首先得先把opencv安装上。
在PC上我使用的是anaconda,直接输入:
conda install --channel https://conda.anaconda.org/menpo opencv3
测试代码:
import cv2
print(cv2.__version__)
这一步真简单,网上也到处能搜到,我这里就是记个笔记。
第二步,使用opencv来读取图像:
import cv2
from matplotlib import pyplot as plt
#读取图像
img=cv2.imread('Test3.jpg',cv2.IMREAD_COLOR)
#显示图像的方法1
cv2.imshow('Test3',img)
k=cv2.waitKey(0)
#显示图像的方法2
#首先得把GRG调换个个头
img3=img[:,:,::-1]
plt.imshow(img3)
plt.show()
为了适合Mnist模型,我们还得转成灰度图,反色,并缩放到28*28
img=cv2.imread('Test3.jpg',cv2.IMREAD_COLOR)
img =cv2.resize(img, (28, 28), interpolation=cv2.INTER_CUBIC)
img = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
img = 0xFF-img
cv2.imshow('Test3',img)
k=cv2.waitKey(0)
下面读取w、b参数,还得把输入图像像素归一化
然后直接计做矩阵乘加、softmax输出:
import cv2
from matplotlib import pyplot as plt
img=cv2.imread('Test3.jpg',cv2.IMREAD_COLOR)
img =cv2.resize(img, (28, 28), interpolation=cv2.INTER_CUBIC)
img = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
img = 0xFF-img
img = img/255
img = img.reshape(784)
testx = [img]
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
import pandas as pd
from pandas import Series,DataFrame
data = pd.read_csv('mnist_w.csv')
#print(data.shape)
usew = data.values
data = pd.read_csv('mnist_b.csv')
useb = data.values
useb = useb.reshape(1,10)#必须确定大小,否则会出错
a1 = mat(img);
a2 = mat(usew);
a4 = a1*a2+useb
#计算softmax
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)) )
最后得到输出:
0.0303718806336
0.0306637445764
0.0985644947741
0.496698573451
0.0684541058624
0.193191997366
0.0177791782552
0.0252268936033
0.0210481976761
0.0180009338012
预测值= 3
明显,预测值为3,并且结果和直接调用tensorflow一致!