« first day (5050 days earlier)      last day (41 days later) » 

1:00 AM
@Marco I'm surprised you needed anyone to write an answer to tell you "adjust filter size" or "pad the input." No part of the answer you have received on AI.SE contains "theoretical knowledge" of SSIM -- these are just commonsensical steps that pertain to image processing and signal filtering. Nor does any part of the answer justify what about changing the filter or padding the image is or is not "correct," which was your main request.
@Marco the existence of tags doesn't have anything to do with whether or not a question is on-topic because practically any user, no matter how misguided, can create a tag.
2
1:45 AM
@Sycorax I needed someone to guide me with a knowledgeable answer, and that's what it felt like. If it was obvious to you that just had to follow these recommendations, great, but not for me. Yes, I was very satisfied, weren't you satisfied?
@Sycorax But the tag is well used, and as I showed, there are many questions that used it.
1:58 AM
All of your questions can be answered by re-reading my messages.
What messages?
Your only practical answer was that: stats.stackexchange.com/questions/649126/…
What's going on, @Sycorax? Some problem?
2:38 AM
2 hours ago, by Sycorax
@Marco I'm surprised you needed anyone to write an answer to tell you "adjust filter size" or "pad the input." No part of the answer you have received on AI.SE contains "theoretical knowledge" of SSIM -- these are just commonsensical steps that pertain to image processing and signal filtering. Nor does any part of the answer justify what about changing the filter or padding the image is or is not "correct," which was your main request.
@Sycorax my questions can't be answered by re-reading these messages.
 
10 hours later…
1:04 PM
@Marco, @Sycorax I would like to clarify that a question whose answer consists of "commonsensical steps" is not off topic for that reason alone. But the nature of this answer (and the question itself) is entirely programming oriented and appears not to require any specialized statistical knowledge or reasoning, suggesting an appropriate venue for obtaining correct, authoritative answers would be one populated by experienced programmers interested in answering programming questions.
2
 
3 hours later…
 
1 hour later…
5:03 PM
@whuber Why the question is entirely programming oriented? Gaussian filtering is a statistical approach.
"The Gaussian Smoothing Operator performs a weighted average of surrounding pixels based on the Gaussian distribution. It is used to remove Gaussian noise and is a realistic model of defocused lens. Sigma defines the amount of blurring. The radius slider is used to control how large the template is. Large values for sigma will only give large blurring for larger template sizes. Noise can be added using the sliders."

https://www.southampton.ac.uk/~msn/book/new_demo/gaussian/#:~:text=The%20Gaussian%20Smoothing%20Operator%20performs,defines%20the%20amount%20of%20blurring.
5:22 PM
@Marco We have to go by what you ask. "How to use a ... function" is the same kind of question, albeit at a higher level, as "what button do I push in my stats software to do an analysis." Yes, both do concern stats; but no, neither is on topic here.
5:48 PM
@whuber Well, perhaps the question could be improved to specify what exactly in the function I need help (use of Gaussian filtering), but that's a detail. And no, programming questions involving statistics/machine learning are not off-topic.
@whuber Questions concerning stats are on topic here.
"There are certain subjects that will probably get better responses on our sister sites. If your question is about

Programming, ask on Stack Overflow. If the language is statistically oriented (such as R, SAS, Stata, SPSS, etc.), then decide based on the nature of your question: if it needs statistical expertise to understand or answer, ask it here; if it's about the implementation of an algorithm, routine data processing, or details of the language, then please refer to the collection of links to resources we maintain."
"if it needs statistical expertise to understand or answer, ask it here"
Here is one of the reasons that users can vote to close a question.

"Programming or data request
Questions primarily concerned with programming are not on-topic at stats.SE. Questions about how to obtain data sets are not on topic at stats.SE, but are on-topic on the Open Data site."

