在TensorFlow中实施MLP
-
16-10-2019 - |
题
关于如何在TensorFlow中实施MLP的在线资源很多,大多数样本确实有效:)但是我对一个特定的样本感兴趣,我从中学到了这些样本 https://www.coursera.org/learn/machine-learning. 。在其中,它使用了 成本 函数定义如下:
$ j( theta)= frac {1} {m} sum_ {i = 1}^{m}^{m} sum_ {k = 1}^{k} {k} left [-y_k^{(i)} log ((h_ theta(x^{(i)}))_ k - (1 -y_k^{(i)}) log(1-(h_ theta(x^{(i)}))_ _ k right ] $
$ h_ theta $是 乙状结肠 功能。
我的实施是:
# one hidden layer MLP
x = tf.placeholder(tf.float32, shape=[None, 784])
y = tf.placeholder(tf.float32, shape=[None, 10])
W_h1 = tf.Variable(tf.random_normal([784, 512]))
h1 = tf.nn.sigmoid(tf.matmul(x, W_h1))
W_out = tf.Variable(tf.random_normal([512, 10]))
y_ = tf.matmul(h1, W_out)
# cross_entropy = tf.nn.sigmoid_cross_entropy_with_logits(y_, y)
cross_entropy = tf.reduce_sum(- y * tf.log(y_) - (1 - y) * tf.log(1 - y_), 1)
loss = tf.reduce_mean(cross_entropy)
train_step = tf.train.GradientDescentOptimizer(0.05).minimize(loss)
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
# train
with tf.Session() as s:
s.run(tf.initialize_all_variables())
for i in range(10000):
batch_x, batch_y = mnist.train.next_batch(100)
s.run(train_step, feed_dict={x: batch_x, y: batch_y})
if i % 100 == 0:
train_accuracy = accuracy.eval(feed_dict={x: batch_x, y: batch_y})
print('step {0}, training accuracy {1}'.format(i, train_accuracy))
我认为这些层的定义是正确的,但是问题在于 cross_entropy. 。如果我使用第一个, 一个人发表了评论, ,模型很快收敛; 但是,如果我使用第二个,我认为/希望是上一个方程式的翻译,则该模型不会收敛。
解决方案
你犯了三个错误:
- 您在非线性转换之前省略了偏移项(变量B_1和B_OUT)。这增加了神经网络的代表性。
- 您省略了顶层的SoftMax转换。这使输出成为概率分布,因此您可以计算跨凝结,这是分类的通常成本函数。
- 当您应该使用多级形式时,您使用了跨熵的二进制形式。
当我运行这个时,我的准确性超过90%:
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('/tmp/MNIST_data', one_hot=True)
x = tf.placeholder(tf.float32, shape=[None, 784])
y = tf.placeholder(tf.float32, shape=[None, 10])
W_h1 = tf.Variable(tf.random_normal([784, 512]))
b_1 = tf.Variable(tf.random_normal([512]))
h1 = tf.nn.sigmoid(tf.matmul(x, W_h1) + b_1)
W_out = tf.Variable(tf.random_normal([512, 10]))
b_out = tf.Variable(tf.random_normal([10]))
y_ = tf.nn.softmax(tf.matmul(h1, W_out) + b_out)
# cross_entropy = tf.nn.sigmoid_cross_entropy_with_logits(y_, y)
cross_entropy = tf.reduce_sum(- y * tf.log(y_), 1)
loss = tf.reduce_mean(cross_entropy)
train_step = tf.train.GradientDescentOptimizer(0.05).minimize(loss)
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
# train
with tf.Session() as s:
s.run(tf.initialize_all_variables())
for i in range(10000):
batch_x, batch_y = mnist.train.next_batch(100)
s.run(train_step, feed_dict={x: batch_x, y: batch_y})
if i % 1000 == 0:
train_accuracy = accuracy.eval(feed_dict={x: batch_x, y: batch_y})
print('step {0}, training accuracy {1}'.format(i, train_accuracy))