Stack Overflow
Stack Overflow

Questions tagged [average-precision]

30 questions
14
votes
1 answer

Mean average precision (mAP) in tensorflow

I need to calculate the mAP described in this question for object detection using Tensorflow. Average precision(AP) is a typical performance measure used for ranked sets. AveragePrecision is defined as the average of the precision scores after each…
Alberto Merciai
  • 474
  • 1
  • 5
  • 17
13
votes
1 answer

MAP@k computation

Mean average precision computed at k (for top-k elements in the answer), according to wiki, ml metrics at kaggle, and this answer: Confusion about (Mean) Average Precision should be computed as mean of average precisions at k, where average…
Pidhorskyi
  • 1,562
  • 12
  • 19
7
votes
1 answer

How to interpret: Label Ranking Average Precision Score

I am new to Array programming and found it difficult to interpret the sklearn.metrics label_ranking_average_precision_score function. Need your help to understand the way it is calculated and any appreciate any tips to learn Numpy Array…
Pavan Kumar Polavarapu
  • 450
  • 3
  • 11
6
votes
0 answers

Mean average precision (mAP) metric keras

I'm training a keras model that takes item embeddings as pairs and outputs a binary classification (close to word2vec). I need to find the mAP of the model for the recommender system after each epoch in order to be able to compare. I couldn't really…
melowgs
  • 420
  • 1
  • 4
  • 13
6
votes
2 answers

Confusion about (Mean) Average Precision

In this question I asked clarifications about the precision-recall curve. In particular, I asked if we have to consider a fixed number of rankings to draw the curve or we can reasonably choose ourselves. According to the answer, the second one is…
justHelloWorld
  • 6,478
  • 8
  • 58
  • 138
4
votes
4 answers

Best strategy to compute average with high precision

I was comparing two algorithms computing the average of random numbers. First algorithm sums all numbers and divides by the items count in the end Second algorithm computes the average on every iteration and reuses the result when new data is…
jpo38
  • 20,821
  • 10
  • 70
  • 151
2
votes
0 answers

What is the difference between mAP from Mask R-CNN utils.py and mAP from (MS)COCO?

I trained my Mask R-CNN Network with my own data, which i transformed into COCO Style for my Thesis and now i want to evaluate my results. I found two methods to do that. One method is the evaluation from COCO itself. Mask R-CNN itself shows how to…
Mob
  • 409
  • 1
  • 5
  • 14
2
votes
2 answers

Apply rolling mean function on data frames with duplicated indices in pandas

I have difficulty to use pd.rolling_mean function on the following data frame containing duplicated indices: amount 20140101 3 20140102 4 20140103 3 20140103 5 20140103 1 20140104 5 …
user6396
  • 1,832
  • 6
  • 23
  • 38
2
votes
2 answers

A faster R implementation of average precision at N

The excellent Metrics package provides a function to calculate average precision: apk. The problem is, it's based on a for loop, and it's slow: require('Metrics') require('rbenchmark') actual <- 1:20000 predicted <- c(1:20, 200:600, 900:1522,…
Zach
  • 29,791
  • 35
  • 142
  • 201
1
vote
1 answer

How do I fix a default error on my switch statement?

So, I have to make a program that shows a menu of a bank, with several options for the user to input. For an input G, the user enters a deposit, which is stored inside an array. For an input S, it displays the sum of all deposits. For D, it…
RedPumpkin
  • 11
  • 1
1
vote
0 answers

How do I calculate Average Precision with r-cnn?

I understand that the way AP is calculated lowers the threshold of any confidence, and for each threshold, it is calculated and graphed. Then, what is the threshold that is lowered when calculating the AP through R-CNN? Is that the result of the…
powerpowe
  • 11
  • 1
1
vote
1 answer

How to calculate average precision and mean average precision in information retrieval

I have a dictionary called ret_docs of retrieved documents (values) based on queries (keys) that looks like this: {'q1': ['d51', 'd874', 'd486', 'd329', 'd114'], 'q2': ['d51', 'd1147', 'd12', 'd100', 'd114'], 'q3': ['d707', 'd144', 'd542', 'd329',…
Hefe
  • 421
  • 3
  • 23
1
vote
1 answer

Why Average Precision and Average Recall = -1 when using tensorflow to do object detection?

I'm using Google Colab, Tensorflow version 1, SSD mobile net v2 CoCo model to train a custom dataset. But evaluation on a custom dataset above the image that AP and AR = -1. I don't understand why the result appears? Can you answer this…
Thong Vo
  • 67
  • 1
  • 6
1
vote
1 answer

Parameters for sklearn average precision score when using Random Forest

I have been trying to fiddle with sklearn metrics, particularly average_precision_score. However, I could only find one example of computing average_precision_score in the sklearn documentation and that too using SVM. Underneath is the code snippet…
Vipul Mehra
  • 141
  • 1
  • 2
  • 8
1
vote
0 answers

VBA (Excel) which average more precise, worksheetfunction or step-wise

I wrote a macro which as a tiny task on the side also calculates the average of around 39000 different values. I noticed that using WorksheetFunction.Average and calculating the average "step-wise" yield different results, but only at the 15th digit…
Nat100
  • 11
  • 2
1
2