import tensorflow as tf
import numpy as np
import matplotlib.pylab as plt
def tfDemo1():
#create data
x_data = np.random.rand(100).astype(np.float32)
y_data = x_data * 0.1 + 0.3
#create tensorflow structure
Weights=tf.Variable(tf.random_uniform([1],-1.0,1.0)) #一維,範圍[-1,1]
biases=tf.Variable(tf.zeros([1]))
y=Weights*x_data+biases
loss=tf.reduce_mean(tf.square(y-y_data))
#建立優化器,減小誤差,提高參數準確度,每次迭代都會優化
optimizer=tf.train.GradientDescentOptimizer(0.5) #學習效率<1
train=optimizer.minimize(loss)
#初始化變量
init=tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
#train
for step in range(201):
sess.run(train)
if step%20==0:
print(step,sess.run(Weights),sess.run(biases))
def tfDemo2():
matrix1 = tf.constant([[3, 3]])
matrix2 = tf.constant([[2], [2]])
#Tensor("Const:0", shape=(1, 2), dtype=int32)
#Tensor("Const_1:0", shape=(2, 1), dtype=int32)
print(matrix1)
print(matrix2)
# matrix multiply
# np.dot(m1,m2)
product = tf.matmul(matrix1, matrix2)
sess = tf.Session() # Session是一個object,首字母要大寫
result = sess.run(product)
print(result)
sess.close()
# method 2
# with 可以自己關閉會話
with tf.Session() as sess:
result2 = sess.run(product)
print(result2)
# Variable
def tfDemo3():
state=tf.Variable(0,name='counter')
print(state)
print(state.name)
one=tf.constant(1)
new_value=tf.add(state,one)
updata=tf.assign(state,new_value)
#變量必須要激活
init=tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
for _ in range(3):
sess.run(updata)
print(sess.run(state))
# placeholder
def tfDemo4():
# 給定type,tf大部分只能處理float32數據
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.]}))
# 添加層
def add_layer(inputs,in_size,out_size,activation_function=None):
#Weights是一個矩陣,[行,列]爲[in_size,out_size]
Weights=tf.Variable(tf.random_normal([in_size,out_size]))#正態分佈
#初始值推薦不爲0,所以加上0.1,一行,out_size列
biases=tf.Variable(tf.zeros([1,out_size])+0.1)
#Weights*x+b的初始化的值,也就是未激活的值
Wx_plus_b=tf.matmul(inputs,Weights)+biases
if activation_function is None:
outputs=Wx_plus_b
else:
outputs=activation_function(Wx_plus_b)
return outputs
# 構建一個神經網絡
def tfDemo5():
# (-1,1)之間,有300個單位,後面的是維度,x_data是有300行(300個例子)
x_data=np.linspace(-1,1,300)[:,np.newaxis]
# 加噪聲,均值爲0,方差爲0.05,大小和x_data一樣
noise=np.random.normal(0,0.05,x_data.shape)
y_data=np.square(x_data)-0.5+noise
xs=tf.placeholder(tf.float32,[None,1])
ys=tf.placeholder(tf.float32,[None,1])
"""建立網絡"""
#定義隱藏層,輸入1個節點,輸出10個節點
l1=add_layer(xs,1,10,activation_function=tf.nn.relu)
#定義輸出層
prediction=add_layer(l1,10,1,activation_function=None)
# 計算loss只需要正向傳播
loss=tf.reduce_mean(tf.reduce_sum(tf.square(ys-prediction),reduction_indices=[1]))
"""訓練"""
#優化算法,minimize(loss)以0.1的學習率對loss進行減小
train_step=tf.train.GradientDescentOptimizer(0.1).minimize(loss)
init=tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
for i in range(2000):
# sess.run()調用一次就進行一次正向傳播,然後根據誤差進行一次反向傳播調整網絡參數(梯度下降進行調整)
sess.run(train_step,feed_dict={xs:x_data,ys:y_data})
if i%50==0:
print(sess.run(loss,feed_dict={xs:x_data,ys:y_data}))
# 可視化
def tfDemo6():
"""定義數據形式"""
# (-1,1)之間,有300個單位,後面的是維度,x_data是有300行(300個例子)
x_data=np.linspace(-1,1,300)[:,np.newaxis]
# 加噪聲,均值爲0,方差爲0.05,大小和x_data一樣
noise=np.random.normal(0,0.05,x_data.shape)
y_data=np.square(x_data)-0.5+noise
xs=tf.placeholder(tf.float32,[None,1])
ys=tf.placeholder(tf.float32,[None,1])
"""建立網絡"""
#定義隱藏層,輸入1個節點,輸出10個節點
l1=add_layer(xs,1,10,activation_function=tf.nn.relu)
#定義輸出層
prediction=add_layer(l1,10,1,activation_function=None)
"""預測"""
#損失函數,算出的是每個例子的平方,要求和(reduction_indices=[1],按行求和),再求均值
loss=tf.reduce_mean(tf.reduce_sum(tf.square(ys-prediction),reduction_indices=[1]))
"""訓練"""
#優化算法,minimize(loss)以0.1的學習率對loss進行減小
train_step=tf.train.GradientDescentOptimizer(0.1).minimize(loss)
init=tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
fig=plt.figure()
#連續性的畫圖
ax=fig.add_subplot(1,1,1)
ax.scatter(x_data,y_data)
# 不暫停
plt.ion()
# plt.show()繪製一次就會暫停
# plt.show() #也可以用plt.show(block=False)來取消暫停,但是python3.5以後提供了ion的功能,更方便
for i in range(1000):
sess.run(train_step,feed_dict={xs:x_data,ys:y_data})
if i%20==0:
# print(sess.run(loss,feed_dict={xs:x_data,ys:y_data}))
#嘗試先抹除,後繪製第二條線
#第一次沒有線,會報錯,try就會忽略錯誤,然後緊接着執行下面的步驟
try:
# 畫出一條後抹除掉,去除第一個線段,但是隻有一個,也就是抹除當前的線段
ax.lines.remove(lines[0])
except Exception:
pass
prediction_value=sess.run(prediction,feed_dict={xs:x_data})
lines=ax.plot(x_data,prediction_value,'r-',lw=5) #lw線寬
# 暫停0.1s
plt.pause(0.1)
def main():
#tfDemo1()
#tfDemo2()
#tfDemo3()
#tfDemo4()
#tfDemo5()
tfDemo6()
if __name__ == '__main__':
main()