tensorflow--代码学习4(dropout)

最新推荐文章于 2022-12-26 18:09:53 发布

u:boom

最新推荐文章于 2022-12-26 18:09:53 发布

阅读量244

点赞数

文章标签： tensorflow 源码

本文链接：https://blog.youkuaiyun.com/newas3/article/details/90145654

版权

这篇博客探讨了在TensorFlow中如何使用Dropout技术来防止过拟合，并通过实例展示了其实现过程。同时，文章还提及了利用TensorBoard进行可视化监控训练效果。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

import tensorflow as tf
from sklearn.datasets import load_digits
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelBinarizer
#load data
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)

def add_layer(inputs,in_size,out_size,layer_name,activation_function=None):
    #add one more layer and return the out of this layer
    with tf.name_scope('layer'):
        with tf.name_scope('Wieght'):
            Weight = tf.Variable(tf.random_normal([in_size,out_size]),name='W')
        with tf.name_scope('biases'):
            biases = tf.Variable(tf.zeros([1,out_size]) + 0.1,name='biases')
        with tf.name_scope('Wx_plus_b'):
            Wx_plus_b = tf.add(tf.matmul(inputs,Weight),biases,name='Wx_plus_b')
            Wx_plus_b = tf.nn.dropout(Wx_plus_b,keep_prob)
        if activation_function is None:
            outputs = Wx_plus_b
        else:
            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])#8*8
ys = tf.placeholder(tf.float32,[None,10])

#add output player
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 error 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(0.6).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)

sess.run(tf.global_variables_initializer())

for i in range(500):
    
    sess.run(train_step,feed_dict={xs:X_train,ys:y_train,keep_prob:0.5})
    if i%50==0:
        #record loss
        train_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)

数据采用sklearn中所有，主要为dropout减小overfitting，可在tensorboard中查看