在Jetson TX1上编译运行Faster R-CNN

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/sinat_31802439/article/details/52604972

本文介绍如何在Jeston TX1上编译运行python版本的Faster R-CNN代码

1.安装相关依赖库

$ sudo apt-get install libatlas-base-dev libprotobuf-dev libleveldb-dev libsnappy-dev libopencv-dev libhdf5-serial-dev protobuf-compiler libboost-all-dev libgflags2 libgflags-dev libgoogle-glog-dev liblmdb-dev libyaml-dev
$ sudo apt-get install python-numpy python-setuptools python-pip cython python-opencv python-skimage python-protobuf
$ sudo pip install easydict PyYAML

2.克隆源码

$ cd py-faster-rcnn/lib
$ sed -i -e 's/lib64/lib/g' setup.py
$ make


$ sed -i -e '1617s/__pyx_t_5numpy_int32_t/int/g' nms/gpu_nms.cpp
$ make

3.复制修改Cmake.config文件

$ ../caffe-fast-rcnn/
$ cp Makefile.config.example Makefile.config

USE_CUDNN := 1
WITH_PYTHON_LAYER := 1

编译caffe

make all -j3

make pycaffe -j3

4.下载模型文件

cd $FRCN_ROOT./data/scripts/fetch_fast_rcnn_models.sh

5.测试运行demo

cd $FRCN_ROOT./tools/demo.py

结果：

ZF网络训练模型：

参考：http://www.cnblogs.com/louyihang-loves-baiyan/p/4885659.html?utm_source=tuicool&utm_medium=referral

http://qiita.com/kndt84/items/a32d07350ad8184ea25e

http://blog.csdn.net/jiajunlee/article/details/50373815