深度学习之神经网络（一）

最新推荐文章于 2021-12-18 08:29:57 发布

山复尔尔，

最新推荐文章于 2021-12-18 08:29:57 发布

阅读量228

点赞数

分类专栏： tensorflow 文章标签：神经网络深度学习

本文链接：https://blog.csdn.net/qq_41511262/article/details/105287274

版权

tensorflow 专栏收录该内容

21 篇文章 0 订阅

订阅专栏

文章目录

深度学习之神经网络（一）

深度学习之神经网络（一）

一、深度学习：传统到现在

在这里插入图片描述

二、TensorFlow介绍

在这里插入图片描述

'''
linear regression experiment, hope you can know:
1. how to design the learning model
2. optimize the model
3. dealing with the dataset

Original Author: Aymeric Damien
Edited by Wei Li for ChinaHadoop Deep learning course
Project: https://github.com/aymericdamien/TensorFlow-Examples/
'''


import tensorflow as tf
import numpy
rng = numpy.random

# model params
learning_rate = 0.02
training_epochs = 3000
display_step=50
# 
train_X = numpy.asarray([3.3,4.4,5.5,6.71,6.93,4.168,9.779,6.182,7.59,2.167,
                         7.042,10.791,5.313,7.997,5.654,9.27,3.1])
train_Y = numpy.asarray([1.7,2.76,2.09,3.19,1.694,1.573,3.366,2.596,2.53,1.221,
                         2.827,3.465,1.65,2.904,2.42,2.94,1.3])
n_samples = train_X.shape[0]

# tf Graph Input
X = tf.placeholder("float")
Y = tf.placeholder("float")

# Set model weights
W = tf.Variable(rng.randn(), name="weight")
b = tf.Variable(rng.randn(), name="bias")

# Construct a linear model
pred = tf.add(tf.multiply(X, W), b)

# Mean squared error
cost = tf.reduce_sum(tf.pow(pred-Y, 2))/(2*n_samples)
# Gradient descent
optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)

# Initializing the variables
init = tf.global_variables_initializer()

# Launch the graph
with tf.Session() as sess:
    sess.run(init)

    # Fit all training data
    for epoch in range(training_epochs):
        for (x, y) in zip(train_X, train_Y):
            sess.run(optimizer, feed_dict={X: x, Y: y})

        # Display logs per epoch step
        if (epoch+1) % display_step == 0:
            c = sess.run(cost, feed_dict={X: train_X, Y:train_Y})
            print("Epoch:", '%04d' % (epoch+1), "cost=", "{:.9f}".format(c), \
                "W=", sess.run(W), "b=", sess.run(b))


    training_cost = sess.run(cost, feed_dict={X: train_X, Y: train_Y})
    print("Training cost=", training_cost, "W=", sess.run(W), "b=", sess.run(b), '\n')

 

    # the testing data
    test_X = numpy.asarray([6.83, 4.668, 8.9, 7.91, 5.7, 8.7, 3.1, 2.1])
    test_Y = numpy.asarray([1.84, 2.273, 3.2, 2.831, 2.92, 3.24, 1.35, 1.03])

    print("Tssting...")
    testing_cost = sess.run(
        tf.reduce_sum(tf.pow(pred - Y, 2)) / (2 * test_X.shape[0]),
        feed_dict={X: test_X, Y: test_Y})  # same function as cost above
    print("Test LOSS=", testing_cost)
    print("Final Loss:", abs(
        training_cost - testing_cost))