tensorflow 使用正则化

最新推荐文章于 2021-01-17 13:13:36 发布

liyaohhh

最新推荐文章于 2021-01-17 13:13:36 发布

阅读量7.1k

点赞数

CC 4.0 BY-SA版权

分类专栏： python学习深度学习入门

本文链接：https://blog.youkuaiyun.com/liyaohhh/article/details/76982716

深度学习入门同时被 2 个专栏收录

38 篇文章

订阅专栏

python学习

2 篇文章

订阅专栏

本文介绍如何在TensorFlow中实现网络正则化，并通过一个示例展示了如何使用l2正则化防止过拟合。文章包括了创建网络、设置正则化项以及构建损失函数等关键步骤。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

Tensorflow 使用正则化T

import tensorflow.contrib.layers as layers

def easier_network(x, reg):
    """ A network based on tf.contrib.learn, with input `x`. """
    with tf.variable_scope('EasyNet'):
        out = layers.flatten(x)
        out = layers.fully_connected(out, 
                num_outputs=200,
                weights_initializer = layers.xavier_initializer(uniform=True),
                weights_regularizer = layers.l2_regularizer(scale=reg),
                activation_fn = tf.nn.tanh)
        out = layers.fully_connected(out, 
                num_outputs=200,
                weights_initializer = layers.xavier_initializer(uniform=True),
                weights_regularizer = layers.l2_regularizer(scale=reg),
                activation_fn = tf.nn.tanh)
        out = layers.fully_connected(out, 
                num_outputs=10, # Because there are ten digits!
                weights_initializer = layers.xavier_initializer(uniform=True),
                weights_regularizer = layers.l2_regularizer(scale=reg),
                activation_fn = None)
        return out

def main(_):
    mnist = input_data.read_data_sets(FLAGS.data_dir, one_hot=True)
    x = tf.placeholder(tf.float32, [None, 784])
    y_ = tf.placeholder(tf.float32, [None, 10])

    # Make a network with regularization
    y_conv = easier_network(x, FLAGS.regu)
    weights = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, 'EasyNet') 
    print("")
    for w in weights:
        shp = w.get_shape().as_list()
        print("- {} shape:{} size:{}".format(w.name, shp, np.prod(shp)))
    print("")
    reg_ws = tf.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES, 'EasyNet')
    for w in reg_ws:
        shp = w.get_shape().as_list()
        print("- {} shape:{} size:{}".format(w.name, shp, np.prod(shp)))
    print("")

    # Make the loss function `loss_fn` with regularization.
    cross_entropy = tf.reduce_mean(
        tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv))
    loss_fn = cross_entropy + tf.reduce_sum(reg_ws)
    train_step = tf.train.AdamOptimizer(1e-4).minimize(loss_fn)

tf.GraphKeys.REGULARIZATION_LOSSES得到在图中正则化的损失

regularizer=tf.contrib.layers.apply_regularization(tf.contrib.layers.l2_regularizer(weight_decay),gen_vars+d_vars)这样也可以