学习可以参考这位大神的git:https://github.com/ljpzzz/machinelearning 从基础到强化
- Python安装
tips:a.安装3.5或者3.6,如果安装最新的3.7,tensorflow安装有问题
b. 注意numpy库和scipy要按照顺序安装,最好是下载whl后本地安装
c.注意安装numpy库和scipy时 jupyter notebook最好关闭 - pip安装
安装numpy scipy (下面要按照顺序安装)
https://www.lfd.uci.edu/~gohlke/pythonlibs/#numpy numpy-1.14.1+mkl-cp36-cp36m-win_amd64.whl
https://www.lfd.uci.edu/~gohlke/pythonlibs/#scipy scipy-1.0.0-cp36-cp36m-win_amd64.whl
pip3 install numpy-1.14.1+mkl-cp36-cp36m-win_amd64.whl
pip3 install scipy-1.0.0-cp36-cp36m-win_amd64.whl
进入到Python安装目录的script目录,找到pip.exe,执行以下命令
pip3 install -U matplotlib
pip3 install -U jinja2
pip3 install -U jsonschema
pip3 install -U pyzmq
pip3 install -U pandas
pip3 install -U scikit-learn - example
pip3 install jupyter
用 jupyter notebook命令测试
安装tensorflow
pip3 install --upgrade tensorflow
测试:
>>> import tensorflow as tf
>>> hello = tf.constant('Hello, TensorFlow!')
>>> sess = tf.Session()
>>> print(sess.run(hello))
- 下一步就是基础学习