Sergei Belousov

@yaseryacoob I hope my code is more "engineering" than "research" because I'm an engineer, not a research scientist in general 😂 But if you find it difficult, please feel free...

@yaseryacoob It's pretty cool idea is to train external networks that will predict the delta between student and teacher! If it works and computational complexity for both networks will be...

@yaseryacoob I added an experiment with iterative refinement to my to-do list. I'll try it when I have free time :) It will be great if you research our work...

Hi, I think that you should find an information bottlenecks in network. I didn't test this network with long text sequences.

Hi, thanks for your feedback. This issue was fixed in master, but pypi package has not this fix yet. I'll try to rebuild pypi package as soon as I can.

@TommasoBendinelli Thanks for your feedback. Currently, I have no plans to support metrics for the instance segmentation task.

There is implemented COCO evaluation protocol in actual release version. https://github.com/bes-dev/mean_average_precision/releases/tag/0.0.2.1

@vpenades * Random values are sampling from standard normal distribution N(0, 1). * We truncate the style values using [average style vector](https://github.com/bes-dev/random_face/blob/86ae87cbe5a98712abfa189845890bcbd1df8ef3/random_face/engine_base.py#L54) * You can find more information about output...

@johnfelipe please, provide more information. Looks like you run code on the system without GUI

@dinarkino What about "async mode". This mode allows to predict bounding boxes by network and compute metric in parallel processes, it doesn't provide to parallel computation of metric. And I...