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
GNU bash, version 4.3.8(1)-release (x86_64-pc-linux-gnu)

Learning in Multidimensional Spaces — Neural Networks. Matrix Formulation by Andrew P Paplinski
March 17, 2017
の「5.4 (Simple) example of function approximation」における2次元入力(実数R^2)から2次元出力(R^2)へのmappingを実装してみた。

入力と出力の関係式は以下に記載している。（もしくはPDFを参照)。
http://qiita.com/7of9/items/54ec092a91880df9dc64

データ生成コード v0.1

Halton Sequenceを使うことで、R^2の入力を、より均一化するようにした。

UtilHaltonSequence.py

'''
v0.3 Mar. 20, 2017
    - change to a static function in a Class
v0.2 Oct. 22, 2016
    - implemented in Python
v0.1 Mar., 2005 or so
    - implemented in C
'''

# codingrule:PEP8


class CHaltonSequence:
    @staticmethod
    def calc_Halton_sequence(index):
        XBASE = 2
        YBASE = 3

        inv_xbase = 1.0 / XBASE
        fac_x = 1.0 / XBASE

        inv_ybase = 1.0 / YBASE
        fac_y = 1.0 / YBASE

        inp = index
        xwrk = 0.0
        while inp > 0:
            xwrk = xwrk + (inp % XBASE) * inv_xbase
            inp = inp / XBASE
            inv_xbase = inv_xbase * fac_x

        inp = index
        ywrk = 0.0
        while inp > 0:
            ywrk = ywrk + (inp % YBASE) * inv_ybase
            inp = inp / YBASE
            inv_ybase = inv_ybase * fac_y

        return xwrk, ywrk

'''
Usage example:

from UtilHaltonSequence import CHaltonSequence

for idx in range(0, 11):
    x0, y0 = CHaltonSequence.calc_Halton_sequence(index=idx)
    print(x0, y0)

'''

prep_data_170321.py

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import numpy as np
import math
import sys
from UtilHaltonSequence import CHaltonSequence

'''
on Python 2.7.6

v0.1 Mar. 21, 2017
  - output to STD
  - add func2d()
  - add get_2d_QMC()
  - add get_2d_random_nums()
'''
# codingrule:PEP8


def get_2d_random_nums(xsize, ysize):
    MAXVAL_PLUS_ONE = 65536
    ints = np.random.randint(MAXVAL_PLUS_ONE, size=(xsize, ysize))
    # print(ints)

    flts = ints / float(MAXVAL_PLUS_ONE)
    # print(flts)
    return flts


def get_2d_QMC(xsize):
    alist = []
    for idx in range(0, xsize):
        xwrk, ywrk = CHaltonSequence.calc_Halton_sequence(index=idx)
        alist.append([xwrk, ywrk])
    # print(alist)
    return np.array(alist)


def func2d(x1, x2):
    rho = x1 ** 2 + x2 ** 2
    epsilon = 10.**(-10)
    if abs(rho) < epsilon:
        return (0.0, 0.0)

    y1 = x1 * math.exp(-rho ** 2)
    try:
        # print(rho) # debug
        y2 = math.sin(2.0 * rho ** 2) / 4.0 / rho ** 2
    except ZeroDivisionError:
        y2 = 0.0
    return (y1, y2)

NUM_SAMPLES = 100

# 1. get random numbers in 2D
#
# a. np.random.randint()
# arr_2d = get_2d_random_nums(NUM_SAMPLES,2) # [0,1)
#
# b. QMC using Halton Sequence
arr_2d = get_2d_QMC(NUM_SAMPLES)  # [0, 1)

for x1, x2 in arr_2d:
    y1, y2 = func2d(x1, x2)
    print('%.7f, %.7f, %.7f, %.7f' % (x1, x2, y1, y2))
    # sys.exit()  # debug

$ python prep_data_170321.py > input.csv 
(tensorflow-GPU)yasokada@voyager01:~/WORK/TensorFlow/170319_xxyyFunc$ head input.csv 
0.0000000, 0.0000000, 0.0000000, 0.0000000
0.5000000, 0.3333333, 0.4388716, 0.4943511
0.2500000, 0.6666667, 0.1933435, 0.4782739
0.7500000, 0.1111111, 0.5389515, 0.4643882
0.1250000, 0.4444444, 0.1194477, 0.4993122
0.6250000, 0.7777778, 0.2319694, 0.2311777
0.3750000, 0.2222222, 0.3617029, 0.4995656
0.8750000, 0.5555556, 0.2759375, 0.1603667
0.0625000, 0.8888889, 0.0332709, 0.3776411
0.5625000, 0.0370370, 0.5084711, 0.4966077

学習コード v0.1

sine curveの学習をベースに作った。

learn_xxyyfunc_170321.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import sys
import tensorflow as tf
import tensorflow.contrib.slim as slim
import numpy as np

'''
v0.1 Mar. 22, 2017
  - learn mapping of R^2 input to R^2 output
     + using data prepared by [prep_data_170321.py]
  - branched from sine curve learning at
    http://qiita.com/7of9/items/ce58e66b040a0795b2ae
'''

# codingrule:PEP8


filename_queue = tf.train.string_input_producer(["input.csv"])

# parse CSV
reader = tf.TextLineReader()
key, value = reader.read(filename_queue)
input1, input2, output1, output2 = tf.decode_csv(
    value, record_defaults=[[0.], [0.], [0.], [0.]])
inputs = tf.pack([input1, input2])
output = tf.pack([output1, output2])

batch_size = 4  # [4]
inputs_batch, output_batch = tf.train.shuffle_batch(
    [inputs, output], batch_size, capacity=40, min_after_dequeue=batch_size)

input_ph = tf.placeholder("float", [None, 2])
output_ph = tf.placeholder("float", [None, 2])

## network
hiddens = slim.stack(input_ph, slim.fully_connected, [7, 7, 7],
                     activation_fn=tf.nn.sigmoid, scope="hidden")
#prediction = slim.fully_connected(
#    hiddens, 2, activation_fn=tf.nn.sigmoid, scope="output")
prediction = slim.fully_connected(
    hiddens, 2, activation_fn=None, scope="output")
loss = tf.contrib.losses.mean_squared_error(prediction, output_ph)

train_op = slim.learning.create_train_op(loss, tf.train.AdamOptimizer(0.001))

init_op = tf.initialize_all_variables()

with tf.Session() as sess:
    coord = tf.train.Coordinator()
    threads = tf.train.start_queue_runners(sess=sess, coord=coord)

    try:
        sess.run(init_op)
        for i in range(30000):  # [10000]
            inpbt, outbt = sess.run([inputs_batch, output_batch])
            _, t_loss = sess.run([train_op, loss],
                                 feed_dict={input_ph: inpbt, output_ph: outbt})

            if (i+1) % 100 == 0:
                print("%d,%f" % (i+1, t_loss))

    finally:
        coord.request_stop()

    coord.join(threads)

$ python learn_xxyyfunc_170321.py > res.2in2out_170322

学習経過の可視化

Jupyter code

check_result_170322.ipynb

%matplotlib inline

# mapping of R^2 to R^2
# Mar. 22, 2017

import numpy as np
import matplotlib.pyplot as plt

data1 = np.loadtxt('res.2in2out_170322', delimiter=',')

input1 = data1[:,0]
output1 = data1[:,1]

fig = plt.figure()
ax1 = fig.add_subplot(2,1,1)

ax1.plot(input1, output1)

ax1.set_xlabel('x')
ax1.set_ylabel('sin(x)')
ax1.set_ylim([0,0.02])
ax1.grid(True)

fig.show()

誤差は29800,0.000344程度にはなった。
時々スパイクは出ている。

実際にmappingが成功しているかは画像で確認することになる。