faster-RCNN环境配置(Ubuntu14.04)
2016-01-26 11:48
447 查看
Requirements: hardware
For training smaller networks (ZF, VGG_CNN_M_1024) a good GPU (e.g., Titan, K20, K40, ...) with at least 3G of memory sufficesFor training with VGG16, you'll need a K40 (~11G of memory)
Installation (sufficient for the demo)
Clone the Faster R-CNN repository# Make sure to clone with --recursive git clone --recursive https://github.com/rbgirshick/py-faster-rcnn.git[/code]
Build the Cython modulescd $FRCN_ROOT/lib makesudo apt-get insatll python-pip [code]
[/code]
sudo pip install cython
sudo apt-get install python-opencv
sudo pip install easydict
Build Caffe and pycaffecd $FRCN_ROOT/caffe-fast-rcnn # Now follow the Caffe installation instructions here: # http://caffe.berkeleyvision.org/installation.html # If you're experienced with Caffe and have all of the requirements installed
参考我的另一篇博客:Ubuntu14.04(64位)+Cuda7.5+Cudnn7.0+Caffe+Matlab(Linux版)
http://blog.csdn.net/qq_26898461/article/details/50586052# In your Makefile.config, make sure to have this line uncommented WITH_PYTHON_LAYER := 1
# and your Makefile.config in place, then simply do:make -j8 && make pycaffe
Download pre-computed Faster R-CNN detectorscd $FRCN_ROOT ./data/scripts/fetch_faster_rcnn_models.shDemo
After successfully completing
basic installation, you'll be ready to run the demo.
Python
To run the democd $FRCN_ROOT ./tools/demo.py
相关文章推荐
- Javascript中匿名函数的调用与写法实例详解(多种)
- OpenSSH中SCP协议实现相关程序
- 即使有一颗强大的心,也要让人看到你美丽的外表
- 【转】android中最好的瀑布流控件PinterestLikeAdapterView
- HTTP 方法
- android从activity跳转到fragment解决
- 线段树解决约瑟夫问题
- ffmpeg解码音频数据时,开展重采样(即改变文件原有的采样率)
- 多线程编程
- MySQL 语句大全:创建、授权、查询、修改等
- 2016这些Android技术会很火
- Linux paste 命令
- nlp资料库集锦
- netiq
- 惯导相关书籍
- 【最大流】POJ3236-ACM Computer Factory
- nmap常用命令
- 支付宝 白名单
- jQuery命名空间,自定义空间及属性,插件开发全解析
- ffmpeg解码音频数据时,进行重采样(即改变文件原有的采样率)