cost = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
# Evaluate model
correct_pred = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
# Initializing the variables
init = tf.global_variables_initializer()
cvscores = []
confusion_sum = [[0 for i in range(7)] for j in range(7)]
#data import
x_bed, x_fall, x_pickup, x_run, x_sitdown, x_standup, x_walk, \
y_bed, y_fall, y_pickup, y_run, y_sitdown, y_standup, y_walk = csv_import()
print(" bed =", len(x_bed), " fall=", len(x_fall), " pickup =", len(x_pickup),
" run=", len(x_run), " sitdown=", len(x_sitdown), " standup=",
len(x_standup), " walk=", len(x_walk))
#data shuffle
minm = min(len(y_bed), len(y_fall), len(y_pickup), len(y_run), len(y_sitdown),
len(y_standup), len(y_walk))
x_bed, y_bed = shuffle(x_bed[:minm], y_bed[:minm], random_state=0)
x_fall, y_fall = shuffle(x_fall[:minm], y_fall[:minm], random_state=0)
x_pickup, y_pickup = shuffle(x_pickup[:minm], y_pickup[:minm], random_state=0)
x_run, y_run = shuffle(x_run[:minm], y_run[:minm], random_state=0)
x_sitdown, y_sitdown = shuffle(x_sitdown[:minm],
y_sitdown[:minm],
# Define loss and optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
# Evaluate model
correct_pred = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
# Initializing the variables
init = tf.initialize_all_variables()
cvscores = []
confusion_sum = [[0 for i in range(7)] for j in range(7)]
#data import
x_bed, x_fall, x_pickup, x_run, x_sitdown, x_standup, x_walk, \
y_bed, y_fall, y_pickup, y_run, y_sitdown, y_standup, y_walk = csv_import( input_data_type )
print(" bed =", len(x_bed), " fall=", len(x_fall), " pickup =", len(x_pickup),
" run=", len(x_run), " sitdown=", len(x_sitdown), " standup=",
len(x_standup), " walk=", len(x_walk))
kk = 10 # k_fold
## Main ##
# mkdir + chdir
os.mkdir(foldername)
os.chdir(foldername)
with tf.Session() as sess:
for i in range(kk):
import numpy.random as npr
from configparser import *
import os
import pickle
import scipy.io
import sys
import glob
from numpy.linalg import norm
from scipy import misc
import utils
from cross_vali_input_data import csv_import, DataSet
from sklearn.utils import shuffle
x_dic, y_dic = csv_import()
# for i in ['bathroom','bathroom2','bedrooms','bedrooms2','corridor1','corridor2_1','corridor2_2','kitchen','kitchen2','lab2']:
# shuffle(x_dic[str(i)],y_dic[str(i)],random_state = 0)
# x_path = 'falldefi'+str(i)+'_images.pkl'
# y_path = 'falldefi'+str(i)+'_labels.pkl'
# pickle_out = open(x_path,"wb")
# cPickle.dump(np.array(x_dic[str(i)]),pickle_out)
# pickle_out.close()
# pickle_out = open(y_path,"wb")
# cPickle.dump(np.array(y_dic[str(i)]),pickle_out)
# pickle_out.close()
dic = {'bathroom':0,'bathroom2':1,'bedrooms':2,'bedrooms2':3,'corridor1':4,'corridor2_1':5,'corridor2_2':6,'kitchen':7,'kitchen2':8,'lab2':9}
for i in ['bathroom','bathroom2','bedrooms','bedrooms2','corridor1','corridor2_1','corridor2_2','kitchen','kitchen2','lab2']:
