TensorFlow利用dropout解决过拟合问题

        在TensorFlow训练样本的数据中，有时会出现过拟合（overfiting）的问题，可以采取dropout的方法来解决，即随机丢弃部分样本。

        下面是示例代码，通过tensorboard对结果进行了可视化：

        

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):
    with tf.name_scope('layer'):
        with tf.name_scope('weigh