%VL_NNPOOL?CNN?poolinng.
%???Y?=?VL_NNPOOL（X?POOL）?applies?the?pooling?operator?to?all
%???channels?of?the?data?X?using?a?square?filter?of?size?POOL.?X?is?a
%???SINGLE?array?of?dimension?H?x?W?x?D?x?N?where?（HW）?are?the
%???height?and?width?of?the?map?stack?D?is?the?image?depth?（number
%???of?feature?channels）?and?N?the?number?of?of?images?in?the?stack.
%
%???Y?=?VL_NNPOOL（X?[POOLY?POOLX]）?uses?a?rectangular?filter?of
%???height?POOLY?and?width?POOLX.
%
%???DZDX?=?VL_NNPOOL（X?POOL?DZDY）?computes?the?derivatives?of?the
%???block?projected?onto?DZDY.?DZDX?and?DZDY?have?the?same?dimensions
%???as?X?and?Y?respectively.
%
%???VL_NNCONV（...?‘option‘?value?...）?takes?the?following?options:
%
%???‘Stride‘::?1
%?????The?output?stride?（downsampling?factor）.?It?can?be?either?a
%?????scalar?for?isotropic?downsampling?or?a?vector?[STRIDEY
%?????STRIDEX].
%
%???‘Pad‘::?0
%?????The?amount?of?input?padding.?Input?images?are?padded?with?zeros
%?????by?this?number?of?pixels?on?all?sides?before?the?convolution?is
%?????computed.?It?can?also?be?a?vector?[TOP?BOTTOM?LEFT?RIGHT]?to
%?????specify?a?different?amount?of?padding?in?each?direction.?The
%?????size?of?the?poolin?filter?has?to?exceed?the?padding.
%
%???‘Method‘::?‘max‘
%?????Specify?method?of?pooling.?It?can?be?either?‘max‘?（retain?max?value
%?????over