Sanghoon Hong

Hi all, Sorry for a late comment. I'm attending a conference right now, I'll check the issue when I get back to my home One more thing, We've trained a...

Thank you for your report. I'm currently on NIPS2016 to present our work at a workshop tomorrow. I'll definitely check it when I get back to my home.

The current codes set bounding box regression targets to be x10 of the real targets. The hyper parameter (=x10) comes from the original py-faster-rcnn. I guess it enhances the trained...

The effects of modifying loss weight and of bounding box targets are different since the loss function is not linear.

Thanks for your comment, I've updated the comment section. ----- Talking about the second change, I encountered such a case when I opened an GLB with an embedded binary buffer....

> ... The important point is that this will still have problems with other referenced data like images. ... That was a good point. I reverted the base64 encoder and...

Sorry for the late reply. Due to a personal reason (a newborn baby), I couldn't have some spare time to work on this. I'll take a look at the issue...

@jkuhlmann I resolved compile warnings by adding explicit castings. While debugging on Windows, I found another bug and fixed it. The bug was related to `fwrite()`. On Windows, the function...

I have a similar issue. My hue wall switch stopped working (only for the second button) I found that an error occurs when I try to change device_mode (e.g. single_rocker,...