TensorFlow Mnist Beginner Code

import tensorflow as tf

//Load data

x = tf.placeholder(tf.float32,[None,784])  //data가 들어갈 부분

W = tf.Variable(tf.zeros([784,10]))  //학습될 weight의 자리 - 0으로 초기화

b = tf.Variable(tf.zeros([10])) //학습될 bias b의 자리 - 0으로 초기화

y = tf.nn.softmax(tf.matmul(x,W)+b) //

//Train the model

y_=tf.placeholder(tf.float32,[None,10])

cross_entropy = -tf.reduce_sum(y_ * tf.log(y))

train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)

init = tf.initialize_all_variables()

sess = tf.Session()

sess.run(init)

//실제 train하는 부분 //데이터를 100개씩 1000번 주면서 train_step을 밟음

for i in range(1000):

  batch_xs, batch_ys = mnist.train.next_batch(100)

  sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})

//Evaluate the model

correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))

accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))

print sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels})