logesticReg.py

import cv2
import numpy as np
import os
import matplotlib.pyplot as plt
from  scipy.spatial import distance


folder='cats'
f=os.listdir(folder)
cats=[]
dogs=[]
train_set=np.array([])
y=np.array([0,0,0,0,0,0,1,1,1,1,1,1,1])
one = np.ones(10000)
for i in f:
    img=cv2.imread(folder+'/'+i,0)
    img=cv2.resize(img,(100,100))
    img=img.flatten()
    img=np.reshape(img,(10000,1))
    train_set=np.append(train_set,img)
    cats.append(img)

plt.show()

folder='dogs'
f=os.listdir(folder)
for i in f:
    img=cv2.imread(folder+'/'+i,0)
    img=cv2.resize(img,(100,100))
    img=img.flatten()
    img=np.reshape(img,(10000,1))
    train_set=np.append(train_set,img)

    dogs.append(img)

train_set=np.reshape(train_set,(13,10000))

X=train_set
#==============================================================
w=0
b=0
cos=[]
e=[]
def init(s):
    global w,b
    w=np.zeros((s,1))
    b=0
    return w,b

def sigmoid(x):
    return (1/(1+np.exp(-x)))

def forward():
    z=np.dot(X,w)+b
    a=sigmoid(z)
    return a

w,b=init(X.shape[1])
print(X.shape)
print(y.shape)
y=y.reshape(13,1)
lr=0.009
def lo():
    a=forward()
    m=X.shape[0]
    #cost=(-1/m)*np.sum(y*np.log(a)+(1-y)*np.log(1-a))
    dw=(1/m)*np.dot(X.T,(a-y))	#dw is dL/dw 
    db=(1/m)*np.sum(a-y)		#db is  dL/dz 
    return dw,db#,cost

for i in range(50000):
    dw,db=lo()
    #cos.append(cost)
    e.append(i)
    w=w-dw*lr
    b=b-db*lr
print("Trained!!",w.shape,b)

img=cv2.imread('test.jpeg',0)

img=cv2.resize(img,(100,100))
img=img.flatten()
img=np.reshape(img,(10000,1))
print(img.shape)
print(np.dot(img.T,w)+b)
#output => [[-310346.95084615]]