TensorFlowで input:100, output:100のネットワークでの学習を検討 v0.2 > csvファイル出力追加

動作環境

GeForce GTX 1070 (8GB)
ASRock Z170M Pro4S [Intel Z170chipset]
Ubuntu 14.04 LTS desktop amd64
TensorFlow v0.11
cuDNN v5.1 for Linux
CUDA v8.0
Python 2.7.6
IPython 5.1.0 -- An enhanced Interactive Python.
gcc (Ubuntu 4.8.4-2ubuntu1~14.04.3) 4.8.4

v0.1 http://qiita.com/7of9/items/8b43357bcaea1f1bce4b

v0.2

• csvファイル出力追加
  • 関連してcalcOutput()をnumpy.arrayにて出力するように変更

参考: http://qiita.com/richi40/items/6b3af6f4b00d62dbe8e1

code

Jupyterコード

in100_out100.ipynb

import numpy as np
import matplotlib.pyplot as plt
import matplotlib.cm as cm

'''
v0.2 Jan. 14, 2017
  - sa() return in numpy.array
  - add saveToCsvFile()
v0.1 Jan. 14, 2017
  - add calcOutput()
  - add showIn2D()
  - show 1d in 2d format
'''

'''
codingrule:PEP8
'''

XDIM = 10
YDIM = 10
INDIM = XDIM * YDIM


def saveToCsvFile(data_1d, filename):
    wrk_1d = data_1d.reshape(1,INDIM)
    np.savetxt(filename, wrk_1d, delimiter=',')

def calcOutput(in_1d):
    len_1d = XDIM * YDIM
    out_1d = [0.0] * len_1d
    for idx in range(0, in_1d.size):
        out_1d[idx] = in_1d[len_1d - idx - 1]
    return np.array(out_1d)


def showIn2D(data_1d):
    # print(data_1d)
    data_2d = np.reshape(data_1d, (XDIM, YDIM))
    plt.imshow(data_2d, extent=(0, XDIM, 0, YDIM), cmap=cm.gist_rainbow)
    plt.show()

if __name__ == '__main__':
    in_1d = np.random.rand(INDIM)
    showIn2D(in_1d)
    out_1d = calcOutput(in_1d)
    showIn2D(out_1d)
    saveToCsvFile(in_1d, 'test_in.csv')
    saveToCsvFile(out_1d, 'test_out.csv')

結果

$ cut -c 1-200 test_in.csv 
3.757247572810928915e-04,2.261566444672071796e-01,5.665968126413482020e-01,5.869499141590118763e-01,6.474665738698877071e-01,8.782973384764291014e-01,9.808027016657328012e-01,9.172719111087710431e-01,

$ cut -c 2300-2500 test_out.csv 
,9.172719111087710431e-01,9.808027016657328012e-01,8.782973384764291014e-01,6.474665738698877071e-01,5.869499141590118763e-01,5.665968126413482020e-01,2.261566444672071796e-01,3.757247572810928915e-04