Deep learning 更快的RCNN使失败

Deep learning 更快的RCNN使失败,deep-learning,caffe,object-detection,Deep Learning,Caffe,Object Detection,几天来,我一直在尝试使用GPU(Quadro K5100M)在笔记本电脑上实现更快的RCNN工作。 我能够在只有CPU的笔记本电脑上运行demo.py。 我正在使用CUDA 8和CuDnn 4以及caffe构建工程,但caffe在更快的rcnn中的构建过程不起作用。由于其他一些错误,我现在已将CuDnn注释掉。 谁能给我一些建议吗 我在make-j8&&make-pycaffe期间遇到这个错误 .build\u release/tools/extract\u features.o:In func

几天来,我一直在尝试使用GPU(Quadro K5100M)在笔记本电脑上实现更快的RCNN工作。 我能够在只有CPU的笔记本电脑上运行demo.py。 我正在使用CUDA 8和CuDnn 4以及caffe构建工程,但caffe在更快的rcnn中的构建过程不起作用。由于其他一些错误,我现在已将CuDnn注释掉。 谁能给我一些建议吗

我在make-j8&&make-pycaffe期间遇到这个错误

.build\u release/tools/extract\u features.o:In function
int feature\u extraction\u pipeline(int,char**): extract_features.cpp:(.text.Z27feature_extraction_pipelineifeippc[Z27feature_extraction_pipelineifeippc]+0x162):对
caffe::Net::Net的未定义引用(std:xx11::basic_字符串常量&,caffe::Phase,caffe::Net const*)”
collect2:错误:ld返回了1个退出状态
CXX/LD-o.build\u release/examples/mnist/convert\u mnist\u data.bin
Makefile:607:目标的配方“.build\u release/tools/extract\u features.bin”失败
make:**[.build\u release/tools/extract\u features.bin]错误1
制作:**等待未完成的工作。。。。
.build_release/tools/caffe.o:在函数中
test() caffe.cpp:(.text+0x1157):对
caffe::Net::Net的未定义引用(std:u cxx11::basic_字符串常量&,caffe::Phase,caffe::Net const*)
.build_release/tools/caffe.o:在函数中
train() caffe.cpp:(.text+0x2a3e):对
caffe::P2PSync::P2PSync(boost::shared_ptr,caffe::P2PSync*,caffe::SolverParameter const&)的未定义引用
caffe.cpp:(.text+0x2a6b):对
caffe::P2PSync::run(std::vector>const&)的未定义引用 caffe.cpp:(.text+0x2a73):对
caffe::P2PSync::~P2PSync()的未定义引用
caffe.cpp:(.text+0x3c53):对
caffe::P2PSync::~P2PSync()的未定义引用 caffe.cpp:(.text+0x3f45):对
caffe::P2PSync::~P2PSync()的未定义引用
.build_release/tools/caffe.o:在函数中
time(): caffe.cpp:(.text+0x4136):对
caffe::Net::Net的未定义引用(std:uu cxx11::basic_字符串常量&,caffe::Phase,caffe::Net const*)
caffe.cpp:(.text+0x44ef):对
caffe::Layer::Lock()的未定义引用 caffe.cpp:(.text+0x45ed):对
caffe::Layer::Unlock()的未定义引用
collect2:错误:ld返回了1个退出状态
Makefile:607:目标的配方“.build_release/tools/caffe.bin”失败

This is my makefile
# USE_CUDNN := 1
# CPU-only switch (uncomment to build without GPU support).
# CPU_ONLY := 1
# Uncomment if you're using OpenCV 3
 OPENCV_VERSION := 3
# CUDA directory contains bin/ and lib/ directories that we need.
CUDA_DIR := /usr/local/cuda-8.0
# On Ubuntu 14.04, if cuda tools are installed via
# "sudo apt-get install nvidia-cuda-toolkit" then use this instead:
# CUDA_DIR := /usr

CUDA_ARCH := -gencode arch=compute_20,code=sm_20 \
        -gencode arch=compute_20,code=sm_21 \
        -gencode arch=compute_30,code=sm_30 \
        -gencode arch=compute_35,code=sm_35 \
        -gencode arch=compute_50,code=sm_50 \
        -gencode arch=compute_50,code=compute_50

BLAS := atlas
#BLAS := open

# NOTE: this is required only if you will compile the python interface.
# We need to be able to find Python.h and numpy/arrayobject.h.
PYTHON_INCLUDE := /usr/include/python2.7 \
        /usr/local/lib/python2.7/dist-packages/numpy/core/include \
        /usr/local/lib/python2.7/dist-packages/numpy/core/include/numpy

# We need to be able to find libpythonX.X.so or .dylib.
PYTHON_LIB := /usr/lib
# PYTHON_LIB := $(ANACONDA_HOME)/lib

# Uncomment to support layers written in Python (will link against Python libs)
 WITH_PYTHON_LAYER := 1

# Whatever else you find you need goes here.
INCLUDE_DIRS := $(PYTHON_INCLUDE) /usr/local/include /usr/include/hdf5/serial /usr/include/opencv /usr/local/cuda-8.0/include 
LIBRARY_DIRS := $(PYTHON_LIB) /usr/local/lib /usr/lib /usr/lib/x86_64-linux-gnu /usr/lib/x86_64-linux-gnu/hdf5/serial /usr/local/share/OpenCV /usr/local/cuda-8.0/lib64

# N.B. both build and distribute dirs are cleared on `make clean`
BUILD_DIR := build
DISTRIBUTE_DIR := distribute

# Uncomment for debugging. Does not work on OSX due to https://github.com/BVLC/caffe/issues/171
# DEBUG := 1

# The ID of the GPU that 'make runtest' will use to run unit tests.
TEST_GPUID := 0

# enable pretty build (comment to see full commands)
Q ?= @

我有相同的错误,因为我的库路径(/usr/lib/)包含libcaffe.so的早期版本。移除它修复了问题