tensorflow--学习笔记--莫烦python

jsc142915

于 2022-02-27 20:19:44 发布

阅读量850

点赞数

分类专栏：笔记文章标签： tensorflow 学习深度学习

本文链接：https://blog.csdn.net/jsc142915/article/details/123083258

版权

笔记专栏收录该内容

11 篇文章 0 订阅

订阅专栏

1.处理结构

input-------包含x-input和y-input

gradient descent--梯度下降---更新数据--参数重新赋值给隐藏层--进行下一步更新

一维函数回归

x_data = np.random.rand(100).astype(np.float32)

y_data = x_data*0.1 + 0.3

Weights = tf.Variable(tf.random_uniform([1],-1,1))

biases = tf.Variable(tf.zeros([1]))

y = Weights*x_data + biases

loss = tf.reduce_mean(tf.square(y-y_data))

optimizer = tf.train.GradientDescentOptimizer(0.5)

train = optimizer.minimize(loss)

init = tf.initialize_all_variable()

sees = tf.Session()

sess.run(init)

for step in range(201):

see.run(train)

if step %20 ==0:

print(step, see.run(Weight),see.run(biases))

2.Session

3.variable

( tf.compat.v1.global_variables_initializer())

tf.assign()为赋值功能

4.placeholder

tf.placehoder(tf.float32)---给定type，一般为float32

用字典的形式赋值

5.激励函数

y=AF（wx)-------非线性

6.添加层

def add_layer(inputs, in_size,out_size,activation_function=None):

7.plot

8.optimizer

9.tensorboard

with tf.name_scopeI('inputs'):

x_s = tf.placeholder(tf.float32,[ None , 1],name = 'x_input')

y_s = tf.placeholder(tf.float32,[None,1],name = 'y_input')

10.分类

import tensorflow as tf
from tensorflow.examples.tutorials.minist import input_data

mnist =input_data.read_data_sets('MNIST_data',one_hot=True)

def add_layer(inputs, in_size, out_size, activation_function=None,):
    # add one more layer and return the output of this layer
    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(inputs, Weights) + biases
    if activation_function is None:
        outputs = Wx_plus_b
    else:
        outputs = activation_function(Wx_plus_b,)
    return outputs

def comput_accuracy(v_xc,y_vs):
    global prediction
    y_pre = see.run(prediction, feed_dict={xs:v_xs})
    correct_prediction = tf.equal(tf.argmax(y_pre,1), tf.argmax(v_ys,1))
    #cast数据转换，mean所有元素的均值
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))  
    result = sess.run(accuracy, feed_dict={xs: v_xs, ys: v_ys})
    return result

prediction = add_layer(xs, 784, 10,  activation_function=tf.nn.softmax)

# the error between prediction and real data
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction),
                                              reduction_indices=[1]))       # loss
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)

sess = tf.Session()
# important step
# tf.initialize_all_variables() no long valid from
# 2017-03-02 if using tensorflow >= 0.12
if int((tf.__version__).split('.')[1]) < 12 and int((tf.__version__).split('.')[0]) < 1:
    init = tf.initialize_all_variables()
else:
    init = tf.global_variables_initializer()
sess.run(init)

for i in range(1000):
    batch_xs, batch_ys = mnist.train.next_batch(100)
    sess.run(train_step, feed_dict={xs: batch_xs, ys: batch_ys})
    if i % 50 == 0:
        print(compute_accuracy(
            mnist.test.images, mnist.test.labels))