def SAE_evidence(sae_dict, cp2, ae_ids):
# Init variables and parameters
init = tf.global_variables_initializer()
saver = tf.train.Saver()
# Initialize model save string
saemodelstr = saefinestr.split('.meta')[0]
# Load evidence
K = utils.load_evidence(cp2.get('Experiment', 'EVIDENCEDATAPATH'))
# _full = np.concatenate((K.train.one, K.test.one))
_full = K.train.one
# p = utils.get_perm(perm_str, _full)
# EV = _full[p]
EV = _full
batch_size = cp2.getint('Hyperparameters', 'BatchSize')
# Start Session (Layerwise training)
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
# Initialize graph variables
init.run()
ev_dict = {
'cp2': cp2,
'sess': sess,
'saver': saver,
'EV': EV,
'savestr': saemodelstr,
'ae_ids': ae_ids,
'argv2': sys.argv[2]
}
EviAE.train(ev_dict, sae_dict)
# Save hidden/output layer results for pipeline training
utils.save_OOM(sess,
sae_dict['sda_in'],
EV,
sae_dict['sda_hidden'],
path=cp2.get('Experiment', 'PX_Z_TRAIN'),
batch_size=batch_size)
utils.save_OOM(sess,
sae_dict['sda_in'],
EV,
sae_dict['sda_out'],
path=cp2.get('Experiment', 'PX_XREC'),
batch_size=batch_size)
sess.close()
def evitram(evitramd):
saver = tf.train.Saver()
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
# Restore pretrained model
saver.restore(sess, evitramfinestr.split('.meta')[0])
if cp.get('Experiment', 'PREFIX') == 'MNIST':
# Save hidden/output layer results for pipeline training
px_Z_latent = utils.run_OOM(sess,
evitram_dict['conv_in'],
XX_full,
evitram_dict['conv_z'],
batch_size=batch_size)
# Save latent space
utils.save_OOM(sess,
evitram_dict['conv_in'],
XX_full,
evitram_dict['conv_z'],
path='COND_' + cp.get('Experiment', 'PX_Z_FULL'),
batch_size=batch_size)
# Save reconstruction
utils.save_OOM(sess,
evitram_dict['conv_in'],
XX_full,
evitram_dict['conv_out'],
path='COND_' +
cp.get('Experiment', 'PX_XREC_TRAIN'),
batch_size=batch_size)
else:
px_Z_latent = utils.run_OOM(sess,
evitram_dict['sda_in'],
XX_full,
evitram_dict['sda_hidden'],
batch_size=batch_size)
utils.save_OOM(sess,
evitram_dict['sda_in'],
XX_full,
evitram_dict['sda_hidden'],
path='COND_' + cp.get('Experiment', 'PX_Z_FULL'),
batch_size=batch_size)
# Print clustering ACC
utils.log_accuracy(cp, YY_full, px_Z_latent, 'COND - ACC FULL', SEED)
# Print clustering NMI
utils.log_NMI(cp, YY_full, px_Z_latent, 'COND - NMI FULL', SEED)
# Print clustering CHS score
utils.log_CHS(cp, XX_full, px_Z_latent, 'COND - CHS FULL', SEED)
sess.close()
def px(pae_dict):
saver = tf.train.Saver()
# P(x) Session
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
# Restore pretrained model
saver.restore(sess, pxfinestr.split('.meta')[0])
if cp.get('Experiment', 'PREFIX') == 'MNIST' or \
cp.get('Experiment', 'PREFIX') == 'AMNIST':
# Save hidden/output layer results for pipeline training
px_Z_latent = utils.run_OOM(sess,
pae_dict['conv_in'],
XX_full,
pae_dict['conv_z'],
batch_size=batch_size)
# Save latent space
utils.save_OOM(sess,
pae_dict['conv_in'],
XX_full,
pae_dict['conv_z'],
path=cp.get('Experiment', 'PX_Z_FULL'),
batch_size=batch_size)
# Save reconstruction
utils.save_OOM(sess,
pae_dict['conv_in'],
XX_full,
pae_dict['conv_out'],
path=cp.get('Experiment', 'PX_XREC_TRAIN'),
batch_size=batch_size)
else:
utils.save_OOM(sess,
pae_dict['sda_in'],
XX_full,
pae_dict['sda_hidden'],
path=cp.get('Experiment', 'PX_Z_FULL'),
batch_size=batch_size)
if not (np.array_equal(XX_test, np.zeros(shape=(1, 1)))):
utils.save_OOM(sess,
pae_dict['sda_in'],
XX_test,
pae_dict['sda_hidden'],
path=cp.get('Experiment', 'PX_Z_TEST'),
batch_size=batch_size)
utils.save_OOM(sess,
pae_dict['sda_in'],
XX_test,
pae_dict['sda_out'],
path=cp.get('Experiment', 'PX_XREC_TEST'),
batch_size=batch_size)
utils.save_OOM(sess,
pae_dict['sda_in'],
XX_full,
pae_dict['sda_out'],
path=cp.get('Experiment', 'PX_XREC_TRAIN'),
batch_size=batch_size)
sess.close()