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))
p = utils.get_perm(perm_str, _full)
EV = _full[p]
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()
evitramfinestr = cp.get('Experiment', 'ModelOutputPath') + \
cp.get('Experiment', 'PREFIX') + '_' + \
cp.get('Experiment', 'Enumber') + '_' + \
sys.argv[2] + '_cond_model.ckpt.meta'
# Full dataset random permutation path
perm_str = out_ + cp.get('Experiment', 'PREFIX') + '_perm.npy'
# Initialize Dataset
XX = dataset.train.images
XX_test = dataset.test.images
XX_full = np.concatenate((dataset.train.images, dataset.test.images))
utils.log(str(XX_full.shape))
p = utils.get_perm(perm_str, XX_full)
XX_full = XX_full[p]
# Init ground truth
YY = dataset.train.labels.flatten()
YY_test = dataset.test.labels.flatten()
YY_full = np.concatenate(
(dataset.train.labels.flatten(), dataset.test.labels.flatten()))
YY_full = YY_full[p]
# Get batch size in case of batch save
batch_size = cp.getint('Hyperparameters', 'BatchSize')