Why the value of weight map is set to all 2?

Elin24 / PSPL

The implementation of ICASSP 2020 paper "Pixel-level self-paced learning for super-resolution"

40 stars 13 forks source link

Open JustinAsdz opened 3 years ago

JustinAsdz commented 3 years ago

I can't figure it out why all values will converge to 2 ( the hyper-parameter γ).

Elin24 commented 3 years ago

Do you mean using different γ like 1, 2, 4, 8? or all the value will be 2 at the end of the training process?