乙個簡單的神經網路例子

神經系統的搭建

import tensorflow as tf

import numpy as np
import matplotlib,pylab as plt
def add_layer(input,in_size,out_size,activation_function = none):
weights = tf.variable(tf.random_normal([in_size,out_size]))
biases = tf.variable(tf.zeros([1,out_size])+0.1)
wx_plus_b = tf.matmul(input,weights)+biases
if activation_function is none:
outputs = wx_plus_b
else:
outputs = activation_function(wx_plus_b)
return outputs
#輸入層到神經層
x_data = np.linspace(-1,1,300)[:,np.newaxis]   #產生等差數列
noise = np.random.normal(0,0.05,x_data.shape)
y_data = np.square(x_data)-0.5+noise               #對x_data進行平方
xs = tf.placeholder(tf.float32,[none,1])
ys = tf.placeholder(tf.float32,[none,1])
#神經層到輸出層
l1 = add_layer(xs,1,10,activation_function=tf.nn.relu)
prediction = add_layer(l1,10,1,activation_function=none)
loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys-prediction),reduction_indices=[1]))   #將每個y_data-prediction值取平方，然後求和後去平均值
train_step = tf.train.gradientdescentoptimizer(0.1).minimize(loss)
init = tf.initialize_all_variables()
sess = tf.session()
sess.run(init)
fig = plt.figure()
ax = fig.add_subplot(1,1,1)
ax.scatter(x_data,y_data)
plt.ion()   #使程式不暫停，影象可變動
plt.show()
for i in range(1000):
sess.run(train_step,feed_dict = )
if i%50==0:
try:
ax.lines.remove(lines[0])
except exception:
pass
prediction_value = sess.run(prediction,feed_dict=)
lines = ax.plot(x_data,prediction_value,'r-',lw = 5)
plt.pause(0.1)
#print(sess.run(loss,feed_dict =))```

import numpy as np

import matplotlib,pylab as plt
def add_layer(input,in_size,out_size,n_layer,activation_function = none):
layer_name = 'layer%s'% n_layer
with tf.name_scope(layer_name):
with tf.name_scope('weights'):
weights = tf.variable(tf.random_normal([in_size,out_size]),name = 'w')
tf.summary.histogram(layer_name+'/weights',weights)
with tf.name_scope('biases'):
biases = tf.variable(tf.zeros([1,out_size])+0.1)
tf.summary.histogram(layer_name + '/biases', biases)
with tf.name_scope('wx_plus_b'):
wx_plus_b = tf.matmul(input,weights)+biases
if activation_function is none:
outputs = wx_plus_b
tf.summary.histogram(layer_name + '/outputs', outputs)
else:
outputs = activation_function(wx_plus_b)
return outputs
#輸入層到神經層
x_data = np.linspace(-1,1,300)[:,np.newaxis]   #產生等差數列
noise = np.random.normal(0,0.05,x_data.shape)
y_data = np.square(x_data)-0.5+noise               #對x_data進行平方
with tf.name_scope('input'):
xs = tf.placeholder(tf.float32, [none, 1], name='x_input')
ys = tf.placeholder(tf.float32, [none, 1], name='y_input')
**將其視覺化**
l1 = add_layer(xs,1,10,n_layer = 1,activation_function=tf.nn.relu)
prediction = add_layer(l1,10,1,n_layer = 2,activation_function=none)
with tf.name_scope('loss'):
loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys-prediction),reduction_indices=[1]))   #將每個y_data-prediction值取平方，然後求和後去平均值
tf.summary.scalar('loss',loss)   #event圖
with tf.name_scope('train'):
train_step = tf.train.gradientdescentoptimizer(0.1).minimize(loss)
init = tf.initialize_all_variables()
sess = tf.session()
merged = tf.summary.merge_all()
writer = tf.summary.filewriter("c:/users/administrator/desktop/model",sess.graph)
sess.run(init)
for i in range(1000):
sess.run(train_step,feed_dict=)
if i%50==0:
result = sess.run(merged,feed_dict=)
writer.add_summary(result,i)
fig = plt.figure()
ax = fig.add_subplot(1,1,1)
ax.scatter(x_data,y_data)
plt.ion()   #使程式不暫停，影象可變動
plt.show()
for i in range(1000):
sess.run(train_step,feed_dict = )
if i%50==0:
try:
ax.lines.remove(lines[0])
except exception:
pass
prediction_value = sess.run(prediction,feed_dict=)
lines = ax.plot(x_data,prediction_value,'r-',lw = 5)
plt.pause(0.1)
#print(sess.run(loss,feed_dict =))

步驟2：

乙個簡單的神經網路例子

來自神經網路之家 日期 2015 07 1611 18 37.0 用於訓練的輸入資料 對應的輸出資料 我們這裡設定 1 節點個數設定 輸入層 隱層 輸出層的節點個數分別為 2 3，1 2 傳遞函式設定 隱層 tansig函式 輸出層 purelin函式 3 訓練方式 trainlm。即得到下圖的模型...

TensorFlow 乙個簡單的神經網路

利用tensorflow實現第乙個簡單的神經網路 encoding utf 8 import tensorflow as tf numpy生成模擬資料集 from numpy.random import randomstate 定義訓練資料batch大小 batch size 8 定義神經網路的引數...

搭建乙個簡單的神經網路

def add layer 最基礎的四個引數 輸入值，輸入的大小，輸出的大小和激勵函式，激勵函式可以自己新增，也可以不使用激勵函式。def add layer inputs,in size,out size,activation function none 接下來我們定義weight和biases ...