逻辑斯特回归tensorflow实现

calss

#!/usr/bin/python2.7
#coding:utf-8

from __future__ import print_function
import tensorflow as tf

# Import MNIST data
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("../Mnist_data/", one_hot=True)
print(mnist)

# Parameters setting
learning_rate = 0.01
training_epochs = 25 # 训练迭代的次数
batch_size = 100   # 一次输入的样本
display_step = 1

# set the tf Graph Input & set the model weights
x = tf.placeholder(dtype=tf.float32, shape=[None,784], name="input_x")
y = tf.placeholder(dtype=tf.float32, shape=[None,10],  name="input_y")

#set models weights,bias
W=tf.Variable(tf.zeros([784,10]))
b=tf.Variable(tf.zeros([10]))

# Construct the model
pred=tf.nn.softmax(tf.matmul(x,W)+b)  # 归一化,the possibility of getting the right value

# Minimize error using cross entropy & set the gradient descent
cost=tf.reduce_mean(-tf.reduce_sum(y*tf.log(pred),reduction_indices=1)) #交叉熵，reducion_indices=1横向求和
optimizer=tf.train.GradientDescentOptimizer(learning_rate).minimize(cost)

# Initialize the variables (i.e. assign their default value)
init = tf.global_variables_initializer()

# Start training
with tf.Session() as sess:

    # Run the initializer
    sess.run(init)

    # Training cycle
    for epoch in range(training_epochs):
        avg_cost = 0.
        total_batch = int(mnist.train.num_examples/batch_size)
        # Loop over all batches
        for i in range(total_batch):
            batch_xs, batch_ys = mnist.train.next_batch(batch_size)
            # Run optimization op (backprop) and cost op (to get loss value)
            _, c = sess.run([optimizer, cost], feed_dict={x: batch_xs,
                                                          y: batch_ys})
            # Compute average loss
            avg_cost += c / total_batch
        # Display logs per epoch step
        if (epoch+1) % display_step == 0:
            print("Epoch:", '%04d' % (epoch+1), "cost=", "{:.9f}".format(avg_cost))

    print("Optimization Finished!")

    # Test model
    correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
    # Calculate accuracy
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
    print("Accuracy:", accuracy.eval({x: mnist.test.images, y: mnist.test.labels}))

linear regression

from __future__ import print_function

import tensorflow as tf
import numpy as np

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

# 1.训练的数据 # Make up some real data
x_data = np.linspace(-1,1,300)[:, np.newaxis]
noise = np.random.normal(0, 0.05, x_data.shape)
y_data = np.square(x_data) - 0.5 + noise

# 2.定义节点准备接收数据
#  define placeholder for inputs to network
xs = tf.placeholder(tf.float32, [None, 1])
ys = tf.placeholder(tf.float32, [None, 1])

# 3.定义神经层：隐藏层和预测层
#  add hidden layer 输入值是 xs，在隐藏层有 10 个神经元
l1 = add_layer(xs, 1, 10, activation_function=tf.nn.relu)

# add output layer 输入值是隐藏层 l1，在预测层输出 1 个结果
prediction = add_layer(l1, 10, 1, activation_function=None)

# 4.定义 loss 表达式
#  the error between prediciton and real data
loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys - prediction), reduction_indices=[1]))

# 5.选择 optimizer 使 loss 达到最小
#  这一行定义了用什么方式去减少 loss，学习率是 0.1
train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

# important step 对所有变量进行初始化
init = tf.initialize_all_variables()

with tf.Session() as sess:
    # 上面定义的都没有运算，直到 sess.run 才会开始运算
    sess.run(init)
    #  迭代 1000 次学习，sess.run optimizer
    for epoch in range(1000):
    #  training train_step 和 loss 都是由 placeholder 定义的运算，所以这里要用 feed 传入参数
        _, cost = sess.run([train_step, loss], feed_dict={xs: x_data, ys: y_data})
        if (epoch+1) % 50 == 0:
    # to see the step improvement
            print("Epoch:", '%04d' % (epoch + 1), "cost=", "{:.9f}".format(cost))