# validation_data=[VALIDATION_SIZE,600]
# one-step feed-forward training
# train_x, train_y = mnist.train.next_batch(batch_size)
# elm.feed(train_data, train_labels)
# print('train end')
for i in range(num):
train_data, train_labels = extractData_oned_train_val.extract_data_oned(
numRows=NUM_ROWS,
numData=TRAIN_SIZE,
drivers=DRIVERS,
labels=LABELS,
mode='train',
DATA_SIZE=DATA_SIZE,
NUM_CHANNELS=NUM_CHANNELS,
ONED=True,
BASE=BASE)
elm.feed(train_data, train_labels)
print('train end')
# testing
elm.test(validation_data, validation_labels)
file = open('sensor4_1_elm.txt', 'a')
file.write(str(num * TRAIN_SIZE))
file.write(',')
file.write(str(elm.test(validation_data, validation_labels)))
file.write('\n')
file.close()
print TRAIN_SIZE
from model import ELM
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
# Basic tf setting
tf.set_random_seed(2016)
sess = tf.Session()
# Get data
mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)
# Construct ELM
batch_size = 50000
hidden_num = 50000
print("batch_size : {}".format(batch_size))
print("hidden_num : {}".format(hidden_num))
elm = ELM(sess, batch_size, 784, hidden_num, 10)
# one-step feed-forward training
train_x, train_y = mnist.train.next_batch(batch_size)
elm.feed(train_x, train_y)
# testing
elm.test(mnist.test.images, mnist.test.labels)
# validation_data=[VALIDATION_SIZE,600]
# one-step feed-forward training
# train_x, train_y = mnist.train.next_batch(batch_size)
# elm.feed(train_data, train_labels)
# print('train end')
for i in range(num):
train_data, train_labels = extractData_oned_train_val.extract_data_oned(
numRows=NUM_ROWS,
numData=TRAIN_SIZE,
drivers=DRIVERS,
labels=LABELS,
mode='train',
DATA_SIZE=DATA_SIZE,
NUM_CHANNELS=NUM_CHANNELS,
ONED=True,
BASE=BASE)
elm.feed(train_data, train_labels)
print('train end')
# testing
result = elm.test(validation_data, validation_labels)
file = open('sensor10_elm.txt', 'a')
file.write(str(num * TRAIN_SIZE))
file.write(',')
file.write(str(result))
file.write('\n')
file.close()
print TRAIN_SIZE