You are viewing a plain text version of this content. The canonical link for it is here.

Posted to commits@mxnet.apache.org by gi...@git.apache.org on 2017/10/13 03:07:50 UTC

[GitHub] janelu9 commented on issue #8249: why the Validation-accuracy drops so much when I use mx.mod.BucketingModule() to redefine a symbol model?

janelu9 commented on issue #8249: why the Validation-accuracy drops so much when I use  mx.mod.BucketingModule() to redefine a symbol model?
URL: https://github.com/apache/incubator-mxnet/issues/8249#issuecomment-336337754
 
 
   it looks that the training con't be convergent  after I use:
   `    model=   mx.mod.BucketingModule(
           sym_gen             = sym_gen,
           default_bucket_key  = data_train.default_bucket_key,
           context             = [mx.gpu(int(i)) for i in range(1)])`
 
----------------------------------------------------------------
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