在Jetson TX1上編譯執行Faster R-CNN
阿新 • • 發佈:2019-01-29
本文介紹如何在Jeston TX1上編譯執行python版本的Faster R-CNN程式碼
1.安裝相關依賴庫
$ 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 $2.克隆原始碼sudo pip install easydict PyYAML
$ 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.複製修改Cmake.config檔案
$ ../caffe-fast-rcnn/ $ cp Makefile.config.example Makefile.config
USE_CUDNN := 1 WITH_PYTHON_LAYER := 1
編譯caffe
make all -j3
make pycaffe -j34.下載模型檔案
cd $FRCN_ROOT./data/scripts/fetch_fast_rcnn_models.sh
5.測試執行demo
cd $FRCN_ROOT./tools/demo.py
結果:
ZF網路訓練模型:
參考: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