在树莓派上建立一个最简单手写体识别系统（一）

目标，在树莓派上建立一个最简单的手写体识别系统。

规划如下：

1 在PC上做使用tensorflow做一个最简单的softmax模型，把模型参数全部保存下来

2 在PC上，使用python读取模型参数，编写模型代码，使用opencv读取图片，模型预测

3 将代码直接挪到树莓派上运行，并测试模型预测时间

1代码：

#coding=utf-8
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
from datetime import datetime
import math
import time
#载入数据集
mnist = input_data.read_data_sets("MNIST_data",one_hot=True)

# 配置每个 GPU 上占用的内存的比例
#gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.95)
#sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options))

x = tf.placeholder(tf.float32,[None, 784])
W = tf.Variable(tf.zeros([784, 10]))
b = tf.Variable(tf.zeros([10]))
y = tf.nn.softmax(tf.matmul(x,W)+b)
y_ = tf.placeholder(tf.float32,[None, 10])
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y), reduction_indices=[1]))
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
init = tf.global_variables_initializer()
sess = tf.Session() #无GPU时候打开
sess.run(init)

for i in range(1000):
batch_xs, batch_ys = mnist.train.next_batch(100)
sess.run(train_step, feed_dict = {x: batch_xs, y_: batch_ys})

correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
print(sess.run(accuracy, feed_dict={x:mnist.test.images, y_: mnist.test.labels}))

#保存训练出来的参数
seeb = sess.run(b)
seew = sess.run(W)
print(seeb.shape)
print(seew.shape)
import pandas as pd
from pandas import Series,DataFrame
df = DataFrame(seew)
df.to_csv('mnist_w.csv',index=False)
df = DataFrame(seeb)
#print(df)
df.to_csv('mnist_b.csv',index=False)

读取保存的参数，自己建立模型，和tensorflow结果对比：

testx = [mnist.test.images[0]]
testy = [mnist.test.labels[0]]
#tensorflow预测结果
sess.run(y, feed_dict={x:testx})

#自己搭的softmax模型预测结果
from numpy import *;
import numpy as np; #这个方式使用numpy的函数时，需要以np.开头。
import math

testx = [mnist.test.images[0]]
a1=mat(testx);
a2=mat(seew);
a3=a1*a2;
a4 = a3+seeb
#print(a4)
etab=[0,0,0,0,0,0,0,0,0,0]
for i in range(0,10):
t = a4[0:,i]
t = t.tolist()[0]
t = t[0]
etab[i] = math.exp(t)
a = sum(etab)
for i in range(0,10):
t = etab[i]
t = t/a
print(t)
print ( "预测值=",etab.index(max(etab)) )