search

yuyi-sd / Robust_Rain_Removal

33 stars 5 forks source link

Training parameters #5

Open raindrop313 opened 1 year ago

raindrop313 commented 1 year ago

Hi, how did you set the λ in the adversarial loss during training

yuyi-sd commented 1 year ago

Hi raindrop,

Because large λ will compromise the performance for input without perturbations, we adjust the weight to make the final clean performance around 28.0(±0.2) for Rain100H and 28.5(±0.2) for RainCityscape in terms of PSNR.

For your reference, we set it around 0.15 for RainCityscape and Rain100H in the experiment for our proposed model.