# -*- coding: utf-8 -*-

#匯入資料集
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MINST_data/",one_hot = True)

#檢視資料集相關資訊
print(mnist.train.images.shape,mnist.train.labels.shape)
print(mnist.test.images.shape,mnist.test.labels.shape)
print(mnist.validation.images.shape,mnist.validation.labels.shape)

#匯入tensorflow
import tensorflow as tf
sess = tf.InteractiveSession()
x = tf.placeholder(tf.float32,[None,784])

#初始化權重，偏置
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))

#呼叫softmax函式估算對每一類別的概率
y = tf.nn.softmax(tf.matmul(x,W) + b)

#設定損失函式
y_ = tf.placeholder(tf.float32,[None,10])
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y),
                                              reduction_indices=[1]))

#設定學習速率為0.5，優化目標為cross_entropy
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
tf.global_variables_initializer().run()

#迭代訓練，每次隨機取出100條資料進行訓練
for i in range(1000):
    batch_xs,batch_ys = mnist.train.next_batch(100)
    train_step.run({x:batch_xs,y_:batch_ys})
  
#計算輸出學習結果，準確率為91%左右
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}))