Caffe Installation failed

[vinson2233]

I've struggled with Caffe installation for several days. It gives me a headache with fixing one error and then moves to the next error. Can I ask for :

• Python Version
• CUDA Version
• CUDNN Version
• NCCL Version
• OS Version
  That you guys use?

I'm using Ubuntu 16.04 inside GCP
This is information I got from cMake :

-- Boost version: 1.58.0
-- Found the following Boost libraries:
--   system
--   thread
--   filesystem
--   chrono
--   date_time
--   atomic
-- Found gflags  (include: /usr/include, library: /usr/lib/x86_64-linux-gnu/libgflags.so)
-- Found glog    (include: /usr/include, library: /usr/lib/x86_64-linux-gnu/libglog.so)
-- Found PROTOBUF Compiler: /usr/bin/protoc
-- Found lmdb    (include: /usr/include, library: /usr/lib/x86_64-linux-gnu/liblmdb.so)
-- Found LevelDB (include: /usr/include, library: /usr/lib/x86_64-linux-gnu/libleveldb.so)
-- Found Snappy  (include: /usr/include, library: /usr/lib/x86_64-linux-gnu/libsnappy.so)
-- CUDA detected: 7.5
-- Found cuDNN: ver. 8.1.1 found (include: /usr/include, library: /usr/lib/x86_64-linux-gnu/libcudnn.so)
-- Added CUDA NVCC flags for: sm_37
-- OpenCV found (/usr/share/OpenCV)
-- Found Atlas (include: /usr/include, library: /usr/lib/libatlas.so)
-- NumPy ver. 1.11.0 found (include: /usr/lib/python2.7/dist-packages/numpy/core/include)
-- Boost version: 1.58.0
-- Found the following Boost libraries:
--   python
-- Could NOT find Doxygen (missing:  DOXYGEN_EXECUTABLE) 
-- 
-- ******************* Caffe Configuration Summary *******************
-- General:
--   Version           :   1.0.0-rc3
--   Git               :   514e561-dirty
--   System            :   Linux
--   C++ compiler      :   /usr/bin/c++
--   Release CXX flags :   -O3 -DNDEBUG -fPIC -Wall -Wno-sign-compare -Wno-uninitialized
--   Debug CXX flags   :   -g -fPIC -Wall -Wno-sign-compare -Wno-uninitialized
--   Build type        :   Release
-- 
--   BUILD_SHARED_LIBS :   ON
--   BUILD_python      :   ON
--   BUILD_matlab      :   OFF
--   BUILD_docs        :   ON
--   CPU_ONLY          :   OFF
--   USE_OPENCV        :   ON
--   USE_LEVELDB       :   ON
--   USE_LMDB          :   ON
--   USE_NCCL          :   OFF
--   ALLOW_LMDB_NOLOCK :   OFF
-- 
-- Dependencies:
--   BLAS              :   Yes (Atlas)
--   Boost             :   Yes (ver. 1.58)
--   glog              :   Yes
--   gflags            :   Yes
--   protobuf          :   Yes (ver. 2.6.1)
--   lmdb              :   Yes (ver. 0.9.17)
--   LevelDB           :   Yes (ver. 1.18)
--   Snappy            :   Yes (ver. 1.1.3)
--   OpenCV            :   Yes (ver. 2.4.9.1)
--   CUDA              :   Yes (ver. 7.5)
-- 
-- NVIDIA CUDA:
--   Target GPU(s)     :   Auto
--   GPU arch(s)       :   sm_37
--   cuDNN             :   Yes (ver. 8.1.1)
-- 
-- Python:
--   Interpreter       :   /usr/bin/python2.7 (ver. 2.7.12)
--   Libraries         :   /usr/lib/x86_64-linux-gnu/libpython2.7.so (ver 2.7.12)
--   NumPy             :   /usr/lib/python2.7/dist-packages/numpy/core/include (ver 1.11.0)
-- 
-- Documentaion:
--   Doxygen           :   No
--   config_file       :   
-- 
-- Install:
--   Install path      :   /home/vinson.ciawandy/bottom-up-attention/caffe/build/install
-- 
-- Configuring done
-- Generating done
-- Build files have been written to: /home/vinson.ciawandy/bottom-up-attention/caffe/build

