在前面已经引入了Fashion-MNIST数据集,并设置数据迭代器的批量大小为256
import torch
from IPython import display
# IPython是一个python的交互式shell,支持交互式数据可视化
from d2l import torch as d2l
batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)
num_inputs = 784
num_outputs = 10
# 数据集有10个类别,所以网络输出维度为10
W = torch.normal(0, 0.01, size=(num_inputs, num_outputs), requires_grad=True)
# 权重
b = torch.zeros(num_outputs, requires_grad=True)
# 偏置
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
# 广播机制在一些情况下可以节省代码量,比如一个mn的矩阵加减乘除一个1*n的矩阵,则计算过程中1*n的矩阵会被复制m次,成为一个mn的矩阵,然后再逐项作操作;即不够的位会自动补全
def cross_entropy(y_hat, y):
return - torch.log(y_hat[range(len(y_hat)), y])
cross_entropy(y_hat, y)
当预测与标签分类y一致时,它们是正确的。分类准确率即正确预测数量与总预测数量之比。虽然直接优化准确率可能很困难(因为准确率的计算不可导),但准确率通常是我们最关心的性能衡量标准,我们在训练分类器时几乎总是会报告它。
为了计算准确率,我们执行以下操作。首先,如果y_hat是矩阵,那么假定第二个维度存储每个类的预测分数。我们使用argmax获得每行中最大元素的索引来获得预测类别。然后我们将预测类别与真实y元素进行比较。由于等式运算符“==”对数据类型很敏感,因此我们将y_hat的数据类型转换为与y的数据类型一致。结果是一个包含0(错)和1(对)的张量。进行求和会得到正确预测的数量。
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())
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 = 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]
class Accumulator: #@save
"""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)。"""
# 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)
# 累加器
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())
# numel 返回元素个数
# 返回训练损失和训练准确率
return metric[0] / metric[2], metric[1] / metric[2]
class Animator: #@save
"""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)
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_acc
# assert函数是断言函数,是对表达式布尔值的判断
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): #@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))
# argmax是对函数求参数集合的函数
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)
# 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);
loss = nn.CrossEntropyLoss()
trainer = torch.optim.SGD(net.parameters(), lr=0.1)
num_epochs = 10
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, trainer)