import tensorflow as tf;
import numpy as np;

state = tf.Variable(0,name='counter')   #引數值為0，name為counter
# print(state.name)
one = tf.constant(1)

new_value = tf.add(state,one)
update = tf.assign(state,new_value)  #assgin英文是：賦值，分配，所以在這裡就是一個賦值過程

init = tf.initialize_all_variables()  #如果定義變數一定需要

with tf.Session() as sess:
    sess.run(init)
    for _ in range(3):
        sess.run(update)
        print(sess.run(state))

import tensorflow as tf
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

#create data  程式碼預測引數。就是為了預測weight接近0.1，biaes接近0.3
x_data = np.random.rand(100).astype(np.float32)
y_data = x_data*0.1+0.3

# creat tensorflow structure start #
Weights = tf.Variable(tf.random_uniform([1],-1.0,1.0)) #生成一個隨機數列，是一維的，範圍是-1-1
biases = tf.Variable(tf.zeros([1])) #第一次賦值是0

y = Weights*x_data+biases
loss = tf.reduce_mean(tf.square(y-y_data))#真實值和預測值的一個差
optimizer = tf.train.GradientDescentOptimizer(0.5)#優化器，optimizer可以有很多種選擇，先選擇GradientDescentOptimizer；0.5是一個學習效率，一般是小於一的數
train = optimizer.minimize(loss)#用優化器減少誤差

init = tf.initialize_all_variables()#都是需要初始化的，就是模型建立好了，需要初始化讓這個模型“活”起來
# creat tensorflow structure end #

sess = tf.Session()
sess.run(init)  #結構啟用！！！sess就像一個指標指像init,並激活！

for step in range(200):
    sess.run(train)
    if step % 20 == 0:
        print(step,sess.run(Weights),sess.run(biases))

import tensorflow as tf;
import numpy as np;

matrix1 = tf.constant([[3,3]])  #constnt恆量
matrix2 = tf.constant([[2],[2]])

product = tf.matmul(matrix1,matrix2)  #matmul: matrix muliply  用np.dot(m1,m2)也是對兩個矩陣進行乘法運算

#method 1
# sess = tf.Session()
# result = sess.run(product)  #sess.run()返回值給result
# print(result)
#sess.close()

#mesthod 2
with tf.Session() as sess:    #用sess開啟tf.Session()
    print(sess.run(product))  #自動close

#placeholder是傳入值

import tensorflow as tf

input1 = tf.placeholder(tf.float32)
input2 = tf.placeholder(tf.float32)

output = tf.multiply (input1,input2)

with tf.Session() as sess:
    print(sess.run(output,feed_dict={input1:[7.],input2:[2.]}))  #placeholder傳入的值是和先開始定義的資料是繫結的，在輸出的時候一定需要feed_dict