zihaomu

@the-star-sea Please keep one in the mobile and normal models, as we discussed before, to avoid confusing users.

> I suggest we remove DB from opencv_zoo after this pull request is merged. Hi @fengyuentau, how about leaving it to the next PR to remove `DB` model, because we...

> @zihaomu Please update benchmark results on this model. Hi, @fengyuentau the benchmark results will be updated at PR #73, the student will complete it in the near future.

Ok, let's wait.

After [this PR](https://github.com/opencv/opencv/pull/22614) is merged, PP-OCR_v3 can be supported and loaded with high-level API. And I think we can only put PP-OCR_v3 in `opencv_zoo` since it has better accuracy.

@the-star-sea, please refactor the code according to the test framework for other models. And after that, I think we can merge it.

Hi @vpisarev, I get your point now. A very useful trick so that the end of the loop can still use SIMD acceleration. That means there some tails will be...

Hi @EchoEkhi. Your model has multiple outputs. For this model, I recommend using the following ways to ensure the correct output. C++ code example. ``` std::vector outs; std::vector outBlobNames =...

> But the default behaviour was changed without documentation in the changelog, as far as I can tell. Would you still consider this a compatibility break or is this a...

> @zihaomu Friendly reminder about tests. Thanks. I will keep working on it.