search

TomTomTommi / HiNet

Official PyTorch implementation of "HiNet: Deep Image Hiding by Invertible Network" (ICCV 2021)
166 stars 35 forks source link

Hard to repreduce the performance #6

Closed BZboys closed 2 years ago

BZboys commented 2 years ago

Thanks for your code! But I can not repreduce the performance with the same training settings. The model are prone to degradation during training. Looking forward to your reply!

loss

TomTomTommi commented 2 years ago

Thanks for your interest! During the training process, we sometimes meet the same problems. My solution is to fall back to the latest normal training node, and then decrease the learning rate. (e.g. 10^-4.5 -->10^-5)

Tips: Note that it would be better to set lamda_low_frequency=0 in the pre-trained stage. After the model has converged, then add lamda_low_frequency to fine-tune the network.

TomTomTommi commented 2 years ago

We have updated a training demo for your question in Readme. Hope this helps~