ericvlognow commented on issue #10067: keras imdb data set is not converged  
when maximum size of the word sequence is 500
   i found the issue.  the pre-padding instead of post-padding solved the 
   dyld: warning, LC_RPATH ${ORIGIN} in 
/Library/Python/2.7/site-packages/mxnet/ being ignored in restricted 
program because it is a relative path
   Preparing train set...
   Preparing test set...
   Trimming to 5000 max-features
   Padding to length 500
   Epoch 0, Training ('accuracy', 0.7589114450127877)
   Epoch 1, Training ('accuracy', 0.8890664961636828)
   Epoch 2, Training ('accuracy', 0.9126838235294118)
   Epoch 3, Training ('accuracy', 0.9197969948849105)
   ('Accuracy: ', 0.81308)

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:

With regards,
Apache Git Services

Reply via email to