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)
Backend Qt5Agg is interactive backend. Turning interactive mode on.
In[3]: 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)
def softmax(X):
"""定义softmax操作"""
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
"""定义模型"""
Out[5]: '定义模型'
def net(X):
return softmax(torch.matmul(X.reshape((-1, W.shape[0])), W) + b)
#-1表示自己算一下，批量大小
"""定义损失函数"""
Out[7]: '定义损失函数'
def cross_entropy(y_hat, y):
return - torch.log(y_hat[range(len(y_hat)), y])
cross_entropy(y_hat, y)
Traceback (most recent call last):
File "C:\ProgramData\Anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 3437, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "", line 4, in
cross_entropy(y_hat, y)
NameError: name 'y_hat' is not defined
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]
Out[9]: 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)
Out[10]: tensor([2.3026, 0.6931])
len(y_hat)
Out[11]: 2
range(len(y_hat))
Out[12]: range(0, 2)
aa=range(len(y_hat))
aa
Out[14]: range(0, 2)
"""range 生成一个0一直到n的一个向量"""
Out[15]: 'range 生成一个0一直到n的一个向量'
"""分类准确率"""
Out[16]: '分类准确率'
def accuracy(y_hat, y): #@save
"""计算预测正确的数量。y_hat是矩阵，那么假定第二个维度存储每个类的预测分数"""
"""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
"""
if len(y_hat.shape) > 1 and y_hat.shape[1] > 1:
y_hat = y_hat.argmax(axis=1) #按照每一行最大的那个下标存到y_hat里
cmp = y_hat.type(y.dtype) == y
return float(cmp.type(y.dtype).sum())
cmp
Traceback (most recent call last):
File "C:\ProgramData\Anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 3437, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "", line 1, in
cmp
NameError: name 'cmp' is not defined
accuracy(y_hat, y) / len(y)
Out[19]: 0.5
"""任意数据迭代器data_iter可访问的数据集，我们可以评估在任意模型net的准确率"""
Out[20]: '任意数据迭代器data_iter可访问的数据集，我们可以评估在任意模型net的准确率'
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]
evaluate_accuracy(net, test_iter)
Out[23]: 0.1388
"""训练"""
Out[24]: '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()
"""我要开始训练了，计算梯度"""
# 训练损失总和、训练准确度总和、样本数
metric = Accumulator(3)#累加上面三个需要的信息
for X, y in train_iter:
# 计算梯度并更新参数
y_hat = net(X) #扫一遍我们的函数
l = loss(y_hat, y) #交叉熵损失函数计算l
if isinstance(updater, torch.optim.Optimizer):#updater是优化器
# 使用PyTorch内置的优化器和损失函数
updater.zero_grad()
l.backward()
updater.step() #参数进行自更新
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()#求和，算梯度
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]
"""定义一个在动画中绘制数据的实用程序类"""
Out[26]: '定义一个在动画中绘制数据的实用程序类'
"""实时看到训练中的变化"""
Out[27]: '实时看到训练中的变化'
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): #@save
"""训练模型（定义见第3章）。之后还会用"""
animator = Animator(xlabel='epoch', xlim=[1, num_epochs], ylim=[0.3, 0.9],
legend=['train loss', 'train acc', 'test acc'])
#上面是定义可视化
for epoch in range(num_epochs):#扫n遍数据
"""train_metrics更新我们的模型，训练的误差拿下来"""
train_metrics = train_epoch_ch3(net, train_iter, loss, updater)
"""在测试数据集上评估我们的进度"""
test_acc = evaluate_accuracy(net, test_iter)
"""显示训练误差，训练进度，测试误差，测试进度"""
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
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:#拿出一个样本
break
trues = d2l.get_fashion_mnist_labels(y) #真实标号
preds = d2l.get_fashion_mnist_labels(net(X).argmax(axis=1)) #预测标号
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)
