You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I am planning to use yolov4-tiny for an embedded device (rockchip rk3399pro) but groups and group_id are not supported parameters for model conversion toolkit. If i understood correctly, route layer slices the input feature map into 2 parts (groups = 2) and forwards the second part (group_id = 1) to the next convolutional layer. It seems that replacing route layers (not concatenating ones) with 1x1 convolution layers are supposed to work. However, training fails and loss becomes nan after a while with modified cfg with yolov4-tiny.conv.29.
Original code piece
Route layer replaced with 1x1 convolution
My questions
Is it ok to replace some route layers with 1x1 convolutions ?
Should i retrain yolov4-tiny backbone with imagenet from scratch first ? If yes, how ?
What are the alternative backbones for yolov4-tiny without having groups params ?
The text was updated successfully, but these errors were encountered:
I am planning to use yolov4-tiny for an embedded device (rockchip rk3399pro) but
groups
andgroup_id
are not supported parameters for model conversion toolkit. If i understood correctly,route
layer slices the input feature map into 2 parts (groups = 2) and forwards the second part (group_id = 1) to the next convolutional layer. It seems that replacingroute
layers (not concatenating ones) with1x1
convolution layers are supposed to work. However, training fails and loss becomes nan after a while with modified cfg withyolov4-tiny.conv.29.
Original code piece
Route layer replaced with 1x1 convolution
My questions
The text was updated successfully, but these errors were encountered: