Everything is Diningtable

[RunOrVeith]

Hi,

I've compiled the net with Cuda 7.0 and and Cudnn 4.
This compiles, but every image that it segments is labeled "dining table", for every pixel.
Using Cudnn 5, like you recommended, it does not compile with the following error message:

    make -j1
PROTOC src/caffe/proto/caffe.proto
CXX .build_release/src/caffe/proto/caffe.pb.cc
CXX src/caffe/internal_thread.cpp
In file included from ./include/caffe/util/device_alternate.hpp:40:0,
                from ./include/caffe/common.hpp:19,
                from ./include/caffe/internal_thread.hpp:4,
                from src/caffe/internal_thread.cpp:4:
./include/caffe/util/cudnn.hpp: In function ‘void caffe::cudnn::createPoolingDesc(cudnnPoolingStruct**, caffe::PoolingParameter_PoolMethod, cudnnPoolingMode_t*, int, int, int, int, int, int)’:
./include/caffe/util/cudnn.hpp:126:3: error: too few arguments to function ‘cudnnStatus_t cudnnSetPooling2dDescriptor(cudnnPoolingDescriptor_t, cudnnPoolingMode_t, cudnnNanPropagation_t, int, int, int, int, int, int)’
In file included from ./include/caffe/util/cudnn.hpp:5:0,
                from ./include/caffe/util/device_alternate.hpp:40,
                from ./include/caffe/common.hpp:19,
                from ./include/caffe/internal_thread.hpp:4,
                from src/caffe/internal_thread.cpp:4:
/usr/local/cuda/include/cudnn.h:799:27: note: declared here
make: *** [.build_release/src/caffe/internal_thread.o] Error 1

It works fine if I compile without Cudnn, then everything is segmented fine.
Any idea why this mad bug may be? I've been trying to find out for a week now, without success.

Greetings,
Veith

[lbwang2006]

I have the similar problems, It works fine if I compile without Cudnn, but it fails to train with cudnn4.0+cuda8.0 without compiling error. You have solved it?@RunOrVeith

[kardoszc]

these cudnn_layers based on cudnn4.0, if you want to use cudnn5.0, (especially when you train your model with new gpu like ttx or 1080 which cudnn4.0 didn't work well), you need to replace these cudnn_layers with latest caffe layers.

cp new_caffe/include/caffe/util/cudnn.hpp ./include/caffe/util/cudnn.hpp 
cp new_caffe/include/caffe/layers/cudnn_* ./include/caffe/layers/ 
cp new_caffe/src/caffe/layers/cudnn_* ./src/caffe/layers/

you can try these, hope these will help you