[GitHub] KnightOfTheMoonlight commented on issue #5540: BatchNorm is not support for 3D? only support 2D?

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

KnightOfTheMoonlight commented on issue #5540: BatchNorm is not support for 3D? only support 2D?
URL: https://github.com/apache/incubator-mxnet/issues/5540#issuecomment-352912276
 
 
   Hi,3d bn is suported at least in mxnet version 0.12.0
   Here is the example code:
   ```
   import mxnet as mx
   print(mx.__version__)
   data = mx.nd.arange(1029).reshape((3,1,7,7,7)) # NCDHW
   data_shape=(3,1,7,7,7)
   x = mx.sym.Variable('data')
   conv3D = mx.sym.Convolution(data=x, kernel=(3, 3, 3), pad=(2, 2, 2), num_filter=2)
   conv3D_bn = mx.sym.BatchNorm(data=conv3D)
   conv3D_exe = conv3D.simple_bind(mx.gpu(),data=data.shape)
   ```
   

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