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
