编译 Faster Rcnn

来源：互联网发布：mac cosmetics美国官网编辑：程序博客网时间：2024/05/22 16:23

编译 Faster Rcnn

Rcnn 是比较经典的做目标检测的算法，今天准备学习一下，啥都不用说，先把程序调通。

一、编译caffe
编译caffe是最麻烦的事情。。

首先下载rcnn 的代码git clone --recursive https://github.com/rbgirshick/py-faster-rcnn.git

然后开始编译cd /home/mmt/Desktop/py-faster-rcnn/libmake

编译caffecd /home/mmt/Desktop/py-faster-rcnn/caffe-fast-rcnncp Makefile.config.example Makefile.config 然后修改里面的内容WITH_PYTHON_LAYER := 1  USE_CUDNN := 1将这两句前面的 # 号去掉然后make -j8 && make pycaffe

出现错误1src/caffe/net.cpp:8:18: fatal error: hdf5.h: No such file or directory解决方法：将Makefile.config中的INCLUDE_DIRS := $(PYTHON_INCLUDE) /usr/local/includeLIBRARY_DIRS := $(PYTHON_LIB) /usr/local/lib /usr/lib修改为：INCLUDE_DIRS := $(PYTHON_INCLUDE) /usr/local/include /usr/include/hdf5/serialLIBRARY_DIRS := $(PYTHON_LIB) /usr/local/lib /usr/lib /usr/lib/x86_64-linux-gnumake将 Makefile中LIBRARIES += glog gflags protobuf boost_system boost_filesystem m hdf5_hl hdf5修改为：LIBRARIES += glog gflags protobuf boost_system boost_filesystem m hdf5_serial_hl hdf5_serial重新编译：make -j8 && make pycaffe 出现错误2 error: too few arguments to function ‘cudnnStatus_t cudnnSetPooling2dDescriptor(cudnnPoolingDescriptor_t, cudnnPoolingMod解决方法：将BVLC(https://github.com/BVLC/caffe)中的下列文件copy 到相应的文件夹，即将这三个文件夹里的cudnn开头的文件全部换成新的：./include/caffe/util/cudnn.hpp./include/caffe/layers/cudnn_conv_layer.hpp./include/caffe/layers/cudnn_relu_layer.hpp./include/caffe/layers/cudnn_sigmoid_layer.hpp./include/caffe/layers/cudnn_tanh_layer.hpp./src/caffe/layers/cudnn_conv_layer.cpp./src/caffe/layers/cudnn_conv_layer.cu./src/caffe/layers/cudnn_relu_layer.cpp./src/caffe/layers/cudnn_relu_layer.cu./src/caffe/layers/cudnn_sigmoid_layer.cpp./src/caffe/layers/cudnn_sigmoid_layer.cu./src/caffe/layers/cudnn_tanh_layer.cpp./src/caffe/layers/cudnn_tanh_layer.cumake cleanmake -j8出现build_release/lib/libcaffe.so：对‘cv::imdecode(cv::_InputArray const&, int)’未定义的引用对于各种cv出错：解决方法：修改Makefile:LIBRARIES += glog gflags protobuf boost_system boost_filesystem m hdf5_serial_hl hdf5_serial matio opencv_core opencv_highgui opencv_imgproc opencv_imgcodecs下次编译之前要 make cleanmake clean make -j8编译成功make pycaffepython/caffe/_caffe.cpp:11:31: fatal error: numpy/arrayobject.h: No such file or directory解决方法：然后对照 Makefile.config将第二行加一个localPYTHON_INCLUDE := /usr/include/python2.7 \/usr/local/lib/python2.7/dist-packages/numpy/core/include重新编译成功

二、下载models
./data/scripts/fetch_faster_rcnn_models.sh

这里写图片描述
然后跑一个demo
./tools/demo.py

这里写图片描述

编译到此就成功了。

三、训练 Fast RCNN 出错
1、在网络初始化到loss_bbox层时会出现smoothL1loss.cpperror :bottom.size=4(3vs.4) If weightsare used, must specify both inside and outside weights之类错误！

解决方法：参考 http://blog.csdn.net/qq_34220460/article/details/72778714找到SmoothL1loss.cpp,找到出错误的那部分看到has_weights=(bottom.size()>=3);把它改成has_weights=(bottom.size()==3);然后下面的if语句用//注释掉。接着还要改，看到下面的这几行代码：    CHECK_EQ(bottom[0]->channels(),bottom[3]->channels());   CHECK_EQ(bottom[0]->height(), bottom[3]->height());   CHECK_EQ(bottom[0]->width(), bottom[3]->width());这三行，也要用//注释掉。Ok!!!!!再重新编译！！！！make clean     make  -j8

2、AttributeError: ‘module’ object has no attribute ‘text_format’
解决方法：参考网址 http://blog.csdn.net/qq_33202928/article/details/72526710

解决办法1：sudo pip install protobuf==2.5.0解决办法2：在文件./lib/fast_rcnn/train.py增加一行import google.protobuf.text_format 即可解决问题

3、TypeError: ‘numpy.float64’ object cannot be interpreted as an index
参考网址：http://m.blog.csdn.net/hongbin_xu/article/details/77278329

阅读全文

0 0