Created
February 9, 2019 17:11
-
-
Save shubham7298/4eb161078018a90902b9a91bcd52da37 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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]] |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment