ElonKou

It seems that TX2 doesn't support int8,[int8 calibration support on TX2](https://devtalk.nvidia.com/default/topic/1032623/jetson-tx2/int8-calibration-support-on-tx2/) I also test the yolo3-416(fp16) speed on TX2 ,it's about 211ms,The same config performance is about 14ms per image...

hi,did you solved the question?I'd like to run tiny-yolo3 on my TX2, But I can't find "tinyyolo.caffemodel", can you share the download link for me,thanks you very much.

The small objects disappeared when I changed the classNum and className. But the result still contains overlap. 

Maybe you can try in this issue #39

I create a Chinese interface, which is a genetic algorithm controller. 

OK, I solved this problem by changing the keyboard mapping. Thank you very much! ```bash Config() : SettingsFile("NodeEditor.json") , BeginSaveSession(nullptr) , EndSaveSession(nullptr) , SaveSettings(nullptr) , LoadSettings(nullptr) , SaveNodeSettings(nullptr) , LoadNodeSettings(nullptr)...