Vlad Vinogradov

Results 12 comments of Vlad Vinogradov

Thank you for the sample. Yes, I understand that we can stack images into one tensor, but the problem is in different sizes of images that might come (btw, this...

@shazhumao, change parameter `max_boxes` of method `yolo_eval` in `keras_yolo.py` to desired value. By default `max_boxes=10`.

Any updates? The feature would be usefull indeed for debugging locally

As a workaround I found a solution to change the default parameters of the Docker daemon. May be suitable for those who have rights to change them: 1. Open this...

The same problem with Places365 model. Is there any special preprocessing? I tried grayscale images in ranges [0, 1] and [0, 255]. Both give nearly the same output. I'm guessing,...

I also find it useful to support other alphabets except binary. Look, for example, at [ORB descriptors](https://opencv-python-tutroals.readthedocs.io/en/latest/py_tutorials/py_feature2d/py_orb/py_orb.html#orb-in-opencv) in OpenCV, specifically parameter `WTA_K`. When it's 3 or 4, the hamming distance...

Yes, we now have `poetry` setup. The only thing left to do is to give instructions to contributors on how to use it. So, I keep this issue open until...

Discussed with @Animatory @VladislavPatrushev @VladVin to add instructions on how to use our repo's examples instead of adding them into the package.

Indeed, we need a documentation for this

Hey @DomInvivo , Thank you for the reply. Update here: I was exploring MPNN++ and GPS++ models, and when I read the [GPS++ paper](https://arxiv.org/abs/2212.02229) I came into understanding that there's...