本文共 3047 字,大约阅读时间需要 10 分钟。
from tensorflow.examples.tutorials.mnist import input_dataimport tensorflow as tf# prepare datamnist = input_data.read_data_sets('MNIST_data', one_hot=True)xs = tf.placeholder(tf.float32, [None, 784])ys = tf.placeholder(tf.float32, [None, 10])# the model of the fully-connected networkweights = tf.Variable(tf.random_normal([784, 10]))biases = tf.Variable(tf.zeros([1, 10]) + 0.1)outputs = tf.matmul(xs, weights) + biasespredictions = tf.nn.softmax(outputs)cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(predictions), reduction_indices=[1]))train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)# compute the accuracycorrect_predictions = tf.equal(tf.argmax(predictions, 1), tf.argmax(ys, 1))accuracy = tf.reduce_mean(tf.cast(correct_predictions, tf.float32))with tf.Session() as sess: init = tf.global_variables_initializer() sess.run(init) for i in range(1000): batch_xs, batch_ys = mnist.train.next_batch(100) sess.run(train_step, feed_dict={ xs: batch_xs, ys: batch_ys }) if i % 50 == 0: print(sess.run(accuracy, feed_dict={ xs: mnist.test.images, ys: mnist.test.labels }))
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
xs = tf.placeholder(tf.float32, [None, 784])ys = tf.placeholder(tf.float32, [None, 10])
xs
代表图片像素数据, 每张图片(28×28)被展开成(1×784), 有多少图片还未定, 所以shape为None×784.ys
代表图片标签数据, 0-9十个数字被表示成One-hot
形式, 即只有对应bit为1, 其余为0.weights = tf.Variable(tf.random_normal([784, 10]))biases = tf.Variable(tf.zeros([1, 10]) + 0.1)outputs = tf.matmul(xs, weights) + biasespredictions = tf.nn.softmax(outputs)cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(predictions), reduction_indices=[1]))train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
使用Softmax函数作为激活函数:
correct_predictions = tf.equal(tf.argmax(predictions, 1), tf.argmax(ys, 1))accuracy = tf.reduce_mean(tf.cast(correct_predictions, tf.float32))
with tf.Session() as sess: init = tf.global_variables_initializer() sess.run(init) for i in range(1000): batch_xs, batch_ys = mnist.train.next_batch(100) sess.run(train_step, feed_dict={ xs: batch_xs, ys: batch_ys }) if i % 50 == 0: print(sess.run(accuracy, feed_dict={ xs: mnist.test.images, ys: mnist.test.labels }))
训练1000个循环, 准确率在87%左右.
Extracting MNIST_data/train-images-idx3-ubyte.gzExtracting MNIST_data/train-labels-idx1-ubyte.gzExtracting MNIST_data/t10k-images-idx3-ubyte.gzExtracting MNIST_data/t10k-labels-idx1-ubyte.gz0.10410.6320.73570.78370.79710.81470.82830.83760.84230.85010.85010.85330.85670.85970.85520.86470.86540.87010.87120.8712
转载地址:http://kiloi.baihongyu.com/