第一个教程给出了minist数据集的字符识别(分类),将手写数字0-9分类到0-9中。
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
上面的代码将从https://storage.googleapis.com/cvdf-datasets/mnist/上下载数据集,自动创建数据文件夹,数据格式为压缩格式gz。
详细的压缩格式数据集如何读取和reshape成训练和测试数组见源码中的minist.py文件,路径为:tensorflow\tensorflow\contrib\learn\python\learn\datasets\minist.py
接下来就是创建模型:y=W*x+b (y为用softmax回归后得到的分类结果,y_为标签结果)
sess = tf.InteractiveSession()
x = tf.placeholder(tf.float32, [None, 784])
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))
y = tf.nn.softmax(tf.matmul(x, W) + b)
y_ = tf.placeholder(tf.float32, [None, 10])
接下来计算损失函数:
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y), reduction_indices=[1]))
设置求损失函数解梯度的方法:
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
初始变量和训练最优求解过程:
tf.global_variables_initializer().run()
for i in range(1000):
batch_xs, batch_ys = mnist.train.next_batch(100)
train_step.run({x: batch_xs, y_: batch_ys})
计算正确率:
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
print(accuracy.eval({x: mnist.test.images, y_: mnist.test.labels}))