注:本代码在jupyter notebook上运行
封面图片来源
通过深度学习框架的高级API实现softmax回归模型更简单。 如在上一篇文章中一样, 继续使用Fashion-MNIST数据集,并保持批量大小为256。
导包
from torch import nn
import torch
from IPython import display
import torchvision
from torchvision import transforms
from torch.utils import data
def get_dataloader_workers(): # 设置线程数
"""使用4个进程来读取数据"""
return 4
def load_data_fashion_mnist(batch_size, resize=None):# 加载数据组件
"""下载Fashion-MNIST数据集,然后将其加载到内存中"""
trans = [transforms.ToTensor()]
if resize:
trans.insert(0, transforms.Resize(resize))
trans = transforms.Compose(trans)
mnist_train = torchvision.datasets.FashionMNIST( # 下载数据集
root="data", train=True, transform=trans, download=True)
mnist_test = torchvision.datasets.FashionMNIST(
root="data", train=False, transform=trans, download=True)
return (data.DataLoader(mnist_train, batch_size, shuffle=True,
num_workers=get_dataloader_workers()),
data.DataLoader(mnist_test, batch_size, shuffle=False,
num_workers=get_dataloader_workers()))
设置数据迭代器的批量大小为256
batch_size = 256
train_iter, test_iter = load_data_fashion_mnist(batch_size)
初始化模型参数
softmax回归的输出层是一个全连接层。 因此,为了实现我们的模型, 我们只需在Sequential中添加一个带有10个输出的全连接层。 同样,在这里Sequential并不是必要的, 但它是实现深度模型的基础。 我们仍然以均值0和标准差0.01随机初始化权重。
# 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);
损失函数
loss = nn.CrossEntropyLoss(reduction='none')
优化算法
使用学习率为0.1的小批量随机梯度下降作为优化算法
trainer = torch.optim.SGD(net.parameters(), lr=0.1)
训练
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) # 第二维度取最大值的索引
cmp = y_hat.type(y.dtype) == y
return float(cmp.type(y.dtype).sum())
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 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
with torch.no_grad():
for X, y in data_iter:
metric.add(accuracy(net(X), y), y.numel())
return metric[0] / metric[1]
def train_epoch_ch3(net, train_iter, loss, updater): #@save
"""训练模型一个迭代周期"""
# 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)
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]
%matplotlib inline
import matplotlib.pyplot as plt
def set_axes(axes, xlabel, ylabel, xlim, ylim, xscale, yscale, legend):
axes.set_xlabel(xlabel)
axes.set_ylabel(ylabel)
axes.set_xscale(xscale)
axes.set_yscale(yscale)
axes.set_xlim(xlim)
axes.set_ylim(ylim)
if legend:
axes.legend(legend)
axes.grid()
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 = []
# plt.use_svg_display()
self.fig, self.axes = 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: 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() # 清除当前轴
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) # 更新显示图形
def train_ch3(net, train_iter, test_iter, loss, num_epochs, updater): #@save
"""训练模型"""
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
num_epochs = 10
train_ch3(net, train_iter, test_iter, loss, num_epochs, trainer)
欢迎点击我的主页查看更多文章。
本人学习地址https://zh-v2.d2l.ai/
恳请大佬批评指正。