softmax回归从零开始实现
""""***********************1.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)
""""**************2. 定义softmax操作*************"""
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)
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)"""
"""****************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——交叉熵********************"""
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]
def cross_entropy(y_hat,y):
return -torch.log(y_hat[range(len(y_hat)),y])
"""**************************5 分类准确率*******************"""
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):
"""计算在指定数据集上模型的精度"""
if isinstance(net,torch.nn.Module):
net.eval()
metric = Accumulator(2)
for X, y in data_iter:
metric.add(accuracy(net(X),y), y.numel())
return metric[0]/metric[1]
class Accumulator:
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)
"""**********************6 训练************************"""
def train_epoch_ch3(net, train_iter, loss, updater):
"""updater是更新模型参数的常用函数,它接受批量大小作为参数。"""
"""它可以是封装的d2l.sgd函数,也可以是框架的内置优化函数"""
"""训练模型一个迭代周期"""
if isinstance(net,torch.nn.Module):
net.train()
metric = Accumulator(3)
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()
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]
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)
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)
"""在train_iter访问到的训练数据集上训练一个模型net。
该训练函数将会运行多个迭代周期(由num_epochs指定)。
在每个迭代周期结束时,利用test_iter访问到的测试数据集对模型进行评估"""
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
"""*********************7. 开始训练*****************"""
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)