Fine Tuning the model - Githubissues

csjliang / LPTN

Official implementation of the paper 'High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Network' in CVPR 2021

Apache License 2.0

411 stars 46 forks source link

Fine Tuning the model #26

Closed AhmedHashish123 closed 3 years ago

AhmedHashish123 commented 3 years ago

If I want to fine tune the model, do I only have to change train_FiveK.yml? I should open this options file and go to "path" then pretrain_network_g: and set the path of the pretrained model correct? This should load in the pretrained weights and continue updating these weights right?

csjliang commented 3 years ago

Hi, Sure, you only need to specify the path of the pretrained model in the yml file. Thanks.

AhmedHashish123 commented 3 years ago

@csjliang thank you for the fast reply.