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 2019/07/25 15:40:01 UTC

[GitHub] [incubator-mxnet] kshitij12345 edited a comment on issue #15656: Can you give me a UpSampling's doc? 'bilinear'!!

kshitij12345 edited a comment on issue #15656: Can you give me a UpSampling's doc?  'bilinear'!!
URL: https://github.com/apache/incubator-mxnet/issues/15656#issuecomment-515095374
 
 
   The documentation seems to be incomplete.
   https://mxnet.incubator.apache.org/api/python/ndarray/ndarray.html#mxnet.ndarray.UpSampling
   
   It doesn't mention about weight when using `bilinear`.
   Digging into the code,
   https://github.com/apache/incubator-mxnet/blob/8158ba4b0f1ebd696ec09a0b1aa6031bacb60740/src/operator/nn/upsampling.cc#L123-L173
   
   It mentions about requiring the weight and also gives an example.
   I have verified that the example works,
   ```
   from mxnet import nd
   x = nd.ones((1,3,3,3)) # NCHW
   w = nd.ones((3,1,4,4))
   upsampled = nd.UpSampling(x, w, scale=2, sample_type='bilinear', num_filter=3)
   ```

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to 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