zoukankan      html  css  js  c++  java
  • Window系统 安装TFLearn

    1. 确保成功安装了tensorflow

    2. 查看当前tensorflow下的库文件,判断是否已经安装了h5py,scipy:conda list

    3. 若没有安装,安装h5py,scipy。我的电脑中没有安装h5py,安装:pip install h5py
    安装scipy同理

    4. 安装tflearn
    有两种安装方式
    1)pip install tflearn
    2) pip install git+https://github.com/tflearn/tflearn.git (要确保先安装了Git)
    我使用的第一种安装方法

    5. 至此tflearn安装成功。

    6. 从tflearn官网找的一个例子:http://tflearn.org/examples/

    from __future__ import absolute_import, division, print_function
    
    import tflearn
    
    # Regression data
    X = [3.3,4.4,5.5,6.71,6.93,4.168,9.779,6.182,7.59,2.167,7.042,10.791,5.313,7.997,5.654,9.27,3.1]
    Y = [1.7,2.76,2.09,3.19,1.694,1.573,3.366,2.596,2.53,1.221,2.827,3.465,1.65,2.904,2.42,2.94,1.3]
    
    # Linear Regression graph
    input_ = tflearn.input_data(shape=[None])
    linear = tflearn.single_unit(input_)
    regression = tflearn.regression(linear, optimizer='sgd', loss='mean_square',
                                    metric='R2', learning_rate=0.01)
    m = tflearn.DNN(regression)
    m.fit(X, Y, n_epoch=1000, show_metric=True, snapshot_epoch=False)
    
    print("
    Regression result:")
    print("Y = " + str(m.get_weights(linear.W)) +
          "*X + " + str(m.get_weights(linear.b)))
    
    print("
    Test prediction for x = 3.2, 3.3, 3.4:")
    print(m.predict([3.2, 3.3, 3.4]))

    运行结果部分截图如下:


    --------------------------------分割线--------------------------------------------
    安装过程中遇到的错误


    1. hdf5 is not supported on this machine (please install/reinstall h5py for optimal experience)
    原因:没有安装h5py,安装h5py后,问题得以解决

    2. curses is not supported on this machine (please install/reinstall curses for an optimal experience)
    解决方法:安装curses
    安装过程:
    1)如果没有安装wheel,首先通过pip命令安装wheel:pip install wheel

    2)从https://www.lfd.uci.edu/~gohlke/pythonlibs/ 下载curses‑2.2‑cp35‑none‑win_amd64.whl包

    3)cd到下载的.whl的目录(如我的 ~/PythonTool)。直接输入命令 : pip install curses-2.2-cp36-cp36m-win32.whl

    参考:https://github.com/lxzheng/machine_learning/wiki/TensorFlow--%E5%92%8C-TFlearn-Windows%E5%AE%89%E8%A3%85%E6%8C%87%E5%8D%97

  • 相关阅读:
    P2832 行路难
    P2634 [国家集训队]聪聪可可
    模拟退火算法
    洛谷 P2986 [USACO10MAR]Great Cow Gat…(树形dp+容斥原理)
    bzoj1040: [ZJOI2008]骑士(基环树dp)
    洛谷P2014 选课(树形dp)
    洛谷P3047 [USACO12FEB]Nearby Cows(树形dp)
    bzoj1026: [SCOI2009]windy数(数位dp)
    hdu3555Bomb(数位dp)
    hdu3652B-number(数位dp)
  • 原文地址:https://www.cnblogs.com/zeroingToOne/p/8484710.html
Copyright © 2011-2022 走看看