You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@mxnet.apache.org by GitBox <gi...@apache.org> on 2018/09/10 21:39:28 UTC

[GitHub] zhreshold commented on issue #12334: Load pretrained model with new load_parameters() API

zhreshold commented on issue #12334: Load pretrained model with new load_parameters() API
URL: https://github.com/apache/incubator-mxnet/issues/12334#issuecomment-420070337
 
 
   After transition from `save_params` to `save_parameters` it is no longer enforcing prefix check, and it's really error prone if we are going to load partial weights from different models.  
   So `save_parameters` and `load_parameters` are seriously only for serialization IMO. 
   
   As suggested by @L1aoXingyu I think it's safer to copy loaded parameters between each other, at least you will know what parameters are indeed copied. 
   
   Let me know what's your concern if directly loading partial weights is not applicable. @ShownX 

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services