unable to open caffe_rcnn_imagenet_model or rcnn_imagenet_deploy.prototxt

If you are getting the above errors you need to change the arguments to

--pretrained_model=../examples/imagenet/caffe_rcnn_imagenet_model
--model_def=../examples/imagenet/rcnn_imagenet_deploy.prototxt

./include/caffe/data_layers.hpp:11:18: fatal error: lmdb.h: No such file or directory compilation terminated.

If you get this error when you run make all for caffe. It is possible that you are missing dependencies. To install missing lmdb dependencies 

git clone git://gitorious.org/mdb/mdb.git
cd mdb/libraries/liblmdb
make
sudo make install

./include/caffe/common.hpp:5:27: fatal error: gflags/gflags.h: No such file or directory

If you get this error when you run make all for caffe. It is possible that you are missing dependencies. To install missing gflag dependencies 

wget https://github.com/schuhschuh/gflags/archive/master.zip
unzip master.zip
cd gflags-master
mkdir build && cd build
export CXXFLAGS="-fPIC" && cmake .. && make VERBOSE=1
make 
sudo make install

squeeze() takes no keyword arguments on caffe

If you get this error when you run any of the python modules in caffe. It is possible that you have an older version of numpy. You just need to upgrade to the latest version. You can do

sudo pip install -U numpy


Good luck

mkl_vsl.h: No such file or directory with caffe

I encounter this problem when trying to compile the implementation of NIN on the caffe branch cccp-dev.

To fix the error I had to include a MKL_DIR variable in the Makefile.config file and set it to

MKL_DIR := /opt/intel/mkl

I also included the mkl directory on my LD_LIBRARY_PATH but that didn't seem to help.

After doing that it compiled the code

invalid device function cudaGetLastError() on cuda-convnet dropout

When installing the library from this library :

https://github.com/dnouri/cuda-convnet

I came across this error :

invalid device function cudaGetLastError()

 All I had to do was to comment this line in the CMakeLists.txt file

#list(APPEND CUDA_NVCC_FLAGS -gencode arch=compute_30,code=sm_30)

and uncomment this line

 list(APPEND CUDA_NVCC_FLAGS -gencode arch=compute_20,code=sm_20)


The problem as described by this post

https://forums.udacity.com/questions/100015837/invalid-device-function-cudagetlasterror#cs344

is that the the device requirement is higher than what it is specified

It Was Mom: A Mother's Day Tribute To Moms #itwasmom