search

apple / ml-cvnets

CVNets: A library for training computer vision networks
https://apple.github.io/ml-cvnets
Other
1.77k stars 225 forks source link

Significance of update_scales() during training #14

Closed mmaaz60 closed 1 year ago

mmaaz60 commented 2 years ago

Hi, Thank you for the great work.

I have a question related to the update_scales() function in VariableBatchSamplerDDP class. I see by default the code is not updating scales during training as self.scale_inc=False. As the code is there I am assuming that you could have tried enabling it. If so, may you provide the ablation results that you got with and without using update_scales() during training? Thank you

sacmehta commented 1 year ago

You can use it to dynamically scale the input resolution during the training. We studied it briefly and found that it helps in improving training efficiency. However, careful selection of scales is required in order to get good accuracy with this setting.