RobotEdh / Yolov-4

Yolo v4 using TensorFlow 2.x
110 stars 30 forks source link

Wrong ! Shortcut layer in CSPdarknet-53 #6

Open NguyenThaiHoc1 opened 3 years ago

NguyenThaiHoc1 commented 3 years ago

Hi Author

I had read your code but i realize shortcut layer don't have performs in your code I read common config of author who create at https://github.com/AlexeyAB/darknet/blob/master/cfg/yolov4.cfg

and shortcut layer is a layer Adding previous layer with layers specified in from= parameter

you can see https://github.com/AlexeyAB/darknet/wiki/CFG-Parameters-in-the-different-layers

That so Sorry if I have wrong but i confuse when i read your code although is perfect Thai Hoc

RobotEdh commented 3 years ago

Hello Thai Hoc,

Sorry for my late answer.

Shortcut are managed with the boolean skip as parameter of the function _conv_block if skip is true, then this function generates an add of the last layer and the layer -3. this is equivalent to

[shortcut] from=-3 activation=linear

Hope it is clear.

thanks for reading my code

Eric