def main():
# parameters
nsamples = 2325
ndim = 10
#encoding_dim = 200
batch_size = 2325
epochs = 8000
# generate dummy data
x_train = data_gather.ggg()
# model
autoencoder, encoder, encoder1 = create_model(ndim)
# train model
autoencoder = train_model(autoencoder, x_train, batch_size, epochs)
# encoded signal
x_test = data_gather4.ggg()
encodedsig = encoder1.predict(x_train)
encodedsig1 = encoder1.predict(x_test)
#encodedsig = autoencoder.predict(x_train)
#encodedsig1=x_train
return (encodedsig, encodedsig1)
from sklearn.model_selection import KFold
import numpy as np
import matplotlib.pyplot as plt
from sklearn.svm import NuSVC
import data_gather
import data_gather4
import xlwt
import random
mnist1 = data_gather.ggg()
mnist2 = data_gather4.ggg()
XX = np.concatenate((mnist1, mnist2))
np.random.shuffle(XX)
#input_var = input("Number of data fold:")
size = len(XX)
y = np.zeros(shape=[size, 1])
for index in range(0, size):
if (4321 - index) >= 0:
y[index, 0] = 0
else:
y[index, 0] = 1
kf = KFold(n_splits=20)
kf.get_n_splits(XX)
print(kf)
KFold(n_splits=20, random_state=None, shuffle=False)
ii = 0
dum = np.zeros(len(XX))
for train_index, test_index in kf.split(XX):
#print("TRAIN:", train_index, "TEST:", test_index)
X_train, X_test = XX[train_index], XX[test_index]
y_train, y_test = y[train_index], y[test_index]
from __future__ import division, print_function, absolute_import
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
from random import randint
import data_gather1
import data_gather
import data_gather2
mnist2 = data_gather2.ggg()
mnist1 = data_gather1.ggg()
mnist = data_gather.ggg()
# Parameters
learning_rate = 0.0005
training_epochs = 5
batch_size = 1
display_step = 1
examples_to_show = 10
total_data_row = 2325
total_batch = np.floor(total_data_row / batch_size)
# Network Parameters
n_hidden_1 = 10 # 1st layer num features
n_hidden_2 = 10 # 2nd layer num features
n_input = 5 # MNIST data input (img shape: 28*28)
# tf Graph input (only pictures)
X = tf.placeholder("float", [None, n_input])
weights = {