Closed luchaoqi closed 1 year ago
Hi @luchaoqi, playing with the hyper-parameters of the L2 and the lpips as you suggested is the best option in my opinion. Moreover, you might change the convergence criteria in the configuration file as well so the current alexnet would not overfit
Hello,
I find that the option of
lpips_type = 'alex'
tend to affect my inversion results: withlpips_type = 'alex'
, it introduces undesirable checkerboard/noise-like artifact which gives me a sense of overfitting (input left and reconstruction right) withlpips=type='vgg'
, results are smoother which gives me a sense of underfitting: you may need to zoom-in a bit to tell the difference. any suggestions in this case? do I need to tune options likeLPIPS_value_threshold = 0.06
to find a sweet point between this trade-off?