search

dk-liang / FIDTM

[IEEE TMM] Focal Inverse Distance Transform Maps for Crowd Localization
MIT License
169 stars 41 forks source link

ISSIM-Loss #40

Closed rydenisbak closed 1 year ago

rydenisbak commented 1 year ago

Hello @dk-liang, thank you for the great work.

Can you provide ISSIM Loss validation value for the last epoch for SHA dataset? I can do normalization the loss by several ways, knowledge about your validation value helps me choose the right one. And I will know your loss balance between MSE and ISSIM.

mariosconsta commented 7 months ago

Hey @rydenisbak, how do you handle the huge range of value difference between MSE and SSIM? MSE ranges in the hundreds and SSIM ranges between 0 and 1.

SSIM Loss: 0.96907794 - MSE Loss: 1452.20227051 - Loss: 1453.17138672

So I suspect that the model will try to minimize based on MSE only?