Sparse Accuracy Function

Practical Deep Learning: Image Search Engine Dataset Preprocessing and Helper Functions
2 minutes
Share the link to this page
Copied
  Completed
You need to have access to the item to view this lesson.
One-time Fee
$69.99
List Price:  $99.99
You save:  $30
€66.27
List Price:  €94.67
You save:  €28.40
£55.39
List Price:  £79.13
You save:  £23.74
CA$98.13
List Price:  CA$140.19
You save:  CA$42.06
A$107.73
List Price:  A$153.90
You save:  A$46.17
S$93.76
List Price:  S$133.95
You save:  S$40.19
HK$544.73
List Price:  HK$778.23
You save:  HK$233.49
CHF 61.80
List Price:  CHF 88.29
You save:  CHF 26.48
NOK kr772.72
List Price:  NOK kr1,103.93
You save:  NOK kr331.21
DKK kr494.34
List Price:  DKK kr706.23
You save:  DKK kr211.89
NZ$118.90
List Price:  NZ$169.87
You save:  NZ$50.96
د.إ257.06
List Price:  د.إ367.25
You save:  د.إ110.18
৳8,323.66
List Price:  ৳11,891.45
You save:  ৳3,567.79
₹5,909.11
List Price:  ₹8,441.95
You save:  ₹2,532.83
RM313.06
List Price:  RM447.25
You save:  RM134.19
₦116,728.62
List Price:  ₦166,762.32
You save:  ₦50,033.70
₨19,349.93
List Price:  ₨27,643.94
You save:  ₨8,294.01
฿2,418.69
List Price:  ฿3,455.42
You save:  ฿1,036.73
₺2,421.05
List Price:  ₺3,458.79
You save:  ₺1,037.74
B$406.02
List Price:  B$580.06
You save:  B$174.03
R1,265.11
List Price:  R1,807.38
You save:  R542.27
Лв129.77
List Price:  Лв185.40
You save:  Лв55.62
₩97,597.80
List Price:  ₩139,431.41
You save:  ₩41,833.60
₪261.71
List Price:  ₪373.90
You save:  ₪112.18
₱4,123.18
List Price:  ₱5,890.51
You save:  ₱1,767.32
¥10,762.63
List Price:  ¥15,375.85
You save:  ¥4,613.21
MX$1,416.38
List Price:  MX$2,023.49
You save:  MX$607.10
QR254.03
List Price:  QR362.91
You save:  QR108.88
P950.29
List Price:  P1,357.62
You save:  P407.32
KSh9,046.20
List Price:  KSh12,923.70
You save:  KSh3,877.50
E£3,467.03
List Price:  E£4,953.11
You save:  E£1,486.08
ብር8,622.47
List Price:  ብር12,318.34
You save:  ብር3,695.87
Kz63,865.87
List Price:  Kz91,240.87
You save:  Kz27,375
CLP$68,034.44
List Price:  CLP$97,196.23
You save:  CLP$29,161.78
CN¥506.75
List Price:  CN¥723.96
You save:  CN¥217.21
RD$4,196.84
List Price:  RD$5,995.75
You save:  RD$1,798.90
DA9,336.57
List Price:  DA13,338.53
You save:  DA4,001.96
FJ$158.85
List Price:  FJ$226.94
You save:  FJ$68.09
Q538.15
List Price:  Q768.81
You save:  Q230.66
GY$14,572.68
List Price:  GY$20,819.01
You save:  GY$6,246.32
ISK kr9,629.22
List Price:  ISK kr13,756.62
You save:  ISK kr4,127.40
DH697.40
List Price:  DH996.34
You save:  DH298.93
L1,272.08
List Price:  L1,817.34
You save:  L545.25
ден4,077.86
List Price:  ден5,825.76
You save:  ден1,747.90
MOP$558.50
List Price:  MOP$797.89
You save:  MOP$239.39
N$1,261.49
List Price:  N$1,802.21
You save:  N$540.71
C$2,563.56
List Price:  C$3,662.39
You save:  C$1,098.82
रु9,404.05
List Price:  रु13,434.94
You save:  रु4,030.88
S/264.76
List Price:  S/378.24
You save:  S/113.48
K280.20
List Price:  K400.31
You save:  K120.10
SAR262.74
List Price:  SAR375.36
You save:  SAR112.62
ZK1,920.74
List Price:  ZK2,744.04
You save:  ZK823.29
L329.81
List Price:  L471.18
You save:  L141.36
Kč1,677.50
List Price:  Kč2,396.54
You save:  Kč719.03
Ft26,973.98
List Price:  Ft38,535.91
You save:  Ft11,561.93
SEK kr767.99
List Price:  SEK kr1,097.18
You save:  SEK kr329.18
ARS$69,886.30
List Price:  ARS$99,841.85
You save:  ARS$29,955.55
Bs481.32
List Price:  Bs687.64
You save:  Bs206.31
COP$309,520.29
List Price:  COP$442,190.80
You save:  COP$132,670.50
₡35,473.68
List Price:  ₡50,678.85
You save:  ₡15,205.17
L1,759.47
List Price:  L2,513.64
You save:  L754.17
₲542,904.89
List Price:  ₲775,611.66
You save:  ₲232,706.76
$U3,004.92
List Price:  $U4,292.93
You save:  $U1,288
zł286.84
List Price:  zł409.79
You save:  zł122.95
Already have an account? Log In

Transcript

Hello everyone. In this video we are going to write our sparse accuracy function, which is our last helper function as well. This function is used to check how accurate our model is. Or in other words how often it predicts the correct plus. Basically, it will take the true label the probability distribution from our model. And then based on the two inputs, our goal is to check whether the highest probability is given through class or label.

This was mouthful. Let's explain this in simple plain English. For each true label, we will have an array that is length equal to number of classes in our data set. In our case, it is 10. Each element corresponds to the likelihood of a particular class. So when we put one image to our model, it produces 10 predictions.

And obviously we want the highest number to be the one overcorrect class. So our function will compare whether the index of the maximum element is equal to the true label. The first thing that will check is if there are the same number of elements in the true label and predicted labels. We can do that by simply comparing the lens and assert. If you haven't used the assert method before, here's a crash course. It takes some Boolean statement and checks if it's correct.

If the answer is negative, it will stop our code and want to execute any further. And that's it. Now let's define our variable that will store the number of correct predictions and set it to zero. The one thing I like to do is to iterate through our inputs and compare them. In this example, I will use in range of length true labels. But it doesn't really matter since we made sure that number of predicted labels and true labels has same number of elements so you can use either.

To compare the elements, we need to get the index of the highest probability. We can do it by simply using MP dot arg Max, which takes an array and returns the index of the maximum element. Now that we have the index, we will compare it with a true label. If these two are equal, we'll just add one to our correct predictions. Return the number of predictions divided by number of elements. This will give us a number between zero and one, which will indicate our accuracy.

To sum up what happened here, we compared the index of maximum element with the true label. If these two are equal, we'll increase the number of correct predictions by one and return it by dividing it with the number of elements to get the accuracy. If you have any questions so far, please post them in the comment section. Otherwise, assume the next tutorial

Sign Up

Share

Share with friends, get 20% off
Invite your friends to LearnDesk learning marketplace. For each purchase they make, you get 20% off (upto $10) on your next purchase.