def open_settings(self, action, *args):
dialog = Gtk.FileChooserDialog(
"Open a settings file", self.window, Gtk.FileChooserAction.OPEN,
(Gtk.STOCK_CANCEL, Gtk.ResponseType.CANCEL, Gtk.STOCK_OPEN,
Gtk.ResponseType.OK))
self.add_filters_to_chooserdialog(dialog)
response = dialog.run()
if response == Gtk.ResponseType.OK:
# TODO: Check for read permissions
# TODO: Check if it's a xjoy settings file
# TODO: Check if it's a non corrupted xjoy settings file
self.settings, objects = U.load_settings_from_file(
dialog.get_filename())
self.window.edit_area.set_objects(objects)
elif response == Gtk.ResponseType.CANCEL:
print("Cancel clicked")
dialog.destroy()
from sklearn.metrics.classification import *
from sklearn.metrics.ranking import *
from time import time
begin = time()
"""
Here, only the discriminator was used to do the anomaly detection
"""
# --- get settings --- #
# parse command line arguments, or use defaults
parser = utils.rgan_options_parser()
settings = vars(parser.parse_args())
# if a settings file is specified, it overrides command line arguments/defaults
if settings['settings_file']:
settings = utils.load_settings_from_file(settings)
# --- get data, split --- #
data_path = './experiments/data/' + settings['data_load_from'] + '.data.npy'
print('Loading data from', data_path)
settings["eval_single"] = False
settings["eval_an"] = False
samples, labels, index = data_utils.get_data(
settings["data"], settings["seq_length"], settings["seq_step"],
settings["num_signals"], settings["sub_id"], settings["eval_single"],
settings["eval_an"], data_path)
# --- save settings, data --- #
# no need
print('Ready to run with settings:')
for (k, v) in settings.items():
print(v, '\t', k)
import json
from scipy.stats import mode
import data_utils
import plotting
import model
import utils
from time import time
from math import floor
from mmd import rbf_mmd2, median_pairwise_distance, mix_rbf_mmd2_and_ratio
tf.logging.set_verbosity(tf.logging.ERROR)
with tf.device('/gpu:0'):
identifier = 'mnistfull'
settings = utils.load_settings_from_file(identifier)
samples, pdf, labels = data_utils.get_samples_and_labels(settings)
locals().update(settings)
# json.dump(settings, open('./experiments/settings/' + identifier + '.txt', 'w'), indent=0)
data_path = './experiments/data/' + identifier + '.data.npy'
np.save(data_path, {'samples': samples, 'pdf': pdf, 'labels': labels})
print('Saved training data to', data_path)
# --- build model --- #
Z, X, CG, CD, CS = model.create_placeholders(batch_size, seq_length,
latent_dim, num_signals,
cond_dim)
import model
import utils
import eval
from time import time
from math import floor
from mmd import rbf_mmd2, median_pairwise_distance, mix_rbf_mmd2_and_ratio
tf.logging.set_verbosity(tf.logging.ERROR)
begin = time()
# --- get settings --- #
# parse command line arguments, or use defaults
parser = utils.rgan_options_parser()
settings = vars(parser.parse_args())
# if a settings file is specified, it overrides command line arguments/defaults
if settings['settings_file']: settings = utils.load_settings_from_file(settings)
# --- get data, split --- #
# samples, pdf, labels = data_utils.get_samples_and_labels(settings)
samples, pdf, labels = data_utils.get_data(settings['data'], settings['seq_length'], settings['seq_step'], settings['num_signals'])
# --- training sample --- #
# --- save settings, data --- #
print('Ready to run with settings:')
for (k, v) in settings.items(): print(v, '\t', k)
# add the settings to local environment
# WARNING: at this point a lot of variables appear
locals().update(settings)
json.dump(settings, open('./experiments/settings/' + identifier + '.txt', 'w'), indent=0)
