syjeon

@achigin hi, have you tested it in TRT 8.4? Sorry if you're still on vacation :)

@WongKinYiu hi, thanks for your explanation but i am still confused about separate feature map >There are two equivalent implementation. > >1. separate it to two convolution > ``` >...

oh, sorry i made mistake. thank you

@robosina hello, thanks for your works applying your code and testing, result is not good. unlike previous training, mAP dose not rise. are you working well?