Tried to train a model with unpooling layer, but unpooling backpropagation seems to be not implemented (8308 vision_layers.hpp:686] Not Implemented Yet)

At lines 101-102 of UnpoolingLayer::Reshape

unpooled_height_ = static_cast((height_ - 1) * stride_h_ + kernel_h_ - 2 * pad_h_);
unpooled_width_ = static_cast((width_ - 1) * stride_w_ + kernel_w_ - 2 * pad_w_);

shouldn't these instead read

unpooled_height_ = static_cast((height_ - 1) * stride_h_ + kernel_h_ - 2 * pad_h_) - 1;
unpooled_width_ = static_cast((width_ - 1) * stride_w_ + kernel_w_ - 2 * pad_w_) - 1;

so that they match (in reverse) the lines 90-93 of PoolingLayer::Reshape

pooled_height_ = static_cast(ceil(static_cast(
height_ + 2 * pad_h_ - kernel_h_) / stride_h_)) + 1;
pooled_width_ = static_cast(ceil(static_cast(
width_ + 2 * pad_w_ - kernel_w_) / stride_w_)) + 1;

I may have this wrong, but the unpooled calculations for height and width appear to be missing needed a -1 on each of unpooled height and width calculations.

Good day,
Please, I'm having a problem setting up the caffe, because I get an error from the constrative_loss file, is like their is something wrong with file and how do I fix. thank you and I wait in anticipation for your reply.
Best Regards
Alex Gbenimachor

Below is the Error in the code.

src/caffe/layers/contrastive_loss_layer.cpp: In instantiation of ‘void caffe::ContrastiveLossLayer::Forward_cpu(const std::vector<caffe::Blob>&, const std::vector<caffe::Blob>&) [with Dtype = float]’:
src/caffe/layers/contrastive_loss_layer.cpp:116:1: required from here
src/caffe/layers/contrastive_loss_layer.cpp:54:30: error: no matching function for call to ‘max(float, double)’
Dtype dist = std::max(margin - sqrt(dist_sq_.cpu_data()[i]), 0.0);
~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
In file included from /usr/include/c++/6/algorithm:61:0,
from src/caffe/layers/contrastive_loss_layer.cpp:1:
/usr/include/c++/6/bits/stl_algobase.h:219:5: note: candidate: template constexpr const _Tp& std::max(const _Tp&, const _Tp&)
max(const _Tp& __a, const _Tp& __b)
^~~
/usr/include/c++/6/bits/stl_algobase.h:219:5: note: template argument deduction/substitution failed:
src/caffe/layers/contrastive_loss_layer.cpp:54:30: note: deduced conflicting types for parameter ‘const Tp’ (‘float’ and ‘double’)
Dtype dist = std::max(margin - sqrt(dist_sq.cpu_data()[i]), 0.0);
~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
In file included from /usr/include/c++/6/algorithm:61:0,
from src/caffe/layers/contrastive_loss_layer.cpp:1:
/usr/include/c++/6/bits/stl_algobase.h:265:5: note: candidate: template<class _Tp, class _Compare> constexpr const _Tp& std::max(const _Tp&, const _Tp&, _Compare)
max(const _Tp& __a, const _Tp& __b, _Compare __comp)
^~~
/usr/include/c++/6/bits/stl_algobase.h:265:5: note: template argument deduction/substitution failed:
src/caffe/layers/contrastive_loss_layer.cpp:54:30: note: deduced conflicting types for parameter ‘const Tp’ (‘float’ and ‘double’)
Dtype dist = std::max(margin - sqrt(dist_sq.cpu_data()[i]), 0.0);
~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
In file included from /usr/include/c++/6/algorithm:62:0,
from src/caffe/layers/contrastive_loss_layer.cpp:1:
/usr/include/c++/6/bits/stl_algo.h:3459:5: note: candidate: template constexpr _Tp std::max(std::initializer_list<_Tp>)
max(initializer_list<_Tp> __l)
^~~
/usr/include/c++/6/bits/stl_algo.h:3459:5: note: template argument deduction/substitution failed:
src/caffe/layers/contrastive_loss_layer.cpp:54:30: note: mismatched types ‘std::initializer_list<Tp>’ and ‘float’
Dtype dist = std::max(margin - sqrt(dist_sq.cpu_data()[i]), 0.0);
~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
In file included from /usr/include/c++/6/algorithm:62:0,
from src/caffe/layers/contrastive_loss_layer.cpp:1:
/usr/include/c++/6/bits/stl_algo.h:3465:5: note: candidate: template<class _Tp, class _Compare> constexpr _Tp std::max(std::initializer_list<_Tp>, _Compare)
max(initializer_list<_Tp> __l, _Compare __comp)
^~~
/usr/include/c++/6/bits/stl_algo.h:3465:5: note: template argument deduction/substitution failed:
src/caffe/layers/contrastive_loss_layer.cpp:54:30: note: mismatched types ‘std::initializer_list<Tp>’ and ‘float’
Dtype dist = std::max(margin - sqrt(dist_sq.cpu_data()[i]), 0.0);
~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Makefile:552: recipe for target '.build_release/src/caffe/layers/contrastive_loss_layer.o' failed
make: *** [.build_release/src/caffe/layers/contrastive_loss_layer.o] Error 1

it should be bottom[1]

I have a trained model and I'm trying your pipeline for unspooling and visualizing the layers. Do I need a new train_val.protxt? Do I need to train again with the DeConv layers? I have updated my deploy.prototxt. Can you please help?