代码部分复制粘贴即可运行
1.正常情况
代码：
import matplotlib.pyplot as plt
import d2lzh as d2l
from mxnet import autograd, gluon, nd
from mxnet.gluon import data as gdata, loss as gloss, nn
n_train, n_test, true_w, true_b = 100, 100, [1.2, -3.4, 5.6], 5
features = nd.random.normal(shape=(n_train + n_test, 1))
poly_features = nd.concat(features, nd.power(features, 2),
nd.power(features, 3))
labels = (true_w[0] * poly_features[:, 0] + true_w[1] * poly_features[:, 1]
+ true_w[2] * poly_features[:, 2] + true_b)
labels += nd.random.normal(scale=0.1, shape=labels.shape)
def semilogy(x_vals, y_vals, x_label, y_label, x2_vals=None, y2_vals=None,
legend=None, figsize=(3.5, 2.5)):
d2l.set_figsize(figsize)
d2l.plt.xlabel(x_label)
d2l.plt.ylabel(y_label)
d2l.plt.semilogy(x_vals, y_vals)
if x2_vals and y2_vals:
d2l.plt.semilogy(x2_vals, y2_vals, linestyle=':')
d2l.plt.legend(legend)
num_epochs, loss = 100, gloss.L2Loss()
def fit_and_plot(train_features, test_features, train_labels, test_labels):
net = nn.Sequential()
net.add(nn.Dense(1))
net.initialize()
batch_size = min(10, train_labels.shape[0])
train_iter = gdata.DataLoader(gdata.ArrayDataset(
train_features, train_labels), batch_size, shuffle=True)
trainer = gluon.Trainer(net.collect_params(), 'sgd',
{'learning_rate': 0.01})
train_ls, test_ls = [], []
for _ in range(num_epochs):
for X, y in train_iter:
with autograd.record():
l = loss(net(X), y)
l.backward()
trainer.step(batch_size)
train_ls.append(loss(net(train_features),
train_labels).mean().asscalar())
test_ls.append(loss(net(test_features),
test_labels).mean().asscalar())
print('final epoch: train loss', train_ls[-1], 'test loss', test_ls[-1])
semilogy(range(1, num_epochs + 1), train_ls, 'epochs', 'loss',
range(1, num_epochs + 1), test_ls, ['train', 'test'])
print('weight:', net[0].weight.data().asnumpy(),
'\nbias:', net[0].bias.data().asnumpy())
fit_and_plot(poly_features[:n_train, :], poly_features[n_train:, :], labels[:n_train], labels[n_train:])
plt.show()
输出结果：
final epoch: train loss 0.0069854474 test loss 0.006349625
weight: [[ 1.1746308 -3.3920233 5.605342 ]]
bias: [4.9861965]
图：
2.欠拟合
代码：
import matplotlib.pyplot as plt
import d2lzh as d2l
from mxnet import autograd, gluon, nd
from mxnet.gluon import data as gdata, loss as gloss, nn
n_train, n_test, true_w, true_b = 100, 100, [1.2, -3.4, 5.6], 5
features = nd.random.normal(shape=(n_train + n_test, 1))
poly_features = nd.concat(features, nd.power(features, 2),
nd.power(features, 3))
labels = (true_w[0] * poly_features[:, 0] + true_w[1] * poly_features[:, 1]
+ true_w[2] * poly_features[:, 2] + true_b)
labels += nd.random.normal(scale=0.1, shape=labels.shape)
def semilogy(x_vals, y_vals, x_label, y_label, x2_vals=None, y2_vals=None,
legend=None, figsize=(3.5, 2.5)):
d2l.set_figsize(figsize)
d2l.plt.xlabel(x_label)
d2l.plt.ylabel(y_label)
d2l.plt.semilogy(x_vals, y_vals)
if x2_vals and y2_vals:
d2l.plt.semilogy(x2_vals, y2_vals, linestyle=':')
d2l.plt.legend(legend)
num_epochs, loss = 100, gloss.L2Loss()
def fit_and_plot(train_features, test_features, train_labels, test_labels):
net = nn.Sequential()
net.add(nn.Dense(1))
net.initialize()
