Replies: 3 comments
-
@mxnet-label-bot [Question] |
Beta Was this translation helpful? Give feedback.
-
@mxnet-label-bot [NDArray] |
Beta Was this translation helpful? Give feedback.
-
currently upsampling only 4-d tensors is supported - https://github.com/apache/incubator-mxnet/blob/master/src/operator/nn/upsampling.cc#L45. And from the looks of it you are trying to upsample 5-d tensors. Your best bet for now would be to reshape it to a 4-d tensor or take slices of 4-d array and upsample them separately. @mxnet-label-bot remove [Question, NDArray] add [Operator, Feature Request] |
Beta Was this translation helpful? Give feedback.
-
mxnert.ndarray.UpSampling checks if the data is in form: (batch_size, channels, x,y) (that is, number of dimensions=4), however, I want to do UpSampling for volumetric data where the data is of the form: (batch_size,channels,x,y,z).
Is there a way to do this ?
Beta Was this translation helpful? Give feedback.
All reactions