Closed PistonY closed 5 years ago
You just define it but never use. It's that the reason you results higher than proposed?
maybe it's a mistake
LOL, you implement a pixel level attention by mistake.
@PistonY hey, easy, man, i just mean maybe it's legacy code, after all there is no static check for pytorch code.
HaHa
https://github.com/xiaolai-sqlai/mobilenetv3/blob/5ec8ae3386c3f8268e2d79a61017fc13db051885/mobilenetv3.py#L28