Why does the calculation of loss need to be multiplied by a coefficient of 0.5? Is it because fine and coat account for half respectively?
ret['c_l'] = 0.5 * ((inputs['rgb_coarse']-targets)*2).mean()
ret['f_l'] = 0.5 ((inputs['rgb_coarse']-targets)**2).mean()
Why does the calculation of loss need to be multiplied by a coefficient of 0.5? Is it because fine and coat account for half respectively? ret['c_l'] = 0.5 * ((inputs['rgb_coarse']-targets)*2).mean() ret['f_l'] = 0.5 ((inputs['rgb_coarse']-targets)**2).mean()