[GitHub] janejane11 opened a new issue #8768: how to use mx.io.extract()

[GitBox <gi...@apache.org>]

janejane11 opened a new issue #8768:  how to use mx.io.extract()
URL: https://github.com/apache/incubator-mxnet/issues/8768
 
 
   that's my problem: how to use mx.io.extract()
   in the begining,i use mx.io.ImageRecordIter to read my data(7 label) in cnn model (below)
   
   train = mx.io.ImageRecordIter(
   path.imglist=path1,
   path.imgrec=path2,
   batch.size=4,
   round.batch=TRUE,
   data.shape=c(50,50,1),
   preprocess.threads=1
   )
   test = mx.io.ImageRecordIter(
   path.imglist=path3,
   path.imgrec=path4,
   batch.size=4,
   data.shape=c(50,50,1),
   round.batch=FALSE,
   preprocess.threads=1
   
   after many times training..
   finally,i want to show the table about the test result
   so i write
   
   preds<-predict(model,test)
   pred.label<-max.col(t(preds))-1
   cm=confusionMatrix(pred.label,mx.io.extract)
   t(cm$table)
   
   there are always some fault on mx.io.extract
   i think it may need some parameter,but i have no idea
   

----------------------------------------------------------------
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