Udacity深度学习之Dropout

版权声明:博客为作者平时学习备忘,参考资料已在文尾列出一并表示感谢。如若转载,请列明出处。 https://blog.csdn.net/woai8339/article/details/86258830

Dropout含义

       droupout在深度学习中用来防止过拟合,机器学习过拟合现象究竟是什么呢?具体可以可以周志华老师机器学习西瓜书(第二章)——模型评估与选择,同时解释为什么L1可以做特征选择,其系数为0(L2正则类似)来说。
用一张图来表示就是:
在这里插入图片描述
Dropout 是一个降低过拟合的正则化技术。它在网络中暂时的丢弃一些单元(神经元),以及与它们的前后相连的所有节点。图 1dropout 的工作示意图。
TensorFlow 提供了一个 tf.nn.dropout() 函数,你可以用来实现 dropout
让我们来看一个 tf.nn.dropout()的使用例子。

keep_prob = tf.placeholder(tf.float32) # probability to keep units

hidden_layer = tf.add(tf.matmul(features, weights[0]), biases[0])
hidden_layer = tf.nn.relu(hidden_layer)
hidden_layer = tf.nn.dropout(hidden_layer, keep_prob)

logits = tf.add(tf.matmul(hidden_layer, weights[1]), biases[1])

上面的代码展示了如何在神经网络中应用 dropout

tf.nn.dropout()函数有两个参数:

hidden_layer:你要应用 dropouttensor
keep_prob:任何一个给定单元的留存率(没有被丢弃的单元)
keep_prob 可以让你调整丢弃单元的数量。为了补偿被丢弃的单元,tf.nn.dropout() 把所有保留下来的单元(没有被丢弃的单元)* 1/keep_prob

在训练时,一个好的keep_prob初始值是0.5
在测试时,把 keep_prob 值设为1.0 ,这样保留所有的单元,最大化模型的能力。

练习

练习1

下面的代码,哪里出问题了?
语法没问题,但是测试准确率很低。

keep_prob = tf.placeholder(tf.float32) # probability to keep units

hidden_layer = tf.add(tf.matmul(features, weights[0]), biases[0])
hidden_layer = tf.nn.relu(hidden_layer)
hidden_layer = tf.nn.dropout(hidden_layer, keep_prob)

logits = tf.add(tf.matmul(hidden_layer, weights[1]), biases[1])

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    for epoch_i in range(epochs):
        for batch_i in range(batches):
            sess.run(optimizer, feed_dict={
                features: batch_features,
                labels: batch_labels,
                keep_prob: 0.5})
    validation_accuracy = sess.run(accuracy, feed_dict={
        features: test_features,
        labels: test_labels,
        keep_prob: 0.5})

原因:keep_prob在验证测试准确率的时候应该设置成1。

练习2

# Quiz Solution
# Note: You can't run code in this tab
import tensorflow as tf

hidden_layer_weights = [
    [0.1, 0.2, 0.4],
    [0.4, 0.6, 0.6],
    [0.5, 0.9, 0.1],
    [0.8, 0.2, 0.8]]
out_weights = [
    [0.1, 0.6],
    [0.2, 0.1],
    [0.7, 0.9]]

# Weights and biases
weights = [
    tf.Variable(hidden_layer_weights),
    tf.Variable(out_weights)]
biases = [
    tf.Variable(tf.zeros(3)),
    tf.Variable(tf.zeros(2))]

# Input
features = tf.Variable([[0.0, 2.0, 3.0, 4.0], [0.1, 0.2, 0.3, 0.4], [11.0, 12.0, 13.0, 14.0]])

# TODO: Create Model with Dropout
keep_prob = tf.placeholder(tf.float32)
hidden_layer = tf.add(tf.matmul(features, weights[0]), biases[0])
hidden_layer = tf.nn.relu(hidden_layer)
hidden_layer = tf.nn.dropout(hidden_layer, keep_prob)

logits = tf.add(tf.matmul(hidden_layer, weights[1]), biases[1])

# TODO: Print logits from a session
with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    print(sess.run(logits, feed_dict={keep_prob: 0.5}))
output:
[[ 1.1        6.6000004]
 [ 0.9100001  1.016    ]
 [33.74      43.38     ]]

Ref:
1、https://www.cs.toronto.edu/~hinton/absps/JMLRdropout.pdf

猜你喜欢

转载自blog.csdn.net/woai8339/article/details/86258830