深度学习常用软件包:
- Theano 偏底层,实现了GPU矩阵运算
- Pylearn2 模块化
- scikit-neuralnetwork
scikit-neuralnetwork
scikit-neuralnetwork是对pylearn2的神经 络封装,兼容scikit-learn。
GitHub中软件包以及安装步骤
https://github.com/aigamedev/scikit-neuralnetwork
通过CMD输入
pip install scikit-neuralnetwork
自动安装依赖
https://pypi.python.org/pypi/scikit-neuralnetwork
在python中
import theano
出现:
WARNING (theano.configdefaults): g++ not detected ! Theano will be unable to execute optimized C-implementations (for both CPU and GPU) and will default to Python implementations. Performance will be severely degraded. To remove this warning, set Theano flags cxx to an empty string.
Reason:Try installing the g compiler.Python is rather slow, so for performance-critical parts you need a compiled language such as C++.
solution:需要安装g++编译器
直接CMD中输入
conda install mingw libpython
出现
an http error occured when trying to retrieve….
初步认为是 络问题,可以换个 络或者换个时间段再执行上述命令。
文章知识点与官方知识档案匹配,可进一步学习相关知识Python入门技能树人工智能机器学习工具包Scikit-learn211742 人正在系统学习中 相关资源:求解偏微分方程的数学软件Fastflo-教育工具类资源
声明:本站部分文章及图片源自用户投稿,如本站任何资料有侵权请您尽早请联系jinwei@zod.com.cn进行处理,非常感谢!