How to understand terms "kNCHW", "NCW", "NCHW", "NCDHW", "kNHWC", "kNCHW", "kNHWC".
Totally, lost.
The capital letter is used to specify the layout of data, which is used in convolution usually:
N: batch size
C: channel
H: height
W: width
so that "NCHW" means a data whose layout is (batch_size, channel, height, width)
and the lower case k
represents a enum class, see: https://github.com/dmlc/mshadow/blob/master/mshadow/base.h#L312
https://github.com/dmlc/mxnet/blob/master/include/mxnet/operator.h#L24
We need to document the behavior of layout.
Why "batch size" is N, and "k" represents "a enum calss" ?
@kernel8liang just custom, which is also common in other librarys
@sxjscience a pinned FAQ issue in github maybe also good
thanks.
Most helpful comment
The capital letter is used to specify the layout of data, which is used in convolution usually:
N: batch size
C: channel
H: height
W: width
so that "NCHW" means a data whose layout is
(batch_size, channel, height, width)
and the lower case
k
represents a enum class, see: https://github.com/dmlc/mshadow/blob/master/mshadow/base.h#L312https://github.com/dmlc/mxnet/blob/master/include/mxnet/operator.h#L24