This is my last error where I'm giving up the installation:

make all
[  1%] Running C++/Python protocol buffer compiler on /home/vinson.ciawandy/bottom-up-attention/caffe/src/caffe/proto/caffe.proto
Scanning dependencies of target proto
[  1%] Building CXX object src/caffe/CMakeFiles/proto.dir/__/__/include/caffe/proto/caffe.pb.cc.o
[  1%] Linking CXX static library ../../lib/libproto.a
[  1%] Built target proto
[  1%] Building NVCC (Device) object src/caffe/CMakeFiles/cuda_compile.dir/layers/cuda_compile_generated_power_layer.cu.o
In file included from /home/vinson.ciawandy/bottom-up-attention/caffe/include/caffe/util/device_alternate.hpp:40:0,
                 from /home/vinson.ciawandy/bottom-up-attention/caffe/include/caffe/common.hpp:19,
                 from /home/vinson.ciawandy/bottom-up-attention/caffe/include/caffe/blob.hpp:8,
                 from /home/vinson.ciawandy/bottom-up-attention/caffe/include/caffe/layers/power_layer.hpp:6,
                 from /home/vinson.ciawandy/bottom-up-attention/caffe/src/caffe/layers/power_layer.cu:3:
/home/vinson.ciawandy/bottom-up-attention/caffe/include/caffe/util/cudnn.hpp:169:2: error: #endif without #if
 #endif  // CAFFE_UTIL_CUDNN_H_
  ^
CMake Error at cuda_compile_generated_power_layer.cu.o.cmake:207 (message):
  Error generating
  /home/vinson.ciawandy/bottom-up-attention/caffe/build/src/caffe/CMakeFiles/cuda_compile.dir/layers/./cuda_compile_generated_power_layer.cu.o


src/caffe/CMakeFiles/caffe.dir/build.make:525: recipe for target 'src/caffe/CMakeFiles/cuda_compile.dir/layers/cuda_compile_generated_power_layer.cu.o' failed
make[2]: *** [src/caffe/CMakeFiles/cuda_compile.dir/layers/cuda_compile_generated_power_layer.cu.o] Error 1
CMakeFiles/Makefile2:272: recipe for target 'src/caffe/CMakeFiles/caffe.dir/all' failed
make[1]: *** [src/caffe/CMakeFiles/caffe.dir/all] Error 2
Makefile:127: recipe for target 'all' failed
make: *** [all] Error 2

Or can I just ditch the Caffe inside this repo and just use the official one?
Thanks

[SnoopyMark]

Try docker: https://hub.docker.com/r/airsplay/bottom-up-attention

[vinson2233]

@SnoopyMark I have used the code from airsplay, it indeed easy to use, but cannot use for training new images.

[vinson2233]

Here's my step on how I successfully install the caffe inside this repo (March 2021). I use GCP VM with ubuntu 16.04

1. sudo apt update
2. sudo apt-get install git
3. sudo apt-get install software-properties-common
4. sudo apt-get wget
5. sudo apt-get install build-essential
6. wget https://developer.nvidia.com/compute/cuda/9.2/Prod2/local_installers/cuda_9.2.148_396.37_linux
7. sudo sh cuda_9.2.148_396.37_linux.run, leave the default, if no default just choose yes
8. Please make sure that
 - PATH includes /usr/local/cuda-9.2/bin
 - LD_LIBRARY_PATH includes /usr/local/cuda-9.2/lib64, or, add /usr/local/cuda-9.2/lib64 to /etc/ld.so.conf and run ldconfig as root

To uninstall the CUDA Toolkit, run the uninstall script in /usr/local/cuda-9.2/bin
To uninstall the NVIDIA Driver, run nvidia-uninstall
9. Install cudnn both developer and runtime version v7.1.4 https://developer.nvidia.com/rdp/cudnn-archive
10. git clone https://github.com/NVIDIA/nccl, follow their instruction to build, and then install
11. Follow https://atinesh.medium.com/caffe-installation-on-ubuntu-18-04-lts-python-2-7-8e8c388ce51f for dependencies installation
12. pip install easydict and pip install Cython
13. git clone https://github.com/peteanderson80/bottom-up-attention
14. follow step-3 until before make and use caffe inside peteanderson bottom up .https://atinesh.medium.com/caffe-installation-on-ubuntu-18-04-lts-python-2-7-8e8c388ce51f , but don’t uncomment the open cv version line since we use opencv2
15. update cudnn.hpp inside peteanderson’s caffe, see details : warning message when compile BVLC/caffe#6381
16. make all, make test and then make runtest inside caffe
17. sudo apt-get install python-skimage
18. final-step :), add this environment variable inside .bashrc
export PYTHONPATH=/home/username/caffe/python

Caffe should be successfully imported at this step.Now we need to install jupyter without anaconda and only using python2.

1. Update pip with wget https://bootstrap.pypa.io/pip/2.7/get-pip.py and then use python2 to run the downloaded script