ubuntu下测试mask-rcnn过程

本文参考诸多mask rcnn环境配置和测试的相关博客，在此不做列举，记录一下测试的全过程。

一.环境配置
1.python3.5

2.升级pip
sudo python –m pip install --upgrade pip
ps:笔者在升级和下载一些安装包的时候遇到如下错误：Could not fetch URL https://pypi.org/simple/pip/: There was a problem confirming the ssl certificate: HTTPSConnectionPool(host=‘pypi.org’, port=443): Max retries exceeded with url: /simple/pip/ (Caused by SSLError(SSLCertVerificationError(1, ‘[SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1045)’))) - skipping
据说因为高版本python在安装软件包时有不信任软件源的问题，解决方案如下：sudo pip install --trusted-host pypi.python.org --trusted-host files.pythonhosted.org --trusted-host pypi.org opencv-python

3.安装依赖项
numpy，scipy，cython，h5py，Pillow，scikit-image， opencv-python，imgaug，keras
安装keras之前需要安装tensorflow-gpu版本，参考这篇博客https://blog.csdn.net/dcrmg/article/detai