batch_size = min(10, train_labels.shape[0])
train_iter = gdata.DataLoader(gdata.ArrayDataset(
train_features, train_labels), batch_size, shuffle=True)
trainer = gluon.Trainer(net.collect_params(), 'sgd',
{'learning_rate': 0.01})
train_ls, test_ls = [], []
for _ in range(num_epochs):
for X, y in train_iter:
with autograd.record():
l = loss(net(X), y)
l.backward()
trainer.step(batch_size)
train_ls.append(loss(net(train_features),
train_labels).mean().asscalar())
test_ls.append(loss(net(test_features),
test_labels).mean().asscalar())
print('final epoch: train loss', train_ls[-1], 'test loss', test_ls[-1])
semilogy(range(1, num_epochs + 1), train_ls, 'epochs', 'loss',
range(1, num_epochs + 1), test_ls, ['train', 'test'])
print('weight:', net[0].weight.data().asnumpy(),
'\nbias:', net[0].bias.data().asnumpy())
fit_and_plot(features[:n_train, :], features[n_train:, :], labels[:n_train],labels[n_train:])
plt.show()
输出结果：
final epoch: train loss 159.3327 test loss 102.89436
weight: [[22.642]]
bias: [-0.6635639]
图：
3.过拟合
代码：
import matplotlib.pyplot as plt
import d2lzh as d2l
from mxnet import autograd, gluon, nd
from mxnet.gluon import data as gdata, loss as gloss, nn
n_train, n_test, true_w, true_b = 100, 100, [1.2, -3.4, 5.6], 5
features = nd.random.normal(shape=(n_train + n_test, 1))
poly_features = nd.concat(features, nd.power(features, 2),
nd.power(features, 3))
labels = (true_w[0] * poly_features[:, 0] + true_w[1] * poly_features[:, 1]
+ true_w[2] * poly_features[:, 2] + true_b)
labels += nd.random.normal(scale=0.1, shape=labels.shape)
def semilogy(x_vals, y_vals, x_label, y_label, x2_vals=None, y2_vals=None,
legend=None, figsize=(3.5, 2.5)):
d2l.set_figsize(figsize)
d2l.plt.xlabel(x_label)
d2l.plt.ylabel(y_label)
d2l.plt.semilogy(x_vals, y_vals)
if x2_vals and y2_vals:
d2l.plt.semilogy(x2_vals, y2_vals, linestyle=':')
d2l.plt.legend(legend)
num_epochs, loss = 100, gloss.L2Loss()
def fit_and_plot(train_features, test_features, train_labels, test_labels):
net = nn.Sequential()
net.add(nn.Dense(1))
net.initialize()
batch_size = min(10, train_labels.shape[0])
train_iter = gdata.DataLoader(gdata.ArrayDataset(
train_features, train_labels), batch_size, shuffle=True)
trainer = gluon.Trainer(net.collect_params(), 'sgd',
{'learning_rate': 0.01})
train_ls, test_ls = [], []
for _ in range(num_epochs):
for X, y in train_iter:
with autograd.record():
l = loss(net(X), y)
l.backward()
trainer.step(batch_size)
train_ls.append(loss(net(train_features),
train_labels).mean().asscalar())
test_ls.append(loss(net(test_features),
test_labels).mean().asscalar())
print('final epoch: train loss', train_ls[-1], 'test loss', test_ls[-1])
semilogy(range(1, num_epochs + 1), train_ls, 'epochs', 'loss',
range(1, num_epochs + 1), test_ls, ['train', 'test'])
print('weight:', net[0].weight.data().asnumpy(),
'\nbias:', net[0].bias.data().asnumpy())
fit_and_plot(poly_features[0:2, :], poly_features[n_train:, :], labels[0:2],labels[n_train:])
plt.show()
输出结果：
final epoch: train loss 0.48284632 test loss 134.29808
weight: [[1.9822395 1.9652433 2.0623443]]
bias: [2.4985628]
图：
793
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
