pytorch/examples

Doc comment on `accuracy` method in imagenet example, incorrect?

Open

#312 opened on Feb 27, 2018

View on GitHub
 (1 comment) (0 reactions) (0 assignees)Python (21,634 stars) (9,429 forks)batch import
good first issue

Description

I'm confused with the doc comment for the accuracy function in the imagenet example:

def accuracy(output, target, topk=(1,)):
    """Computes the precision@k for the specified values of k"""
    maxk = max(topk)
    batch_size = target.size(0)

    _, pred = output.topk(maxk, 1, True, True)
    pred = pred.t()
    correct = pred.eq(target.view(1, -1).expand_as(pred))

    res = []
    for k in topk:
        correct_k = correct[:k].view(-1).float().sum(0, keepdim=True)
        res.append(correct_k.mul_(100.0 / batch_size))
return res

https://github.com/pytorch/examples/blob/master/imagenet/main.py#L298-L299

This seems like it computes accuracy and not precision as false positives are not accounted for. Should the doc comment read "Computes the accuracy@k for the specified values of k" or is my understanding of precision for object detection incorrect?

Many thanks for pytorch, it's a great library!

Contributor guide

Tech stack
python
Domain
documentationmachine learning
Issue type
documentation
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
1
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
under 1 hour
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
stale
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
clear
Prerequisites
None
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
95
Research direction
Change the doc comment in imagenet/main.py line 298-299 from 'precision@k' to 'accuracy@k'. The function computes top k accuracy, not precision. No other changes needed.
Doc comment on `accuracy` method in imagenet example, incorrect? · pytorch/examples#312 | Good First Issue