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 2017/10/30 14:36:02 UTC
[GitHub] chenbiaolong opened a new issue #8474: How to train invariable input shape CNN?
chenbiaolong opened a new issue #8474: How to train invariable input shape CNN?
URL: https://github.com/apache/incubator-mxnet/issues/8474
I define a CNN network that can process invariable input images, but can't find an example to learn how to train it. All I found is a `MutableModule` find in `example/rcnn`,it rebind the module when the shape changed.But after I implement the DataIter of my dataset, it seems that it failed to update the params, the accuracy didn't increase after several epochs. Any one can give an example?
----------------------------------------------------------------
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