giddyyupp/coco-minitrain

About training settings

kcs6568 opened this issue · 2 comments

Hi. Thank you for the great project!

I'm curious about the training settings for each model epoch, learning rate, etc.

Can I get information about each model? (Faster RCNN, RetinaNet, etc)

Hello,

In order to train the Faster RCNN, MaskRCNN and RetinaNet models we used MMDetection with the default parameter settings. Working with Detectron2 also should be OK. For the training of ExtremeNet, CornerNet and HoughNet we used the official repositories again with the default parameter settings. For some models we have to work with smaller batch sizes. In such cases we followed the linear learning rate rule to scale the learning rate according to batch size.

Great! Thanks for the reply!