Python Question

import matplotlib.pyplot as plt

import numpy as np

import _pickle as pickle

import platform

def load_pickle(f):

version = platform.python_version_tuple()

if version[0] == '2':

return pickle.load(f)

elif version[0] == '3':

return pickle.load(f, encoding='latin1')

raise ValueError("invalid python version: {}".format(version))

def load_batch(filename):

""" load single batch of cifar """

with open(filename, 'rb') as f:

datadict = load_pickle(f)

X = datadict['data']

# print(X.shape)

Y = datadict['labels']

X = X.reshape(10000, 3, 32, 32).transpose(0,2,3,1).astype("float")

Y = np.array(Y)

return X, Y

# get a batch of images, and a batch of test images.

dataimages, datalables = load_batch('data_batch_1')

testimages, testlables = load_batch('test_batch')

print(dataimages.shape)

print(testimages.shape)

def classify(dataimages, datalables, testimages, testlables):

# Step 1: Extract one image randomly from test images, call it testimage

rn = np.random.randint(10000)

testimage = testimages[rn]

testlable = testlables[rn]

plt.imshow(testimage)

result = dataimages - testimage

result = np.abs(result)

res_sum = np.sum(result, axis = (1, 2, 3))

minindex = np.argmin(res_sum)

res_image = dataimages[minindex]

res_lable = datalables[minindex]

return res_lable == testlable

res = classify(dataimages, datalables, testimages, testlables)

print(res)

eff=0

for i in range(100):

res=classify(dataimages,datlabes, tetsimages,testlables)

if res:

eff+=1

print(eff)

# Question # Normalize the images by subtracting a mean value of each image from its pixels

# Calculate the efficiency again with this new method

# Print the resultant efficiency values of both the ways.