sandeep-krishnamurthy commented on issue #12970: Bilinear UpSampling is broken
URL: 
https://github.com/apache/incubator-mxnet/issues/12970#issuecomment-490606970
 
 
   Bilinear upsampling required kernel to be passed as input because it use 
deconvolution under the hood. Clarified the expectation in API documentation.
   ```python
    >>> x = nd.ones((1,1,3,3))
     >>> x
     [[[[1. 1. 1.]
        [1. 1. 1.]
        [1. 1. 1.]]]]
     <NDArray 1x1x3x3 @cpu(0)>
     >>> w = nd.ones((1,1,4,4))
     >>> w
     [[[[1. 1. 1. 1.]
        [1. 1. 1. 1.]
        [1. 1. 1. 1.]
        [1. 1. 1. 1.]]]]
     <NDArray 1x1x4x4 @cpu(0)>
     >>> nd.UpSampling(x, w, scale=2, sample_type='bilinear', num_filter=1)
     [[[[1. 2. 2. 2. 2. 1.]
        [2. 4. 4. 4. 4. 2.]
        [2. 4. 4. 4. 4. 2.]
        [2. 4. 4. 4. 4. 2.]
        [2. 4. 4. 4. 4. 2.]
        [1. 2. 2. 2. 2. 1.]]]]
     <NDArray 1x1x6x6 @cpu(0)>
   ```

----------------------------------------------------------------
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:
[email protected]


With regards,
Apache Git Services

Reply via email to