It is eventually a matter of opinion or community culture for what constitutes being 'primarily' about programming.
If questions involving programming cannot be posted, there are thousands of questions that should have been closed, then.
Example of thousands questions involving TensorFlow that exists here in Cross Validated: stats.stackexchange.com/search?q=tensorflow
Questions involving programming are allowed. Questions primarily about programming are not allowed. Still, you're right that the history of posts doesn't entirely follow that rule. There can be multiple reasons for this.
The rules can change, although I don't know about this particular rule's history. People disagree about what constitutes being 'primarily' about programming. It can even be the case that people knowingly and directly contradict the rules. Some people are also not familiar with the rules, and sometimes unknowingly break the rules. Those are some reasons anyway.
6:10 PM
@Galen My question is not primarily about programming.
@Marco Then, if you're serious about getting an answer, your course is straightforward: change the question to show explicitly what it primarily is about.
I specifically showed it in the content of the question.
@Marco The fact that we're still discussing it here strongly indicates otherwise.
@whuber The fact that you disagree does not imply that my question is primarily about programming.
These are subjective opinions in my opinion.
Where is the proof that my question is primarily about programming?
@Marco Bingo; it is subjective. Individuals, and communities thereof, will form opinions about these types of things. From what I've seen from the feedback you've received in this chat, as well as your post (now deleted?) being closed, your opinion on this issue doesn't appear to comport with common opinion on this site.
6:22 PM
@Galen I'll say it another way, without putting my opinion at stake: the fact is that there was no proof given that my question is primarily about programming, closing the question without proof is a closure based on subjective opinions.
You were even one of those who voted to close my question. I ask you: can you prove that my question is primarily about programming?
@Galen but it should not be subjective.
It's about a change in Gaussian filter size... it's a statistical subject!
Is Gaussian filter size a primary programming topic?
Echoing @whuber's comment:

> Then, if you're serious about getting an answer, your course is straightforward: change the question to show explicitly what it primarily is about.
3
@Galen I already showed, just look at the link to see what the filter size is about, and the simple fact that it is about SSIM already denotes that it is a question about statistics.
Once again I challenge you in proving that the question is primarily about programming.
Can you prove?
6:39 PM
I don't need to prove that your question is off-topic. That's not how this site works. If you want the way that this site operates to change, I am not among the people you would need to persuade.
4
@Galen So you close the question without any basis? Only on subjective conviction?
You who must not know how the site works, to close a question, a justification was given, but this justification is invalid.
@Marco If memory serves, I voted to close your question because it lacked sufficient details or clarity. And yes, that was my subjective conviction, which is considered an acceptable basis on this site. The site only showed the majority reason for closure when closure occurred, which was on the basis of being primarily about programming.
It doesn't matter, it was closed and there is no basis for the closure. Opinion proves nothing.
I suspect that screenshot is showing the consensus reason, not each voters reason.
We agree, opinion proves nothing. Proof is not necessary for voting to close on this site. It is according to either three votes from peers, or closure by a moderator. Your post was closed by your peers on this site.
2
@Galen I'm surprised that you talked indirectly to me about improving my arguments on that occasion, citing rigorous argument, when now you say that you don't need to prove that my question is off-topic, that a subjective opinion is enough. How much inconsistency.
@Galen Right, and closing the question in this way has a null argument.
6:55 PM
Oh, the Physics post about rigor was leapfrogging the earlier discussion about mathematically understanding sufficient statistics. It wasn't intended as commentary about your post.
Ok, so, it seemed very suspicious to me, disregard my statement then, sorry about that, less bad.
I'm not sure what a null argument is. An argument with no premises?
Yes
kk, thanks for clarifying.
No problem.
 
4 hours later…
11:18 PM
15
A: Why do we have a tensorflow tag if questions about programming are off topic?

Glen_bThe actual criterion is in our help/on-topic (search for programming). A question containing code or asking about code -- or even sometimes asking for code is not automatically off topic, but many are. Briefly, if the issue is one that takes our subject-matter knowledge to answer it belongs here....

2

« first day (5050 days earlier)      last day (41 days later) »