You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I come from a research team which works on bugs in real-world applications.
I want to make a report about a potential functionality/performance improvement in your project.
In file (worker/analyzer.js):
if (containsCat && !containsDog) {
type = PostType.CAT;
} else if (containsDog && !containsCat) {
type = PostType.DOG;
} else if (containsCat && containsDog) {
type = PostType.BOTH;
}
If we use objectLocalization, it would work better to detect multiple objects (cat/dogs) from the image. Though labelDetection could return labels for the 2-3 objects separately in some cases, it actually is designed for offering one tag for the whole image. On the contrary, objectLocalization outputs one tag for every object detected in the image, which is more stable and reliable.
Perhaps someone might be able to confirm if these seem reasonable. Also, if so, the fix seems like it would be pretty straightforward, and I’m happy to create a pull request if that will be helpful.
If you are not offended by it, we may include your response as a percentage number (e.g. xx% of applications faces xx problem, and xx% of them confirms it) in our research paper.
Thanks.
The text was updated successfully, but these errors were encountered:
Hi,
I come from a research team which works on bugs in real-world applications.
I want to make a report about a potential functionality/performance improvement in your project.
In file (
worker/analyzer.js
):If we use
objectLocalization
, it would work better to detect multiple objects (cat/dogs) from the image. ThoughlabelDetection
could return labels for the 2-3 objects separately in some cases, it actually is designed for offering one tag for the whole image. On the contrary,objectLocalization
outputs one tag for every object detected in the image, which is more stable and reliable.Perhaps someone might be able to confirm if these seem reasonable. Also, if so, the fix seems like it would be pretty straightforward, and I’m happy to create a pull request if that will be helpful.
If you are not offended by it, we may include your response as a percentage number (e.g. xx% of applications faces xx problem, and xx% of them confirms it) in our research paper.
Thanks.
The text was updated successfully, but these errors were encountered: