就像我们从零开始实现线性回归一样, 你应该知道实现softmax的细节
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)
#将展平每个图像,把它们看作长度为784的向量。 因为我们的数据集有10个类别,所以网络输出维度为 10
num_inputs = 784 #图片(1,28,28) 拉成一个向量
num_outputs = 10
#权重、偏移
W = torch.normal(0, 0.01, size=(num_inputs, num_outputs), requires_grad=True)
b = torch.zeros(num_outputs, requires_grad=True)
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
def net(X):
return softmax(torch.matmul(X.reshape((-1, W.shape[0])), W) + b)
交叉熵 = -log(预测的类别的概率)
def cross_entropy(y_hat, y):
return -torch.log(y_hat[range(len(y_hat)), y])
y
元素进行比较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)
cmp = y_hat.type(y.dtype) == y
return float(cmp.type(y.dtype).sum())
net
的准确率def evaluate_accuracy(net, data_iter):
"""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 = Accumulator(2) # 正确预测数、预测总数
for X, y in data_iter: #没拿到一批数
metric.add(accuracy(net(X), y), y.numel()) #accuracy(net(X),正确预测数 y)y.numel()样本总数,叠加器,不断累加
return metric[0] / metric[1]
Accumulator
实例中创建了 2 个变量,用于分别存储正确预测的数量和预测的总数量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]
def train_epoch_ch3(net, train_iter, loss, updater):
"""训练模型一个迭代周期(定义见第3章)。"""
if isinstance(net, torch.nn.Module): #NN告诉我们考试训练数据
net.train()
metric = Accumulator(3) #3个位置的叠加器,来累加信息
for X, y in train_iter:
y_hat = net(X)
l = loss(y_hat, y)
if isinstance(updater, torch.optim.Optimizer):
updater.zero_grad()
l.backward()
updater.step() #参数自更新
metric.add(
float(l) * len(y), accuracy(y_hat, y),
y.size().numel())
else:
l.sum().backward()
updater(X.shape[0])
metric.add(float(l.sum()), accuracy(y_hat, y), y.numel())
return metric[0] / metric[2], metric[1] / metric[2]
In [16]:
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)):
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,]
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):
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)
def train_ch3(net, train_iter, test_iter, loss, num_epochs, updater):
"""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_ac
lr = 0.1
def updater(batch_size):
return d2l.sgd([W, b], lr, batch_size)
num_epochs = 10
train_ch3(net, train_iter, test_iter, cross_entropy, num_epochs, updater)
def predict_ch3(net, test_iter, n=6):
"""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)
X = torch.tensor([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0]])
X.sum(0, keepdim=True), X.sum(1, keepdim=True)
(tensor([[5., 7., 9.]]),
tensor([[ 6.],
[15.]]))
我们将每个元素变成一个非负数。此外,依据概率原理,每行总和为1
def softmax(X):
X_exp = torch.exp(X)
partition = X_exp.sum(1, keepdim=True)
return X_exp / partition
X = torch.normal(0, 1, (2, 5))
X_prob = softmax(X)
X_prob, X_prob.sum(1)
(tensor([[0.0599, 0.1886, 0.5760, 0.1060, 0.0695],
[0.3192, 0.2758, 0.0286, 0.0575, 0.3189]]),
tensor([1.0000, 1.0000]))
创建一个数据y_hat,其中包含2个样本在3个类别的预测概率, 使用y作为y_hat中概率的索引
下面,我们创建一个数据y_hat,其中包含2个样本在3个类别的预测概率,它们对应的标签y。 有了y,我们知道在第一个样本中,第一类是正确的预测,而在第二个样本中,第三类是正确的预测。 然后使用y作为y_hat中概率的索引,我们选择第一个样本中第一个类的概率和第二个样本中第三个类的概率。
y = torch.tensor([0, 2])
#[0.1, 0.3, 0.6] 第0样本的预测值
y_hat = torch.tensor([[0.1, 0.3, 0.6], [0.3, 0.2, 0.5]])
y_hat[[0, 1], y] #拿出下标 #这里是y_hat第一列拿第0个,第二列拿第二个
Out[8]:
tensor([0.1000, 0.5000])
实现交叉熵损失函数
In [9]:
def cross_entropy(y_hat, y):
return -torch.log(y_hat[range(len(y_hat)), y])
cross_entropy(y_hat, y)
Out[9]:
tensor([2.3026, 0.6931])
将预测类别与真实 y
元素进行比较
In [11]:
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)
cmp = y_hat.type(y.dtype) == y
return float(cmp.type(y.dtype).sum())
accuracy(y_hat, y) / len(y)
Out[11]:
0.5