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
To make the model structure more controllable, I decided to abandon the way of loading model with a yaml config files as Ultralytics and refactor the darknet backbone as separate modules.
Especially, the parse_model() as below containing the DarkNet, BackboneWithPAN, and PathAggregationNetwork modules, so first I will make this modules more visible and clear.
🚀 Feature
Refactor darknet backbone as separate modules
Motivation
To make the model structure more controllable, I decided to abandon the way of loading model with a
yaml
config files as Ultralytics and refactor thedarknet
backbone as separate modules.Especially, the
parse_model()
as below containing theDarkNet
,BackboneWithPAN
, andPathAggregationNetwork
modules, so first I will make this modules more visible and clear.https://github.com/zhiqwang/yolov5-rt-stack/blob/9104887c4cf10061585eb5b8982270790437013d/models/backbone.py#L79
Then, this modifications would change the keys of checkpoint in
state_dict
, it's also necessary to revise the checkpiont update scripts.Pitch
DarkNet
BackboneWithPAN
PathAggregationNetwork
Alternatives
I found several works on this, like:
Additional context
Also follow the philosophy of
torchvision
especially for:fpn
BackboneWithFPN
mobilenet_v2
mobilenet_v3
The text was updated successfully, but these errors were encountered: