gidariss / locnet Goto Github PK

LocNet: Improving Localization Accuracy for Object Detection

License: Other

MATLAB 97.32% Cuda 1.66% C++ 1.02%

locnet's Introduction

LocNet: Improving Localization Accuracy for Object Detection

Introduction

This code implements the following CVPR 2016 paper (accepted for oral presentation):
Title: "LocNet: Improving Localization Accuracy for Object Detection"
Authors: Spyros Gidaris, Nikos Komodakis
Institution: Universite Paris Est, Ecole des Ponts ParisTech
ArXiv Link: http://arxiv.org/abs/1511.07763
Code: https://github.com/gidariss/LocNet

Abstract:
"We propose a novel object localization methodology with the purpose of boosting the localization accuracy of state-of-the-art object detection systems. Our model, given a search region, aims at returning the bounding box of an object of interest inside this region. To accomplish its goal, it relies on assigning conditional probabilities to each row and column of this region, where these probabilities provide useful information regarding the location of the boundaries of the object inside the search region and allow the accurate inference of the object bounding box under a simple probabilistic framework.
For implementing our localization model, we make use of a convolutional neural network architecture that is properly adapted for this task, called LocNet. We show experimentally that LocNet achieves a very significant improvement on the mAP for high IoU thresholds on PASCAL VOC2007 test set and that it can be very easily coupled with recent state-of-the-art object detection systems, helping them to boost their performance. Finally, we demonstrate that our detection approach can achieve high detection accuracy even when it is given as input a set of sliding windows, thus proving that it is independent of region proposal methods."

Citing LocNet

If you find LocNet useful in your research, please consider citing:

@inproceedings{gidaris2016locnet,
title={LocNet: Improving Localization Accuracy for Object Detection},
author={Gidaris, Spyros and Komodakis, Nikos},
booktitle={Computer Vision and Pattern Recognition (CVPR), 2016 IEEE Conference on},
year={2016}
}

License

This code is released under the MIT License (refer to the LICENSE file for details).

Requirements

Hardware:
For training the LocNet models or testing the LocNet object detection pipeline you will require a GPU with at least 6 Gbytes of memory.

Software:

Modified version of Caffe developed to supprot LocNet and installed with the cuDNN library [link].
MATLAB (tested with R2014b)

Optional:
The following packages are necessary for using the EdgeBox or Selective Search bounding box proposas algorithms:

Edge Boxes code [link].
The image processing MATLAB toolbox of Piotr Dollar (used for the Edge Boxes) [link].
Selective search code [link].

Note: we provide the bounding box proposals of PASCAL images and hence installing the above packages is not necessary for training or testing models on this dataset. However, they are necessary for running the demo code on images other than the one that is provided by us.

Installation (sufficient for the demo)

Download and install this modified version of Caffe developed to supprot LocNet. To clone Caffe on your local machine:

# $caffe_LocNet: directory where Caffe will be cloned  
git clone https://github.com/gidariss/caffe_LocNet $caffe_LocNet

$caffe_LocNet is the directory where Caffe is cloned. After cloning Caffe follow the installation instructions here. Note that you have to install Caffe with the cuDNN library.
2. Clone the LocNet code in your local machine: ```Shell

# $LocNet: directory where LocNet will be cloned  
git clone https://github.com/gidariss/LocNet $LocNet
```

From now on, the directory where LocNet was cloned will be called $LocNet.
3. Create a symbolic link of Caffe installatation directory at $LocNet/external/:
```Shell

# $LocNet: directory where LocNet was cloned    
# $caffe_LoNet: directory where caffe was cloned    
ln -sf $caffe_LoNet $LocNet/external/caffe_LocNet    
```

open matlab from the $LocNet/ directory:
```
cd $LocNet  
matlab  
```

Run the LocNet_build.m script on matlab command line

# matlab command line enviroment
>> LocNet_build

Do not worry about the warning messages. They also appear on my machine.

Download and use the pre-trained models

Download the tar.gz files with the pre-trained models:
Recognition models:

Reduced MR-CNN recognition model.
Fast RCNN recognition model (re-implemented by us).
Localization models:
LocNet In-Out model.
LocNet Borders model.
LocNet Combined model.
CNN-based bounding box regression model.

Untar and unzip all of the above files on the following locations:

# Recognition models:
$LocNet/models-exps/VGG16_Reduced_MRCNN # Reduced MR-CNN recognition model
$LocNet/models-exps/VGG16_FastRCNN # Fast RCNN recognition model
# VOC2012 structure:
$LocNet/models-exps/VGG16_LocNet_InOut # LocNet In-Out model
$LocNet/models-exps/VGG16_LocNet_Borders # LocNet Borders model
$LocNet/models-exps/VGG16_LocNet_Combined # LocNet Combined model
$LocNet/models-exps/VGG16_BBoxReg # CNN-based bounding box regression model

All of the above models are based on the VGG16-Net and are trained on the union of VOC2007 train+val plus VOC2012 train+val datasets. Note that they are not the same as those used to report result in the paper and hense their performance is slightly different from them (around 0.2 mAP points difference more or less in the percentage scale).

Demo

After having complete the basic installation, you will be able to run the demo of object detection based on the LocNet localization models. In order to do that, open the matlab from $LocNet/ directory and then run the script 'demo_LocNet_object_detection_pipeline' from the matlab command line enviroment:

cd $LocNet
matlab
# matlab command line enviroment
>> demo_LocNet_object_detection_pipeline

Note: you will require a GPU with at least 6 Gbytes of memory in order to run the demo.

In order to play with the parameters of the object detection pipeline read and edit the demo script:

# matlab command line enviroment
>> edit demo_LocNet_object_detection_pipeline.m

Installing and using the box proposals algorithms (Optional)

First install 1) Edge Boxes, 2) Dollar's image processing MATLAB toolbox (used in Edge Boxes), and 3) Selective Search. Then, create symbolic links of the installation directories at $LocNet/external/:

# $edges: installation directory of Edge Boxes     
ln -sf $edges $LocNet/external/edges   
# $pdollar-toolbox: installation directory of Dollar's image processing MATLAB toolbox  
ln -sf $pdollar-toolbox $LocNet/external/pdollar-toolbox  
# $selective_search: installation directory of selective search code  
ln -sf $selective_search $LocNet/external/selective_search

The above packages are necessary in case you want to try the demo on an image of your choise.

Downloading and preparing the PASCAL VOC2007 and VOC2012 datasets

In order to run experiments (e.g. train or test models) on PASCAL VOC datasets you will need to download and prepare the corresponding data. For that purpose you will have to:

Download the VOC datasets and VOCdevkit:

# VOC2007 DATASET
 wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtrainval_06-Nov-2007.tar # VOC2007 train+val set
 wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtest_06-Nov-2007.tar # VOC2007 test set
 wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCdevkit_08-Jun-2007.tar # VOC2007 devkit
 # VOC2012 DATASET
 wget http://host.robots.ox.ac.uk/pascal/VOC/voc2012/VOCtrainval_11-May-2012.tar # VOC2012 train+val set
 wget http://host.robots.ox.ac.uk/pascal/VOC/voc2012/VOCdevkit_18-May-2011.tar  # VOC2012 devkit

Untar the VOC2007 tar files in a directory named $datasets/VOC2007/VOCdevkit and the VOC2012 tar files in a directory named $datasets/VOC2012/VOCdevkit:

mkdir $dataset
# VOC2007 data:
 mkdir $datasets/VOC2007
 mkdir $datasets/VOC2007/VOCdevkit
 tar xvf VOCtrainval_06-Nov-2007.tar  -C $datasets/VOC2007/VOCdevkit
 tar xvf VOCtest_06-Nov-2007.tar -C $datasets/VOC2007/VOCdevkit
 tar xvf VOCdevkit_08-Jun-2007.tar -C $datasets/VOC2007/VOCdevkit
# VOC2012 data:
 mkdir $datasets/VOC2012
 mkdir $datasets/VOC2012/VOCdevkit
 tar xvf VOCtrainval_11-May-2012.tar -C $datasets/VOC2012/VOCdevkit
 tar xvf VOCdevkit_18-May-2011.tar -C $datasets/VOC2012/VOCdevkit

They should have the following structure:

# VOC2007 structure:
$datasets/VOC2007/VOCdevkit/ # VOC2007 development kit
$datasets/VOC2007/VOCdevkit/VOCcode/ # VOC2007 development kit code
$datasets/VOC2007/VOCdevkit/VOC2007/ # VOC2007 images, annotations, etc 
# VOC2012 structure:
$datasets/VOC2012/VOCdevkit/ # VOC2012 development kit
$datasets/VOC2012/VOCdevkit/VOCcode/ # VOC2012 development kit code
$datasets/VOC2012/VOCdevkit/VOC2012/ # VOC2012 images, annotations, etc

Create symlink of the $datasets directory at $LocNet/datasets:
```
ln -sf $datasets $LocNet/datasets  
```
Download the pre-computed Edge Box and Selective Search proposals of PASCAL images (click the links) and place them on the following locations:
```
 $LocNet/data/edge_boxes_data # Edge Box proposals  
 $LocNet/data/selective_search_data # Selective Search proposals  
```

Testing the (pre-)trained models on VOC2007 test set

To test the object detection pipeline with the (pre-)trained models on VOC2007 test do:

# 1) open matlab from $LocNet directory
cd $LocNet
matlab
# 2) run in the matlab command line enviroment
>> script_test_object_detection_pipeline_PASCAL('VGG16_Reduced_MRCNN','VGG16_LocNet_InOut','bbox_proposals','edge_boxes','gpu_id',1);

The above command will use the Reduced MR-CNN recognition model and the LocNet In-Out localization model located in the following directories:

 $LocNet/models-exps/VGG16_Reduced_MRCNN # Reduced MR-CNN recognition model
 $LocNet/models-exps/VGG16_LocNet_InOut # LocNet In-Out localization model

In general, you can specify the recognition and localization models that will be tested by giving the directory names of the corresponding models as the 1st and 2nd input arguments in the script_test_object_detection_pipeline_PASCAL script. For more instructions on how to test the (pre-)trained models see the script:

 $LocNet/code/script_test_object_detection_pipeline_commands.m

Training your own LocNet models in PASCAL VOC datasets

To train your own LocNet localization models on PASCAL VOC dataset:

Downlaod the archive file of VGG16-Net model pre-trained on ImageNet classification task and then unzip and untar it in the following location: $LocNet/data/vgg16_pretrained.

Then

 # 1) open matlab from $LocNet directory
 cd $LocNet
 matlab
 # 2) run in the matlab command line enviroment
 >> script_train_LocNet_PASCAL('VGG16_LocNet_InOut_model','gpu_id',1,'loc_type','inout');

The above command will train a LocNet In-Out localization model in the union of VOC2007 train+val and VOC2012 train+val datasets using both Selecive Search and Edge Box proposals. The trained model will be saved in the destination directory:

 $LocNet/models-exps/VGG16_LocNet_InOut_model

of which the directory name is the string that is given as 1st input argument in the script script_train_LocNet_PASCAL. For more instructions on how to train your own LocNet localization models see the script:

 $LocNet/code/script_train_localization_models_commands.m

Note: for training each of the LocNet models you will require a GPU with at least 6 Gbytes of memory.

locnet's People

Contributors

Stargazers

Watchers

Forkers

tinyloop tybxiaobao wuxinhong ilovecv wwwanghao cv-ip ericdoug jieeee turinglife wanjinchang baiyancheng20 jeffzhengye onlysang cuijianzhu lkaige morusu kirk86 1292765944 shaoli-huang daidengxin zhonguochong arasharchor mazhengmac caomw wengcq dorniwang wzkg2012 s104061622 guoyilin silasxue litingfeng rhythm92 skair39 123chengbo geekvc poisonbox magicsn0w chelovekhe feiyilicare stormtiti cheneyfan daviehr livst lan1991xu iij0 yyuanad liviust zhangxgu lzd0825 luolongqiang alexa-chen kltsyn gxd1994 zxgdll yowhatever poison520 pustar lgen nemo110110 peiguangjing sz94 liangxi627 wishinger-li xipi702 merlin2013 queenjuliazxx yingning baby47 serendipity999 bison31205 hotlize lincaiming ai3dvision pabloapast tonycmu xxl1995 cuulee klqulei chunyu-lin-bjtu amirunpri2018 nnu-gisa asuradaseed zbqq kamiyuanyang youtang1993 saurabhsalunkhe25

locnet's Issues

Download the pre-computed Edge Box and Selective Search proposals of PASCAL images

Hi. The links of pre-computed Edge Box and Selective Search proposals of PASCAL images are missing. Can you upload them again?

a symbolic link of Caffe

Thx! I am in windows environment, how to create a symbolic link of Caffe?

caffe_LocNet --- Makefile:553: recipe for target '.build_release/src/caffe/net.o' failed

My system specs

Ubuntu 16.04
CUDA 8.0
Matlab R2014b
gcc/g++  5.4.0
OpenCV  3.2

Here is my output:

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 ‘const char* cudnnGetErrorString(cudnnStatus_t)’:
./include/caffe/util/cudnn.hpp:21:10: warning: enumeration value ‘CUDNN_STATUS_RUNTIME_PREREQUISITE_MISSING’ not handled in switch [-Wswitch]
   switch (status) {
          ^
./include/caffe/util/cudnn.hpp:21:10: warning: enumeration value ‘CUDNN_STATUS_RUNTIME_IN_PROGRESS’ not handled in switch [-Wswitch]
./include/caffe/util/cudnn.hpp:21:10: warning: enumeration value ‘CUDNN_STATUS_RUNTIME_FP_OVERFLOW’ not handled in switch [-Wswitch]
./include/caffe/util/cudnn.hpp: In function ‘void caffe::cudnn::setConvolutionDesc(cudnnConvolutionStruct**, cudnnTensorDescriptor_t, cudnnFilterDescriptor_t, int, int, int, int)’:
./include/caffe/util/cudnn.hpp:108:70: error: too few arguments to function ‘cudnnStatus_t cudnnSetConvolution2dDescriptor(cudnnConvolutionDescriptor_t, int, int, int, int, int, int, cudnnConvolutionMode_t, cudnnDataType_t)’
       pad_h, pad_w, stride_h, stride_w, 1, 1, CUDNN_CROSS_CORRELATION));
                                                                      ^
./include/caffe/util/cudnn.hpp:15:28: note: in definition of macro ‘CUDNN_CHECK’
     cudnnStatus_t status = condition; \
                            ^
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:537:27: note: declared here
 cudnnStatus_t CUDNNWINAPI cudnnSetConvolution2dDescriptor( cudnnConvolutionDescriptor_t convDesc,
                           ^
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:127:41: error: too few arguments to function ‘cudnnStatus_t cudnnSetPooling2dDescriptor(cudnnPoolingDescriptor_t, cudnnPoolingMode_t, cudnnNanPropagation_t, int, int, int, int, int, int)’
         pad_h, pad_w, stride_h, stride_w));
                                         ^
./include/caffe/util/cudnn.hpp:15:28: note: in definition of macro ‘CUDNN_CHECK’
     cudnnStatus_t status = condition; \
                            ^
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:1031:27: note: declared here
 cudnnStatus_t CUDNNWINAPI cudnnSetPooling2dDescriptor(
                           ^
Makefile:553: recipe for target '.build_release/src/caffe/internal_thread.o' failed
make: *** [.build_release/src/caffe/internal_thread.o] Error 1
➜  caffe_LocNet git:(master) ✗ ls
build           CONTRIBUTING.md  docs        LICENSE                  matlab     scripts
caffe.cloc      CONTRIBUTORS.md  examples    Makefile                 models     src
cmake           data             include     Makefile.config          python     tools
CMakeLists.txt  distribute       INSTALL.md  Makefile.config.example  README.md
➜  caffe_LocNet git:(master) ✗ cp Makefile Makefile-bak
➜  caffe_LocNet git:(master) ✗ ls
build           CONTRIBUTING.md  docs        LICENSE          Makefile.config.example  README.md
caffe.cloc      CONTRIBUTORS.md  examples    Makefile         matlab                   scripts
cmake           data             include     Makefile-bak     models                   src
CMakeLists.txt  distribute       INSTALL.md  Makefile.config  python                   tools
➜  caffe_LocNet git:(master) ✗ cp ~/caffe/Makefile .
➜  caffe_LocNet git:(master) ✗ ls
build           CONTRIBUTING.md  docs        LICENSE          Makefile.config.example  README.md
caffe.cloc      CONTRIBUTORS.md  examples    Makefile         matlab                   scripts
cmake           data             include     Makefile-bak     models                   src
CMakeLists.txt  distribute       INSTALL.md  Makefile.config  python                   tools
➜  caffe_LocNet git:(master) ✗ make all -8
make: invalid option -- '8'
Usage: make [options] [target] ...
Options:
  -b, -m                      Ignored for compatibility.
  -B, --always-make           Unconditionally make all targets.
  -C DIRECTORY, --directory=DIRECTORY
                              Change to DIRECTORY before doing anything.
  -d                          Print lots of debugging information.
  --debug[=FLAGS]             Print various types of debugging information.
  -e, --environment-overrides
                              Environment variables override makefiles.
  --eval=STRING               Evaluate STRING as a makefile statement.
  -f FILE, --file=FILE, --makefile=FILE
                              Read FILE as a makefile.
  -h, --help                  Print this message and exit.
  -i, --ignore-errors         Ignore errors from recipes.
  -I DIRECTORY, --include-dir=DIRECTORY
                              Search DIRECTORY for included makefiles.
  -j [N], --jobs[=N]          Allow N jobs at once; infinite jobs with no arg.
  -k, --keep-going            Keep going when some targets can't be made.
  -l [N], --load-average[=N], --max-load[=N]
                              Don't start multiple jobs unless load is below N.
  -L, --check-symlink-times   Use the latest mtime between symlinks and target.
  -n, --just-print, --dry-run, --recon
                              Don't actually run any recipe; just print them.
  -o FILE, --old-file=FILE, --assume-old=FILE
                              Consider FILE to be very old and don't remake it.
  -O[TYPE], --output-sync[=TYPE]
                              Synchronize output of parallel jobs by TYPE.
  -p, --print-data-base       Print make's internal database.
  -q, --question              Run no recipe; exit status says if up to date.
  -r, --no-builtin-rules      Disable the built-in implicit rules.
  -R, --no-builtin-variables  Disable the built-in variable settings.
  -s, --silent, --quiet       Don't echo recipes.
  -S, --no-keep-going, --stop
                              Turns off -k.
  -t, --touch                 Touch targets instead of remaking them.
  --trace                     Print tracing information.
  -v, --version               Print the version number of make and exit.
  -w, --print-directory       Print the current directory.
  --no-print-directory        Turn off -w, even if it was turned on implicitly.
  -W FILE, --what-if=FILE, --new-file=FILE, --assume-new=FILE
                              Consider FILE to be infinitely new.
  --warn-undefined-variables  Warn when an undefined variable is referenced.

This program built for x86_64-pc-linux-gnu
Report bugs to <[email protected]>
➜  caffe_LocNet git:(master) ✗ make all -8
make: invalid option -- '8'
Usage: make [options] [target] ...
Options:
  -b, -m                      Ignored for compatibility.
  -B, --always-make           Unconditionally make all targets.
  -C DIRECTORY, --directory=DIRECTORY
                              Change to DIRECTORY before doing anything.
  -d                          Print lots of debugging information.
  --debug[=FLAGS]             Print various types of debugging information.
  -e, --environment-overrides
                              Environment variables override makefiles.
  --eval=STRING               Evaluate STRING as a makefile statement.
  -f FILE, --file=FILE, --makefile=FILE
                              Read FILE as a makefile.
  -h, --help                  Print this message and exit.
  -i, --ignore-errors         Ignore errors from recipes.
  -I DIRECTORY, --include-dir=DIRECTORY
                              Search DIRECTORY for included makefiles.
  -j [N], --jobs[=N]          Allow N jobs at once; infinite jobs with no arg.
  -k, --keep-going            Keep going when some targets can't be made.
  -l [N], --load-average[=N], --max-load[=N]
                              Don't start multiple jobs unless load is below N.
  -L, --check-symlink-times   Use the latest mtime between symlinks and target.
  -n, --just-print, --dry-run, --recon
                              Don't actually run any recipe; just print them.
  -o FILE, --old-file=FILE, --assume-old=FILE
                              Consider FILE to be very old and don't remake it.
  -O[TYPE], --output-sync[=TYPE]
                              Synchronize output of parallel jobs by TYPE.
  -p, --print-data-base       Print make's internal database.
  -q, --question              Run no recipe; exit status says if up to date.
  -r, --no-builtin-rules      Disable the built-in implicit rules.
  -R, --no-builtin-variables  Disable the built-in variable settings.
  -s, --silent, --quiet       Don't echo recipes.
  -S, --no-keep-going, --stop
                              Turns off -k.
  -t, --touch                 Touch targets instead of remaking them.
  --trace                     Print tracing information.
  -v, --version               Print the version number of make and exit.
  -w, --print-directory       Print the current directory.
  --no-print-directory        Turn off -w, even if it was turned on implicitly.
  -W FILE, --what-if=FILE, --new-file=FILE, --assume-new=FILE
                              Consider FILE to be infinitely new.
  --warn-undefined-variables  Warn when an undefined variable is referenced.

This program built for x86_64-pc-linux-gnu
Report bugs to <[email protected]>
➜  caffe_LocNet git:(master) ✗ make all -8
make: invalid option -- '8'
Usage: make [options] [target] ...
Options:
  -b, -m                      Ignored for compatibility.
  -B, --always-make           Unconditionally make all targets.
  -C DIRECTORY, --directory=DIRECTORY
                              Change to DIRECTORY before doing anything.
  -d                          Print lots of debugging information.
  --debug[=FLAGS]             Print various types of debugging information.
  -e, --environment-overrides
                              Environment variables override makefiles.
  --eval=STRING               Evaluate STRING as a makefile statement.
  -f FILE, --file=FILE, --makefile=FILE
                              Read FILE as a makefile.
  -h, --help                  Print this message and exit.
  -i, --ignore-errors         Ignore errors from recipes.
  -I DIRECTORY, --include-dir=DIRECTORY
                              Search DIRECTORY for included makefiles.
  -j [N], --jobs[=N]          Allow N jobs at once; infinite jobs with no arg.
  -k, --keep-going            Keep going when some targets can't be made.
  -l [N], --load-average[=N], --max-load[=N]
                              Don't start multiple jobs unless load is below N.
  -L, --check-symlink-times   Use the latest mtime between symlinks and target.
  -n, --just-print, --dry-run, --recon
                              Don't actually run any recipe; just print them.
  -o FILE, --old-file=FILE, --assume-old=FILE
                              Consider FILE to be very old and don't remake it.
  -O[TYPE], --output-sync[=TYPE]
                              Synchronize output of parallel jobs by TYPE.
  -p, --print-data-base       Print make's internal database.
  -q, --question              Run no recipe; exit status says if up to date.
  -r, --no-builtin-rules      Disable the built-in implicit rules.
  -R, --no-builtin-variables  Disable the built-in variable settings.
  -s, --silent, --quiet       Don't echo recipes.
  -S, --no-keep-going, --stop
                              Turns off -k.
  -t, --touch                 Touch targets instead of remaking them.
  --trace                     Print tracing information.
  -v, --version               Print the version number of make and exit.
  -w, --print-directory       Print the current directory.
  --no-print-directory        Turn off -w, even if it was turned on implicitly.
  -W FILE, --what-if=FILE, --new-file=FILE, --assume-new=FILE
                              Consider FILE to be infinitely new.
  --warn-undefined-variables  Warn when an undefined variable is referenced.

This program built for x86_64-pc-linux-gnu
Report bugs to <[email protected]>
➜  caffe_LocNet git:(master) ✗ ls
build           CONTRIBUTING.md  docs        LICENSE          Makefile.config.example  README.md
caffe.cloc      CONTRIBUTORS.md  examples    Makefile         matlab                   scripts
cmake           data             include     Makefile-bak     models                   src
CMakeLists.txt  distribute       INSTALL.md  Makefile.config  python                   tools
➜  caffe_LocNet git:(master) ✗ cp Makefile-bak Makefile
➜  caffe_LocNet git:(master) ✗ ls
build           CONTRIBUTING.md  docs        LICENSE          Makefile.config.example  README.md
caffe.cloc      CONTRIBUTORS.md  examples    Makefile         matlab                   scripts
cmake           data             include     Makefile-bak     models                   src
CMakeLists.txt  distribute       INSTALL.md  Makefile.config  python                   tools
➜  caffe_LocNet git:(master) ✗ make all -j8
CXX src/caffe/internal_thread.cpp
CXX src/caffe/net.cpp
CXX src/caffe/data_transformer.cpp
CXX src/caffe/blob.cpp
CXX src/caffe/data_reader.cpp
CXX src/caffe/util/cudnn.cpp
CXX src/caffe/util/db_leveldb.cpp
CXX src/caffe/util/db_lmdb.cpp
In file included from ./include/caffe/util/device_alternate.hpp:40:0,
                 from ./include/caffe/common.hpp:19,
                 from ./include/caffe/util/db.hpp:6,
                 from ./include/caffe/util/db_lmdb.hpp:9,
                 from src/caffe/util/db_lmdb.cpp:2:
./include/caffe/util/cudnn.hpp: In function ‘const char* cudnnGetErrorString(cudnnStatus_t)’:
./include/caffe/util/cudnn.hpp:21:10: warning: enumeration value ‘CUDNN_STATUS_RUNTIME_PREREQUISITE_MISSING’ not handled in switch [-Wswitch]
   switch (status) {
          ^
./include/caffe/util/cudnn.hpp:21:10: warning: enumeration value ‘CUDNN_STATUS_RUNTIME_IN_PROGRESS’ not handled in switch [-Wswitch]
./include/caffe/util/cudnn.hpp:21:10: warning: enumeration value ‘CUDNN_STATUS_RUNTIME_FP_OVERFLOW’ not handled in switch [-Wswitch]
./include/caffe/util/cudnn.hpp: In function ‘void caffe::cudnn::setConvolutionDesc(cudnnConvolutionStruct**, cudnnTensorDescriptor_t, cudnnFilterDescriptor_t, int, int, int, int)’:
./include/caffe/util/cudnn.hpp:108:70: error: too few arguments to function ‘cudnnStatus_t cudnnSetConvolution2dDescriptor(cudnnConvolutionDescriptor_t, int, int, int, int, int, int, cudnnConvolutionMode_t, cudnnDataType_t)’
       pad_h, pad_w, stride_h, stride_w, 1, 1, CUDNN_CROSS_CORRELATION));
                                                                      ^
./include/caffe/util/cudnn.hpp:15:28: note: in definition of macro ‘CUDNN_CHECK’
     cudnnStatus_t status = condition; \
                            ^
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/util/db.hpp:6,
                 from ./include/caffe/util/db_lmdb.hpp:9,
                 from src/caffe/util/db_lmdb.cpp:2:
/usr/local/cuda/include/cudnn.h:537:27: note: declared here
 cudnnStatus_t CUDNNWINAPI cudnnSetConvolution2dDescriptor( cudnnConvolutionDescriptor_t convDesc,
                           ^
In file included from ./include/caffe/util/device_alternate.hpp:40:0,
                 from ./include/caffe/common.hpp:19,
                 from ./include/caffe/util/db.hpp:6,
                 from ./include/caffe/util/db_lmdb.hpp:9,
                 from src/caffe/util/db_lmdb.cpp:2:
./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:127:41: error: too few arguments to function ‘cudnnStatus_t cudnnSetPooling2dDescriptor(cudnnPoolingDescriptor_t, cudnnPoolingMode_t, cudnnNanPropagation_t, int, int, int, int, int, int)’
         pad_h, pad_w, stride_h, stride_w));
                                         ^
./include/caffe/util/cudnn.hpp:15:28: note: in definition of macro ‘CUDNN_CHECK’
     cudnnStatus_t status = condition; \
                            ^
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/util/db.hpp:6,
                 from ./include/caffe/util/db_lmdb.hpp:9,
                 from src/caffe/util/db_lmdb.cpp:2:
/usr/local/cuda/include/cudnn.h:1031:27: note: declared here
 cudnnStatus_t CUDNNWINAPI cudnnSetPooling2dDescriptor(
                           ^
Makefile:553: recipe for target '.build_release/src/caffe/util/db_lmdb.o' failed
make: *** [.build_release/src/caffe/util/db_lmdb.o] Error 1
make: *** Waiting for unfinished jobs....
In file included from src/caffe/util/cudnn.cpp:2:0:
./include/caffe/util/cudnn.hpp: In function ‘const char* cudnnGetErrorString(cudnnStatus_t)’:
./include/caffe/util/cudnn.hpp:21:10: warning: enumeration value ‘CUDNN_STATUS_RUNTIME_PREREQUISITE_MISSING’ not handled in switch [-Wswitch]
   switch (status) {
          ^
./include/caffe/util/cudnn.hpp:21:10: warning: enumeration value ‘CUDNN_STATUS_RUNTIME_IN_PROGRESS’ not handled in switch [-Wswitch]
./include/caffe/util/cudnn.hpp:21:10: warning: enumeration value ‘CUDNN_STATUS_RUNTIME_FP_OVERFLOW’ not handled in switch [-Wswitch]
./include/caffe/util/cudnn.hpp: In function ‘void caffe::cudnn::setConvolutionDesc(cudnnConvolutionStruct**, cudnnTensorDescriptor_t, cudnnFilterDescriptor_t, int, int, int, int)’:
./include/caffe/util/cudnn.hpp:108:70: error: too few arguments to function ‘cudnnStatus_t cudnnSetConvolution2dDescriptor(cudnnConvolutionDescriptor_t, int, int, int, int, int, int, cudnnConvolutionMode_t, cudnnDataType_t)’
       pad_h, pad_w, stride_h, stride_w, 1, 1, CUDNN_CROSS_CORRELATION));
                                                                      ^
./include/caffe/util/cudnn.hpp:15:28: note: in definition of macro ‘CUDNN_CHECK’
     cudnnStatus_t status = condition; \
                            ^
In file included from ./include/caffe/util/cudnn.hpp:5:0,
                 from src/caffe/util/cudnn.cpp:2:
/usr/local/cuda/include/cudnn.h:537:27: note: declared here
 cudnnStatus_t CUDNNWINAPI cudnnSetConvolution2dDescriptor( cudnnConvolutionDescriptor_t convDesc,
                           ^
In file included from src/caffe/util/cudnn.cpp:2:0:
./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:127:41: error: too few arguments to function ‘cudnnStatus_t cudnnSetPooling2dDescriptor(cudnnPoolingDescriptor_t, cudnnPoolingMode_t, cudnnNanPropagation_t, int, int, int, int, int, int)’
         pad_h, pad_w, stride_h, stride_w));
                                         ^
./include/caffe/util/cudnn.hpp:15:28: note: in definition of macro ‘CUDNN_CHECK’
     cudnnStatus_t status = condition; \
                            ^
In file included from ./include/caffe/util/cudnn.hpp:5:0,
                 from src/caffe/util/cudnn.cpp:2:
/usr/local/cuda/include/cudnn.h:1031:27: note: declared here
 cudnnStatus_t CUDNNWINAPI cudnnSetPooling2dDescriptor(
                           ^
Makefile:553: recipe for target '.build_release/src/caffe/util/cudnn.o' failed
make: *** [.build_release/src/caffe/util/cudnn.o] Error 1
In file included from ./include/caffe/util/device_alternate.hpp:40:0,
                 from ./include/caffe/common.hpp:19,
                 from ./include/caffe/util/db.hpp:6,
                 from ./include/caffe/util/db_leveldb.hpp:10,
                 from src/caffe/util/db_leveldb.cpp:2:
./include/caffe/util/cudnn.hpp: In function ‘const char* cudnnGetErrorString(cudnnStatus_t)’:
./include/caffe/util/cudnn.hpp:21:10: warning: enumeration value ‘CUDNN_STATUS_RUNTIME_PREREQUISITE_MISSING’ not handled in switch [-Wswitch]
   switch (status) {
          ^
./include/caffe/util/cudnn.hpp:21:10: warning: enumeration value ‘CUDNN_STATUS_RUNTIME_IN_PROGRESS’ not handled in switch [-Wswitch]
./include/caffe/util/cudnn.hpp:21:10: warning: enumeration value ‘CUDNN_STATUS_RUNTIME_FP_OVERFLOW’ not handled in switch [-Wswitch]
./include/caffe/util/cudnn.hpp: In function ‘void caffe::cudnn::setConvolutionDesc(cudnnConvolutionStruct**, cudnnTensorDescriptor_t, cudnnFilterDescriptor_t, int, int, int, int)’:
./include/caffe/util/cudnn.hpp:108:70: error: too few arguments to function ‘cudnnStatus_t cudnnSetConvolution2dDescriptor(cudnnConvolutionDescriptor_t, int, int, int, int, int, int, cudnnConvolutionMode_t, cudnnDataType_t)’
       pad_h, pad_w, stride_h, stride_w, 1, 1, CUDNN_CROSS_CORRELATION));
                                                                      ^
./include/caffe/util/cudnn.hpp:15:28: note: in definition of macro ‘CUDNN_CHECK’
     cudnnStatus_t status = condition; \
                            ^
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/util/db.hpp:6,
                 from ./include/caffe/util/db_leveldb.hpp:10,
                 from src/caffe/util/db_leveldb.cpp:2:
/usr/local/cuda/include/cudnn.h:537:27: note: declared here
 cudnnStatus_t CUDNNWINAPI cudnnSetConvolution2dDescriptor( cudnnConvolutionDescriptor_t convDesc,
                           ^
In file included from ./include/caffe/util/device_alternate.hpp:40:0,
                 from ./include/caffe/common.hpp:19,
                 from ./include/caffe/util/db.hpp:6,
                 from ./include/caffe/util/db_leveldb.hpp:10,
                 from src/caffe/util/db_leveldb.cpp:2:
./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:127:41: error: too few arguments to function ‘cudnnStatus_t cudnnSetPooling2dDescriptor(cudnnPoolingDescriptor_t, cudnnPoolingMode_t, cudnnNanPropagation_t, int, int, int, int, int, int)’
         pad_h, pad_w, stride_h, stride_w));
                                         ^
./include/caffe/util/cudnn.hpp:15:28: note: in definition of macro ‘CUDNN_CHECK’
     cudnnStatus_t status = condition; \
                            ^
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/util/db.hpp:6,
                 from ./include/caffe/util/db_leveldb.hpp:10,
                 from src/caffe/util/db_leveldb.cpp:2:
/usr/local/cuda/include/cudnn.h:1031:27: note: declared here
 cudnnStatus_t CUDNNWINAPI cudnnSetPooling2dDescriptor(
                           ^
Makefile:553: recipe for target '.build_release/src/caffe/util/db_leveldb.o' failed
make: *** [.build_release/src/caffe/util/db_leveldb.o] Error 1
In file included from ./include/caffe/util/device_alternate.hpp:40:0,
                 from ./include/caffe/common.hpp:19,
                 from ./include/caffe/blob.hpp:8,
                 from src/caffe/blob.cpp:4:
./include/caffe/util/cudnn.hpp: In function ‘const char* cudnnGetErrorString(cudnnStatus_t)’:
./include/caffe/util/cudnn.hpp:21:10: warning: enumeration value ‘CUDNN_STATUS_RUNTIME_PREREQUISITE_MISSING’ not handled in switch [-Wswitch]
   switch (status) {
          ^
./include/caffe/util/cudnn.hpp:21:10: warning: enumeration value ‘CUDNN_STATUS_RUNTIME_IN_PROGRESS’ not handled in switch [-Wswitch]
./include/caffe/util/cudnn.hpp:21:10: warning: enumeration value ‘CUDNN_STATUS_RUNTIME_FP_OVERFLOW’ not handled in switch [-Wswitch]
./include/caffe/util/cudnn.hpp: In function ‘void caffe::cudnn::setConvolutionDesc(cudnnConvolutionStruct**, cudnnTensorDescriptor_t, cudnnFilterDescriptor_t, int, int, int, int)’:
./include/caffe/util/cudnn.hpp:108:70: error: too few arguments to function ‘cudnnStatus_t cudnnSetConvolution2dDescriptor(cudnnConvolutionDescriptor_t, int, int, int, int, int, int, cudnnConvolutionMode_t, cudnnDataType_t)’
       pad_h, pad_w, stride_h, stride_w, 1, 1, CUDNN_CROSS_CORRELATION));
                                                                      ^
./include/caffe/util/cudnn.hpp:15:28: note: in definition of macro ‘CUDNN_CHECK’
     cudnnStatus_t status = condition; \
                            ^
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/blob.hpp:8,
                 from src/caffe/blob.cpp:4:
/usr/local/cuda/include/cudnn.h:537:27: note: declared here
 cudnnStatus_t CUDNNWINAPI cudnnSetConvolution2dDescriptor( cudnnConvolutionDescriptor_t convDesc,
                           ^
In file included from ./include/caffe/util/device_alternate.hpp:40:0,
                 from ./include/caffe/common.hpp:19,
                 from ./include/caffe/blob.hpp:8,
                 from src/caffe/blob.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:127:41: error: too few arguments to function ‘cudnnStatus_t cudnnSetPooling2dDescriptor(cudnnPoolingDescriptor_t, cudnnPoolingMode_t, cudnnNanPropagation_t, int, int, int, int, int, int)’
         pad_h, pad_w, stride_h, stride_w));
                                         ^
./include/caffe/util/cudnn.hpp:15:28: note: in definition of macro ‘CUDNN_CHECK’
     cudnnStatus_t status = condition; \
                            ^
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/blob.hpp:8,
                 from src/caffe/blob.cpp:4:
/usr/local/cuda/include/cudnn.h:1031:27: note: declared here
 cudnnStatus_t CUDNNWINAPI cudnnSetPooling2dDescriptor(
                           ^
Makefile:553: recipe for target '.build_release/src/caffe/blob.o' failed
make: *** [.build_release/src/caffe/blob.o] Error 1
In file included from ./include/caffe/util/device_alternate.hpp:40:0,
                 from ./include/caffe/common.hpp:19,
                 from ./include/caffe/blob.hpp:8,
                 from ./include/caffe/data_transformer.hpp:6,
                 from src/caffe/data_transformer.cpp:8:
./include/caffe/util/cudnn.hpp: In function ‘const char* cudnnGetErrorString(cudnnStatus_t)’:
./include/caffe/util/cudnn.hpp:21:10: warning: enumeration value ‘CUDNN_STATUS_RUNTIME_PREREQUISITE_MISSING’ not handled in switch [-Wswitch]
   switch (status) {
          ^
./include/caffe/util/cudnn.hpp:21:10: warning: enumeration value ‘CUDNN_STATUS_RUNTIME_IN_PROGRESS’ not handled in switch [-Wswitch]
./include/caffe/util/cudnn.hpp:21:10: warning: enumeration value ‘CUDNN_STATUS_RUNTIME_FP_OVERFLOW’ not handled in switch [-Wswitch]
./include/caffe/util/cudnn.hpp: In function ‘void caffe::cudnn::setConvolutionDesc(cudnnConvolutionStruct**, cudnnTensorDescriptor_t, cudnnFilterDescriptor_t, int, int, int, int)’:
./include/caffe/util/cudnn.hpp:108:70: error: too few arguments to function ‘cudnnStatus_t cudnnSetConvolution2dDescriptor(cudnnConvolutionDescriptor_t, int, int, int, int, int, int, cudnnConvolutionMode_t, cudnnDataType_t)’
       pad_h, pad_w, stride_h, stride_w, 1, 1, CUDNN_CROSS_CORRELATION));
                                                                      ^
./include/caffe/util/cudnn.hpp:15:28: note: in definition of macro ‘CUDNN_CHECK’
     cudnnStatus_t status = condition; \
                            ^
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/blob.hpp:8,
                 from ./include/caffe/data_transformer.hpp:6,
                 from src/caffe/data_transformer.cpp:8:
/usr/local/cuda/include/cudnn.h:537:27: note: declared here
 cudnnStatus_t CUDNNWINAPI cudnnSetConvolution2dDescriptor( cudnnConvolutionDescriptor_t convDesc,
                           ^
In file included from ./include/caffe/util/device_alternate.hpp:40:0,
                 from ./include/caffe/common.hpp:19,
                 from ./include/caffe/blob.hpp:8,
                 from ./include/caffe/data_transformer.hpp:6,
                 from src/caffe/data_transformer.cpp:8:
./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:127:41: error: too few arguments to function ‘cudnnStatus_t cudnnSetPooling2dDescriptor(cudnnPoolingDescriptor_t, cudnnPoolingMode_t, cudnnNanPropagation_t, int, int, int, int, int, int)’
         pad_h, pad_w, stride_h, stride_w));
                                         ^
./include/caffe/util/cudnn.hpp:15:28: note: in definition of macro ‘CUDNN_CHECK’
     cudnnStatus_t status = condition; \
                            ^
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/blob.hpp:8,
                 from ./include/caffe/data_transformer.hpp:6,
                 from src/caffe/data_transformer.cpp:8:
/usr/local/cuda/include/cudnn.h:1031:27: note: declared here
 cudnnStatus_t CUDNNWINAPI cudnnSetPooling2dDescriptor(
                           ^
Makefile:553: recipe for target '.build_release/src/caffe/data_transformer.o' failed
make: *** [.build_release/src/caffe/data_transformer.o] Error 1
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 ‘const char* cudnnGetErrorString(cudnnStatus_t)’:
./include/caffe/util/cudnn.hpp:21:10: warning: enumeration value ‘CUDNN_STATUS_RUNTIME_PREREQUISITE_MISSING’ not handled in switch [-Wswitch]
   switch (status) {
          ^
./include/caffe/util/cudnn.hpp:21:10: warning: enumeration value ‘CUDNN_STATUS_RUNTIME_IN_PROGRESS’ not handled in switch [-Wswitch]
./include/caffe/util/cudnn.hpp:21:10: warning: enumeration value ‘CUDNN_STATUS_RUNTIME_FP_OVERFLOW’ not handled in switch [-Wswitch]
./include/caffe/util/cudnn.hpp: In function ‘void caffe::cudnn::setConvolutionDesc(cudnnConvolutionStruct**, cudnnTensorDescriptor_t, cudnnFilterDescriptor_t, int, int, int, int)’:
./include/caffe/util/cudnn.hpp:108:70: error: too few arguments to function ‘cudnnStatus_t cudnnSetConvolution2dDescriptor(cudnnConvolutionDescriptor_t, int, int, int, int, int, int, cudnnConvolutionMode_t, cudnnDataType_t)’
       pad_h, pad_w, stride_h, stride_w, 1, 1, CUDNN_CROSS_CORRELATION));
                                                                      ^
./include/caffe/util/cudnn.hpp:15:28: note: in definition of macro ‘CUDNN_CHECK’
     cudnnStatus_t status = condition; \
                            ^
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:537:27: note: declared here
 cudnnStatus_t CUDNNWINAPI cudnnSetConvolution2dDescriptor( cudnnConvolutionDescriptor_t convDesc,
                           ^
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:127:41: error: too few arguments to function ‘cudnnStatus_t cudnnSetPooling2dDescriptor(cudnnPoolingDescriptor_t, cudnnPoolingMode_t, cudnnNanPropagation_t, int, int, int, int, int, int)’
         pad_h, pad_w, stride_h, stride_w));
                                         ^
./include/caffe/util/cudnn.hpp:15:28: note: in definition of macro ‘CUDNN_CHECK’
     cudnnStatus_t status = condition; \
                            ^
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:1031:27: note: declared here
 cudnnStatus_t CUDNNWINAPI cudnnSetPooling2dDescriptor(
                           ^
Makefile:553: recipe for target '.build_release/src/caffe/internal_thread.o' failed
make: *** [.build_release/src/caffe/internal_thread.o] Error 1
In file included from ./include/caffe/util/device_alternate.hpp:40:0,
                 from ./include/caffe/common.hpp:19,
                 from src/caffe/data_reader.cpp:6:
./include/caffe/util/cudnn.hpp: In function ‘const char* cudnnGetErrorString(cudnnStatus_t)’:
./include/caffe/util/cudnn.hpp:21:10: warning: enumeration value ‘CUDNN_STATUS_RUNTIME_PREREQUISITE_MISSING’ not handled in switch [-Wswitch]
   switch (status) {
          ^
./include/caffe/util/cudnn.hpp:21:10: warning: enumeration value ‘CUDNN_STATUS_RUNTIME_IN_PROGRESS’ not handled in switch [-Wswitch]
./include/caffe/util/cudnn.hpp:21:10: warning: enumeration value ‘CUDNN_STATUS_RUNTIME_FP_OVERFLOW’ not handled in switch [-Wswitch]
./include/caffe/util/cudnn.hpp: In function ‘void caffe::cudnn::setConvolutionDesc(cudnnConvolutionStruct**, cudnnTensorDescriptor_t, cudnnFilterDescriptor_t, int, int, int, int)’:
./include/caffe/util/cudnn.hpp:108:70: error: too few arguments to function ‘cudnnStatus_t cudnnSetConvolution2dDescriptor(cudnnConvolutionDescriptor_t, int, int, int, int, int, int, cudnnConvolutionMode_t, cudnnDataType_t)’
       pad_h, pad_w, stride_h, stride_w, 1, 1, CUDNN_CROSS_CORRELATION));
                                                                      ^
./include/caffe/util/cudnn.hpp:15:28: note: in definition of macro ‘CUDNN_CHECK’
     cudnnStatus_t status = condition; \
                            ^
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 src/caffe/data_reader.cpp:6:
/usr/local/cuda/include/cudnn.h:537:27: note: declared here
 cudnnStatus_t CUDNNWINAPI cudnnSetConvolution2dDescriptor( cudnnConvolutionDescriptor_t convDesc,
                           ^
In file included from ./include/caffe/util/device_alternate.hpp:40:0,
                 from ./include/caffe/common.hpp:19,
                 from src/caffe/data_reader.cpp:6:
./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:127:41: error: too few arguments to function ‘cudnnStatus_t cudnnSetPooling2dDescriptor(cudnnPoolingDescriptor_t, cudnnPoolingMode_t, cudnnNanPropagation_t, int, int, int, int, int, int)’
         pad_h, pad_w, stride_h, stride_w));
                                         ^
./include/caffe/util/cudnn.hpp:15:28: note: in definition of macro ‘CUDNN_CHECK’
     cudnnStatus_t status = condition; \
                            ^
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 src/caffe/data_reader.cpp:6:
/usr/local/cuda/include/cudnn.h:1031:27: note: declared here
 cudnnStatus_t CUDNNWINAPI cudnnSetPooling2dDescriptor(
                           ^
Makefile:553: recipe for target '.build_release/src/caffe/data_reader.o' failed
make: *** [.build_release/src/caffe/data_reader.o] Error 1
In file included from ./include/caffe/util/device_alternate.hpp:40:0,
                 from ./include/caffe/common.hpp:19,
                 from src/caffe/net.cpp:10:
./include/caffe/util/cudnn.hpp: In function ‘const char* cudnnGetErrorString(cudnnStatus_t)’:
./include/caffe/util/cudnn.hpp:21:10: warning: enumeration value ‘CUDNN_STATUS_RUNTIME_PREREQUISITE_MISSING’ not handled in switch [-Wswitch]
   switch (status) {
          ^
./include/caffe/util/cudnn.hpp:21:10: warning: enumeration value ‘CUDNN_STATUS_RUNTIME_IN_PROGRESS’ not handled in switch [-Wswitch]
./include/caffe/util/cudnn.hpp:21:10: warning: enumeration value ‘CUDNN_STATUS_RUNTIME_FP_OVERFLOW’ not handled in switch [-Wswitch]
./include/caffe/util/cudnn.hpp: In function ‘void caffe::cudnn::setConvolutionDesc(cudnnConvolutionStruct**, cudnnTensorDescriptor_t, cudnnFilterDescriptor_t, int, int, int, int)’:
./include/caffe/util/cudnn.hpp:108:70: error: too few arguments to function ‘cudnnStatus_t cudnnSetConvolution2dDescriptor(cudnnConvolutionDescriptor_t, int, int, int, int, int, int, cudnnConvolutionMode_t, cudnnDataType_t)’
       pad_h, pad_w, stride_h, stride_w, 1, 1, CUDNN_CROSS_CORRELATION));
                                                                      ^
./include/caffe/util/cudnn.hpp:15:28: note: in definition of macro ‘CUDNN_CHECK’
     cudnnStatus_t status = condition; \
                            ^
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 src/caffe/net.cpp:10:
/usr/local/cuda/include/cudnn.h:537:27: note: declared here
 cudnnStatus_t CUDNNWINAPI cudnnSetConvolution2dDescriptor( cudnnConvolutionDescriptor_t convDesc,
                           ^
In file included from ./include/caffe/util/device_alternate.hpp:40:0,
                 from ./include/caffe/common.hpp:19,
                 from src/caffe/net.cpp:10:
./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:127:41: error: too few arguments to function ‘cudnnStatus_t cudnnSetPooling2dDescriptor(cudnnPoolingDescriptor_t, cudnnPoolingMode_t, cudnnNanPropagation_t, int, int, int, int, int, int)’
         pad_h, pad_w, stride_h, stride_w));
                                         ^
./include/caffe/util/cudnn.hpp:15:28: note: in definition of macro ‘CUDNN_CHECK’
     cudnnStatus_t status = condition; \
                            ^
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 src/caffe/net.cpp:10:
/usr/local/cuda/include/cudnn.h:1031:27: note: declared here
 cudnnStatus_t CUDNNWINAPI cudnnSetPooling2dDescriptor(
                           ^
Makefile:553: recipe for target '.build_release/src/caffe/net.o' failed
make: *** [.build_release/src/caffe/net.o] Error 1

Any solution?

Matlab crush when running 'demo_LocNet_object_detection_pipeline.m'

Dear author:

Thanks for your great work and code.
My env is Ubuntu 16.04+CUDA-8+cudnn-5.
When I ran the demo_LocNet_object_detection_pipeline.m, the matlab was crushed and the log is shown as follows.
Have you met this error before? Could you help me with this?
I have been sloving this problem for 2 days.
Thanks a lot!

`
Configuration:
Crash Decoding : Disabled - No sandbox or build area path
Crash Mode : continue (default)
Current Graphics Driver: Unknown software
Current Visual : 0x24 (class 4, depth 15)
Default Encoding : UTF-8
Deployed : false
GNU C Library : 2.23 stable
Host Name : gteam-inspur
MATLAB Architecture : glnxa64
MATLAB Entitlement ID: 6257193
MATLAB Root : /usr/local/MATLAB/R2016b
MATLAB Version : 9.1.0.441655 (R2016b)
OpenGL : software
Operating System : Linux 4.4.0-116-generic #140-Ubuntu SMP Mon Feb 12 21:23:04 UTC 2018 x86_64
Processor ID : x86 Family 6 Model 79 Stepping 1, GenuineIntel
Virtual Machine : Java 1.7.0_60-b19 with Oracle Corporation Java HotSpot(TM) 64-Bit Server VM mixed mode
Window System : The XFree86 Project, Inc (40300000), display :14.0

Fault Count: 6