search

open-mmlab / mmdetection

OpenMMLab Detection Toolbox and Benchmark
https://mmdetection.readthedocs.io
Apache License 2.0
29.31k stars 9.42k forks source link

Stochastic depth on backbone #7207

Open CanyonWind opened 2 years ago

CanyonWind commented 2 years ago

Hi, I'm wondering if anyone could share some thoughts on whether it is recommended to train the detection/instance segmentation model with stochastic depth on the backbone? E.g. A (224x224, 28M parameters, 4.2G FLOPs) transformer backbone + cascade rcnn, should the backbone part contain stochastic depth when training the detection pipeline?

Thanks a lot!

hhaAndroid commented 2 years ago

@CanyonWind We plan to add this feature in the near future, are you interested in creating a PR?