Dropout 解決 overfitting

相對于過擬合（overfitting，或稱：過度學習）是指，使用過多參數，以致太適應訓練數據而非一般情況；另一種常見的現象是使用太少參數，以致于不適應當前的訓練數據，這則稱為欠擬合（underfitting，或稱：擬合不足）現象。^[2]

防止過擬合，我們需要用到一些方法，如：early stopping、數據集擴增（Data augmentation）、正則化（Regularization）、Dropout等。^[3]

本次數據來自 sklearn, 首先導入模塊

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

在之前代碼的基礎上修改, 增加 keep_prob 占位符保留數據的概率

# k = 1, 保留 100%, 即沒有 dropout 任何數據. keep_prob = tf.placeholder(tf.float32)

準備訓練數據（train）測試數據（test）

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)

在訓練過程中，overfitting 的問題與 keep_prob 相關，keep_prob = 1 沒有dropout 任何數據， keep_prob = 0.5 則能明顯看出 dropout 的效果。

keep_prob = 1

keep_prob = 0.5

---

完整代碼

# !/usr/bin/python3 # -*- coding: utf-8 -*-from __future__ import print_function import tensorflow as tf from sklearn.datasets import load_digits from sklearn.cross_validation import train_test_split from sklearn.preprocessing import LabelBinarizer# load data digits = load_digits() X = digits.data # img 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)def add_layer(inputs, in_size, out_size, layer_name, activation_function=None, ):# add one more layer and return the output of this layerWeights = tf.Variable(tf.random_normal([in_size, out_size]))biases = tf.Variable(tf.zeros([1, out_size]) + 0.1, )Wx_plus_b = tf.matmul(inputs, Weights) + biases# here to dropoutWx_plus_b = tf.nn.dropout(Wx_plus_b, keep_prob) # +++if activation_function is None:outputs = Wx_plus_belse:outputs = activation_function(Wx_plus_b, )tf.summary.histogram(layer_name + '/outputs', outputs)return outputs# define placeholder for inputs to network keep_prob = tf.placeholder(tf.float32) # +++ xs = tf.placeholder(tf.float32, [None, 64]) # 8x8 ys = tf.placeholder(tf.float32, [None, 10])# 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)# the loss between prediction and real data cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction),reduction_indices=[1])) # loss tf.summary.scalar('loss', cross_entropy) # +++ train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)sess = tf.Session() merged = tf.summary.merge_all() # summary writer goes in here train_writer = tf.summary.FileWriter("logs/train", sess.graph) # +++ test_writer = tf.summary.FileWriter("logs/test", sess.graph)# tf.initialize_all_variables() no long valid from # 2017-03-02 if using tensorflow >= 0.12 if int((tf.__version__).split('.')[1]) < 12 and int((tf.__version__).split('.')[0]) < 1:init = tf.initialize_all_variables() else:init = tf.global_variables_initializer() sess.run(init)for i in range(500):# here to determine the keeping probabilitysess.run(train_step, feed_dict={xs: X_train, ys: y_train, keep_prob: 1}) # +++if i % 50 == 0:# record losstrain_result = sess.run(merged, feed_dict={xs: X_train, ys: y_train, keep_prob: 1}) test_result = sess.run(merged, feed_dict={xs: X_test, ys: y_test, keep_prob: 1})train_writer.add_summary(train_result, i)test_writer.add_summary(test_result, i) # +++

Reference

[1] 莫煩Python: Dropout 解決 overfitting
[2] 拾毅者: 機器學習—過擬合overfitting
[3] 一只鳥的天空: 機器學習中防止過擬合的處理方法

轉載于:https://www.cnblogs.com/TaylorBoy/p/6814664.html

總結

以上是生活随笔為你收集整理的T7-Dropout 解决 overfitting 过拟合的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。