Dropout 解决 overfitting

Overfitting 也被称为过度学习，过度拟合

建立 dropout 层

import tensorflow as tf
from sklearn.datasets import load_digits
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelBinarizer

keep_prob是保留概率，即保留的结果所占比例

keep_prob = tf.placeholder(tf.float32)
...
...
Wx_plus_b = tf.nn.dropout(Wx_plus_b, keep_prob)

准备数据:

X_train是训练数据, X_test是测试数据

digits = load_digits()
X = digits.data
y = digits.target
y = LabelBinarizer().fit_transform(y)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.3)

添加隐含层和输出层

# add output layer
l1 = add_layer(xs, 64, 50, 'l1', activation_function=tf.nn.tanh)
prediction = add_layer(l1, 50, 10, 'l2', activation_function=tf.nn.softmax)

cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction),
                                              reduction_indices=[1]))  # loss
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)

训练

sess.run(train_step, feed_dict={xs: X_train, ys: y_train, keep_prob: 0.5})
#sess.run(train_step, feed_dict={xs: X_train, ys: y_train, keep_prob: 1})

可视化结果

训练中keep_prob=1时，就可以暴露出overfitting问题

keep_prob=0.5时，dropout就发挥了作用

keep_prob=1时，模型对训练数据的适应性优于测试数据，存在overfitting

输出如下： 红线是 train 的误差, 蓝线是 test 的误差

keep_prob=0.5:

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt

tf.set_random_seed(1)
np.random.seed(1)

# Hyper parameters
N_SAMPLES = 20
N_HIDDEN = 300
LR = 0.01

# training data
x = np.linspace(-1, 1, N_SAMPLES)[:, np.newaxis]
y = x + 0.3*np.random.randn(N_SAMPLES)[:, np.newaxis]

# test data
test_x = x.copy()
test_y = test_x + 0.3*np.random.randn(N_SAMPLES)[:, np.newaxis]

# show data
plt.scatter(x, y, c='magenta', s=50, alpha=0.5, label='train')
plt.scatter(test_x, test_y, c='cyan', s=50, alpha=0.5, label='test')
plt.legend(loc='upper left')
plt.ylim((-2.5, 2.5))
plt.show()

# tf placeholders
tf_x = tf.placeholder(tf.float32, [None, 1])
tf_y = tf.placeholder(tf.float32, [None, 1])
tf_is_training = tf.placeholder(tf.bool, None)  # to control dropout when training and testing

# overfitting net
o1 = tf.layers.dense(tf_x, N_HIDDEN, tf.nn.relu)
o2 = tf.layers.dense(o1, N_HIDDEN, tf.nn.relu)
o_out = tf.layers.dense(o2, 1)
o_loss = tf.losses.mean_squared_error(tf_y, o_out)
o_train = tf.train.AdamOptimizer(LR).minimize(o_loss)

# dropout net
d1 = tf.layers.dense(tf_x, N_HIDDEN, tf.nn.relu)
d1 = tf.layers.dropout(d1, rate=0.5, training=tf_is_training)   # drop out 50% of inputs
d2 = tf.layers.dense(d1, N_HIDDEN, tf.nn.relu)
d2 = tf.layers.dropout(d2, rate=0.5, training=tf_is_training)   # drop out 50% of inputs
d_out = tf.layers.dense(d2, 1)
d_loss = tf.losses.mean_squared_error(tf_y, d_out)
d_train = tf.train.AdamOptimizer(LR).minimize(d_loss)

sess = tf.Session()
sess.run(tf.global_variables_initializer())

plt.ion()   # something about plotting

for t in range(500):
    sess.run([o_train, d_train], {tf_x: x, tf_y: y, tf_is_training: True})  # train, set is_training=True

    if t % 10 == 0:
        # plotting
        plt.cla()
        o_loss_, d_loss_, o_out_, d_out_ = sess.run(
            [o_loss, d_loss, o_out, d_out], {tf_x: test_x, tf_y: test_y, tf_is_training: False} # test, set is_training=False
        )
        plt.scatter(x, y, c='magenta', s=50, alpha=0.3, label='train'); plt.scatter(test_x, test_y, c='cyan', s=50, alpha=0.3, label='test')
        plt.plot(test_x, o_out_, 'r-', lw=3, label='overfitting'); plt.plot(test_x, d_out_, 'b--', lw=3, label='dropout(50%)')
        plt.text(0, -1.2, 'overfitting loss=%.4f' % o_loss_, fontdict={'size': 20, 'color':  'red'}); plt.text(0, -1.5, 'dropout loss=%.4f' % d_loss_, fontdict={'size': 20, 'color': 'blue'})
        plt.legend(loc='upper left'); plt.ylim((-2.5, 2.5)); plt.pause(0.1)

plt.ioff()
plt.show()