The question Why does VGG16 double number of features after each maxpooling layer? was put on hold after I had already answered it. As such, I think the OP cannot accept my answer (correct?).

In hindsight, I should have seen that coming, because I think that Machine Learning questions are more at risk of being off-topic than other questions. However, unlike the question I mentioned last time (Backpropagation in multi-layer perceptron (MLP) doesn't converge), which I voted to close, this time there's not a line of code in the OP's question: it's purely a question on a certain CNN architecture (VGG16).

If I edit the question removing the reference to Jeremy Howard's fast.ai course, and I add a reference to the paper where VGG16 had been presented, do you think the question could be opened again? Is it acceptable if I edit the question, instead than the OP? I'm not begging for the question to be reopened, just exploring a possibility. If you think it has to be closed, I won't do anything.

| |
  • 2
    $\begingroup$ The question is not off-topic and I don't understand why it was closed as such. It does look rather unclear, at least for people not very familiar with the VGG16 architecture. I think you should edit (no need to remove the reference to the course, but make the Q clearer to everybody) and vote to reopen, sure. $\endgroup$ – amoeba Nov 6 '17 at 15:08
  • 3
    $\begingroup$ Apart from that, I am pretty sure that it's possible to accept answers on closed questions. $\endgroup$ – amoeba Nov 6 '17 at 15:08
  • 2
    $\begingroup$ BTW, why didn't you upvote the question? If you chose to answer it, then presumably you found it a "useful and clear" question, which are criteria for upvoting. $\endgroup$ – amoeba Nov 6 '17 at 15:28
  • 2
    $\begingroup$ uh, sorry, no, I didn't upvote it because I didn't find it very clear (although indeed very useful), but at the same time not so unclear that it should be closed...an "average" question which didn't need either upvoting or downvoting, but which was "good enough" to be worth answering. I think it's quite clear now (after my edit), so I'll upvote: I hope that doesn't make me sound presumptuous! $\endgroup$ – DeltaIV Nov 6 '17 at 15:44
  • $\begingroup$ pardon, our edits: I didn't notice you also made an edit. $\endgroup$ – DeltaIV Nov 6 '17 at 15:48

I think you are being too cautious here.

We close a lot of questions and some of the decisions are inevitably wrong or at least not optimal. If you see a question that was closed but you think it should be re-opened, then vote to re-open! To increase the chances of reopening, you can do two things:

  1. Post a comment explaining why you think this question should be re-opened.
  2. Edit the question to make it as clear and as nicely/cleanly formatted as possible.

Then wait and see if it gets re-opened. Only if it doesn't, then you can post on Meta drawing extra attention to the issue. But normally that should not be the first thing to do (at least given that you have enough rep to edit and to cast re-open votes).

Question put on hold after I already answered it: can I edit it?

Of course you can.

| |
  • 7
    $\begingroup$ It's probably worth me mentioning that this question was in fact reopened by the community (i.e. by votes of ordinary users with enough reputation to vote to reopen). This is exactly how the system should work. $\endgroup$ – Glen_b Nov 6 '17 at 22:24

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .