動作環境

GeForce GTX 1070 (8GB)
ASRock Z170M Pro4S [Intel Z170chipset]
Ubuntu 16.04 LTS desktop amd64
TensorFlow v1.1.0
cuDNN v5.1 for Linux
CUDA v8.0
Python 3.5.2
IPython 6.0.0 -- An enhanced Interactive Python.
gcc (Ubuntu 5.4.0-6ubuntu1~16.04.4) 5.4.0 20160609
GNU bash, version 4.3.48(1)-release (x86_64-pc-linux-gnu)

概要

This article is related to ADDA (light scattering simulator based on the discrete dipole approximation).

TFRecordsを読込んで学習する
input: 5 nodes
output: 6 nodes
サンプル数: 223,872
学習データ: ADDAにより計算した値
- #input
- x,y,z: dipole position
- refractive index: real and imaginary part
- #output
- initial values for linear equation solution for (x,y,z),(real,imaginary)

code v0.1

TensorFlow > TFRecords読込み版sine curveの学習 v0.6 > 学習できた
をベースに
TensorFlow v1.1 / 移行 > tf.pack()はtf.stack()になった
の処理に変更してみた。

learn_mr_mi_170722.py

import numpy as np
import tensorflow as tf
import tensorflow.contrib.slim as slim

"""
v0.1 Jul. 22, 2017
  - increase network structure from [7,7,7] to [100,100,100]
  - increase dimension of [input_ph], [output_ph]
  - alter read_and_decode() to treat 5 input-, 6 output- nodes
  - alter [IN_FILE] to the symbolic linked file

  :reference: [learnExr_170504.py] to expand dimensions to [input:3,output:6]

=== branched from [learn_sineCurve_170708.py] ===
v0.6 Jul. 09, 2017
  - modify for PEP8
  - print prediction after learning
v0.5 Jul. 09, 2017
  - fix bug > [Attempting to use uninitialized value hidden/hidden_1/weights]
v0.4 Jul. 09, 2017
  - fix bug > stops only for one epoch
    + set [num_epochs=None] for string_input_producer()
  - change parameters for shuffle_batch()
  - implement training
v0.3 Jul. 09, 2017
  - fix warning > use tf.local_variables_initializer() instead of
       initialize_local_variables()
  - fix warning > use tf.global_variables_initializer() instead of
       initialize_all_variables()
v0.2 Jul. 08, 2017
  - fix bug > OutOfRangeError (current size 0)
    + use [tf.initialize_local_variables()]
v0.1 Jul. 08, 2017
  - only read [.tfrecords]
    + add inputs_xy()
    + add read_and_decode()
"""

# codingrule: PEP8

IN_FILE = 'LN-IntField-Y_170722.tfrecords'


def read_and_decode(filename_queue):
    reader = tf.TFRecordReader()
    _, serialized_example = reader.read(filename_queue)
    features = tf.parse_single_example(
        serialized_example,
        features={
           'xpos_raw': tf.FixedLenFeature([], tf.string),
           'ypos_raw': tf.FixedLenFeature([], tf.string),
           'zpos_raw': tf.FixedLenFeature([], tf.string),
           'mr_raw': tf.FixedLenFeature([], tf.string),
           'mi_raw': tf.FixedLenFeature([], tf.string),
           'exr_raw': tf.FixedLenFeature([], tf.string),
           'exi_raw': tf.FixedLenFeature([], tf.string),
           'eyr_raw': tf.FixedLenFeature([], tf.string),
           'eyi_raw': tf.FixedLenFeature([], tf.string),
           'ezr_raw': tf.FixedLenFeature([], tf.string),
           'ezi_raw': tf.FixedLenFeature([], tf.string),
        })
    xpos_raw = tf.decode_raw(features['xpos_raw'], tf.float32)
    ypos_raw = tf.decode_raw(features['ypos_raw'], tf.float32)
    zpos_raw = tf.decode_raw(features['zpos_raw'], tf.float32)
    mr_raw = tf.decode_raw(features['mr_raw'], tf.float32)
    mi_raw = tf.decode_raw(features['mi_raw'], tf.float32)
    exr_raw = tf.decode_raw(features['exr_raw'], tf.float32)
    exi_raw = tf.decode_raw(features['exi_raw'], tf.float32)
    eyr_raw = tf.decode_raw(features['eyr_raw'], tf.float32)
    eyi_raw = tf.decode_raw(features['eyi_raw'], tf.float32)
    ezr_raw = tf.decode_raw(features['ezr_raw'], tf.float32)
    ezi_raw = tf.decode_raw(features['ezi_raw'], tf.float32)

    xpos_org = tf.reshape(xpos_raw, [1])
    ypos_org = tf.reshape(ypos_raw, [1])
    zpos_org = tf.reshape(zpos_raw, [1])
    mr_org = tf.reshape(mr_raw, [1])
    mi_org = tf.reshape(mi_raw, [1])
    exr_org = tf.reshape(exr_raw, [1])
    exi_org = tf.reshape(exi_raw, [1])
    eyr_org = tf.reshape(eyr_raw, [1])
    eyi_org = tf.reshape(eyi_raw, [1])
    ezr_org = tf.reshape(ezr_raw, [1])
    ezi_org = tf.reshape(ezi_raw, [1])
    # input
    wrk = [xpos_org[0], ypos_org[0], zpos_org[0], mr_org[0], mi_org[0]]
    inputs = tf.stack(wrk)
    # output
    wrk = [exr_org[0], exi_org[0],
           eyr_org[0], eyi_org[0],
           ezr_org[0], ezi_org[0]]
    outputs = tf.stack(wrk)
    return inputs, outputs


def inputs_xy():
    filename = IN_FILE
    filequeue = tf.train.string_input_producer(
        [filename], num_epochs=None)

    in_org, out_org = read_and_decode(filequeue)
    return in_org, out_org

in_orgs, out_orgs = inputs_xy()
batch_size = 4  # 4
in_batch, out_batch = tf.train.shuffle_batch([in_orgs, out_orgs],
                                             batch_size,
                                             capacity=40,
                                             min_after_dequeue=batch_size)

input_ph = tf.placeholder("float", [None, 5])
output_ph = tf.placeholder("float", [None, 6])  # [6]

# network
hiddens = slim.stack(input_ph, slim.fully_connected, [100, 100, 100],
                     activation_fn=tf.nn.sigmoid, scope="hidden")
prediction = slim.fully_connected(hiddens, 6,
                                  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.global_variables_initializer(), tf.local_variables_initializer()]

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

    try:
        for idx in range(30000):  # 30000
            inpbt, outbt = sess.run([in_batch, out_batch])
            _, t_loss = sess.run([train_op, loss],
                                 feed_dict={input_ph: inpbt, output_ph: outbt})
            if (idx + 1) % 100 == 0:
                print("%d,%f" % (idx+1, t_loss))
    finally:
        coord.request_stop()

    coord.join(threads)

実行準備

TensorFlow > 複数のTFRecordsファイルを１つにまとめる v0.1,v0.2
で作成したcombined_IntField-Y_170722.tfrecordsを以下のようにリンクしておく。

$ ln -fs combined_IntField-Y_170722.tfrecords LN-IntField-Y_170722.tfrecords

実行

$ python3 learn_mr_mi_170722.py
...
2017-07-22 11:24:43.941798: I tensorflow/core/common_runtime/gpu/gpu_device.cc:908] DMA: 0 
2017-07-22 11:24:43.941802: I tensorflow/core/common_runtime/gpu/gpu_device.cc:918] 0:   Y 
2017-07-22 11:24:43.941821: I tensorflow/core/common_runtime/gpu/gpu_device.cc:977] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GeForce GTX 1070, pci bus id: 0000:01:00.0)
100,0.034486
200,0.012395
300,0.017949
400,0.053576
500,0.045468
600,0.059177
700,0.008754
...

補足

とりあえず動いた程度のコード
無駄な処理をしている
- reshapeして
- [0]で値取り出し
capacityやbatch_sizeは今後検討

lossの経過

$ python3 learn_mr_mi_170722.py > log_learn.170722_t1133

$ head log_learn.170722_t1133 
100,0.023204
200,0.010955
300,0.012770
400,0.044665
500,0.032256
600,0.055092
700,0.022653
800,0.016465
900,0.035304
1000,0.019785

Jupyterコード

check_result_170722.ipynb

%matplotlib inline

# learning [Exr,Exi,Eyr,Eyi,Ezr,Ezi] from ADDA
# Jul. 22, 2017

import numpy as np
import matplotlib.pyplot as plt

data1 = np.loadtxt('log_learn.170722_t1133', delimiter=',')

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

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

ax1.plot(input1, output1)

ax1.set_xlabel('step')
ax1.set_ylabel('loss')
ax1.set_ylim([0,0.2])
ax1.grid(True)

# fig.show()

予定どおり芳(かんば)しくない。

http://qiita.com/7of9/items/6c5959c786851bce3e76
と比べてlossが減少していない。

違いはrefractive indexを入れたこと。