Hey, seems like ref_img_features remain uninitialized, featuresweight inited twice instead.
PS: If corrected - the first iteration yelds zero vgg loss, but that might be because I messed something else (trying to use facenet instead of vgg). but might be not **
https://github.com/pbaylies/stylegan-encoder/blob/18919c2565e3947eafc152e320ba573b3e61ad08/encoder/perceptual_model.py#L125
Hey, seems like ref_img_features remain uninitialized, featuresweight inited twice instead. PS: If corrected - the first iteration yelds zero vgg loss, but that might be because I messed something else (trying to use facenet instead of vgg). but might be not **