1,
figsize=(3.5, 2.5)):
# 增量地绘制多条线
if legend is None:
legend = []
d2l.use_svg_display()
self.fig, self.axes = d2l.plt.subplots(nrows, ncols, figsize=figsize)
if nrows * ncols == 1:
self.axes = [self.axes, ]
# 使用lambda函数捕获参数
self.config_axes = lambda: d2l.set_axes(
self.axes[0], xlabel, ylabel, xlim, ylim, xscale, yscale, legend)
self.X, self.Y, self.fmts = None, None, fmts
def add(self, x, y):
# 向图表中添加多个数据点
if not hasattr(y, "__len__"):
y = [y]
n = len(y)
if not hasattr(x, "__len__"):
x = [x] * n
if not self.X:
self.X = [[] for _ in range(n)]
if not self.Y:
self.Y = [[] for _ in range(n)]
for i, (a, b) in enumerate(zip(x, y)):
if a is not None and b is not None:
self.X[i].append(a)
self.Y[i].append(b)
self.axes[0].cla()
for x, y, fmt in zip(self.X, self.Y, self.fmts):
self.axes[0].plot(x, y, fmt)
self.config_axes()
display.display(self.fig)
display.clear_output(wait=True)
"""训练模型一个迭代周期"""
def train_epoch_ch3(net, train_iter, loss, updater):
# 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)
#判断使用的是否是内置的优化器
if isinstance(updater, torch.optim.Optimizer):
# 使用PyTorch内置的优化器和损失函数
updater.zero_grad()
l.mean().backward()
updater.step()
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精度
return metric[0] / metric[2], metric[1] / metric[2]
#实现训练模型的过程
def train_ch3(net, train_iter, test_iter, loss, num_epochs, updater):
"""训练模型"""
#创建一个可视化的小工具
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
#定义优化算法
def updater(batch_size):
return d2l.sgd([W, b], lr, batch_size)
#定义预测函数
def predict_ch3(net, test_iter, n=6):
"""预测标签"""
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])
batch_size = 256
#调用上节课所学的函数来读取训练集和测试集
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)
#初始化模型参数
num_inputs = 784
num_outputs = 10
W = torch.normal(0, 0.01, size=(num_inputs, num_outputs), requires_grad=True)
b = torch.zeros(num_outputs, requires_grad=True)
lr = 0.1
#训练模型
num_epochs = 10
train_ch3(net, train_iter, test_iter, cross_entropy, num_epochs, updater)
predict_ch3(net, test_iter)
2)简洁实现:
import torch
from torch import nn
from d2l import torch as d2l
#初始化参数的函数
def init_weights(m):
#如果使用的是nn里的模型,则对其初始化
if type(m) == nn.Linear:
nn.init.normal_(m.weight, std=0.01)
#读取数据集
batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)
#定义模型
# 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))
#初始化模型参数
net.apply(init_weights);
#定义损失函数
loss = nn.CrossEntropyLoss(reduction='none')
#定义优化算法
trainer = torch.optim.SGD(net.parameters(), lr=0.1)
#训练模型
num_epochs = 10
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, trainer)