def evaluation(self):
a = 0
scores, y_pred_test = self.isolation_forest()
# print("##########scores###########")
# print(scores)
self.testy = np.load("test_y.npy")
# print("##############testy##############")
# print(self.testy)
auroc = do_roc(scores=scores,
true_labels=self.testy,
file_name='roc',
directory='data',
plot=False)
print('AUROC:', auroc)
auprc = do_prc(scores, self.testy, file_name='auprc', directory='data')
auprg = do_prg(scores, self.testy, file_name='auprg', directory='data')
per = get_percentile(scores, self.dataset, self.anomaly_type, a)
print(per)
y_pred = (scores >= per).astype(int)
precision, recall, f1, _ = precision_recall_fscore_support(
self.testy.astype(int), y_pred.astype(int), average='binary')
cm = confusion_matrix(self.testy,
y_pred,
labels=None,
sample_weight=None)
print('confusion matrix:', cm)
# check if folder exist:
if not os.path.exists('results/'):
os.makedirs('results/')
if not os.path.exists('results/tf_results'):
os.makedirs('results/tf_results')
# write results on csv file
csv_name = 'results/tf_results/results_' + self.dataset + '_' + self.anomaly_type + '_' + '.csv'
exists = os.path.isfile(csv_name)
if not exists:
columns = [
'auroc', 'auprc', 'auprg', 'precision', 'recall', 'f1', 'date'
]
df = pd.DataFrame(columns=columns)
df.to_csv(csv_name)
new_data = [
auroc,
auprc,
auprg,
precision,
recall,
f1,
datetime.datetime.now(),
]
with open(csv_name, 'a') as csv_file:
filewriter = csv.writer(csv_file)
filewriter.writerow(new_data)
def train_and_test(nb_epochs, weight, method, degree, random_seed):
""" Runs the Bigan on the KDD dataset
Note:
Saves summaries on tensorboard. To display them, please use cmd line
tensorboard --logdir=model.training_logdir() --port=number
Args:
nb_epochs (int): number of epochs
weight (float, optional): weight for the anomaly score composition
method (str, optional): 'fm' for ``Feature Matching`` or "cross-e"
for ``cross entropy``, "efm" etc.
anomalous_label (int): int in range 0 to 10, is the class/digit
which is considered outlier
"""
logger = logging.getLogger("BiGAN.train.kdd.{}".format(method))
# Placeholders
input_pl = tf.placeholder(tf.float32,
shape=data.get_shape_input(),
name="input")
is_training_pl = tf.placeholder(tf.bool, [], name='is_training_pl')
learning_rate = tf.placeholder(tf.float32, shape=(), name="lr_pl")
# Data
trainx, trainy = data.get_train()
trainx_copy = trainx.copy()
testx, testy = data.get_test()
trainx_org, trainy_org = data.get_train_org()
print('samples:', trainx.shape, testx.shape, trainx_org.shape)
# Parameters
starting_lr = network.learning_rate
batch_size = network.batch_size
latent_dim = network.latent_dim
ema_decay = 0.9999
rng = np.random.RandomState(RANDOM_SEED)
nr_batches_train = int(trainx.shape[0] / batch_size)
nr_batches_test = int(testx.shape[0] / batch_size)
nr_batches_train_org = int(trainx_org.shape[0] / batch_size)
logger.info('Building training graph...')
logger.warn("The BiGAN is training with the following parameters:")
display_parameters(batch_size, starting_lr, ema_decay, weight, method,
degree)
gen = network.decoder
enc = network.encoder
dis = network.discriminator
with tf.variable_scope('encoder_model'):
z_gen = enc(input_pl, is_training=is_training_pl)
with tf.variable_scope('generator_model'):
z = tf.random_normal([batch_size, latent_dim])
x_gen = gen(z, is_training=is_training_pl)
with tf.variable_scope('discriminator_model'):
l_encoder, inter_layer_inp = dis(z_gen,
input_pl,
is_training=is_training_pl)
l_generator, inter_layer_rct = dis(z,
x_gen,
is_training=is_training_pl,
reuse=True)
with tf.name_scope('loss_functions'):
# discriminator
loss_dis_enc = tf.reduce_mean(
tf.nn.sigmoid_cross_entropy_with_logits(
labels=tf.ones_like(l_encoder), logits=l_encoder))
loss_dis_gen = tf.reduce_mean(
tf.nn.sigmoid_cross_entropy_with_logits(
labels=tf.zeros_like(l_generator), logits=l_generator))
loss_discriminator = loss_dis_gen + loss_dis_enc
# generator
loss_generator = tf.reduce_mean(
tf.nn.sigmoid_cross_entropy_with_logits(
labels=tf.ones_like(l_generator), logits=l_generator))
# encoder
loss_encoder = tf.reduce_mean(
tf.nn.sigmoid_cross_entropy_with_logits(
labels=tf.zeros_like(l_encoder), logits=l_encoder))
with tf.name_scope('optimizers'):
# control op dependencies for batch norm and trainable variables
tvars = tf.trainable_variables()
dvars = [var for var in tvars if 'discriminator_model' in var.name]
gvars = [var for var in tvars if 'generator_model' in var.name]
evars = [var for var in tvars if 'encoder_model' in var.name]
update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
update_ops_gen = [
x for x in update_ops if ('generator_model' in x.name)
]
update_ops_enc = [x for x in update_ops if ('encoder_model' in x.name)]
update_ops_dis = [
x for x in update_ops if ('discriminator_model' in x.name)
]
optimizer_dis = tf.train.AdamOptimizer(learning_rate=learning_rate,
beta1=0.5,
name='dis_optimizer')
optimizer_gen = tf.train.AdamOptimizer(learning_rate=learning_rate,
beta1=0.5,
name='gen_optimizer')
optimizer_enc = tf.train.AdamOptimizer(learning_rate=learning_rate,
beta1=0.5,
name='enc_optimizer')
with tf.control_dependencies(update_ops_gen):
gen_op = optimizer_gen.minimize(loss_generator, var_list=gvars)
with tf.control_dependencies(update_ops_enc):
enc_op = optimizer_enc.minimize(loss_encoder, var_list=evars)
with tf.control_dependencies(update_ops_dis):
dis_op = optimizer_dis.minimize(loss_discriminator, var_list=dvars)
# Exponential Moving Average for estimation
dis_ema = tf.train.ExponentialMovingAverage(decay=ema_decay)
maintain_averages_op_dis = dis_ema.apply(dvars)
with tf.control_dependencies([dis_op]):
train_dis_op = tf.group(maintain_averages_op_dis)
gen_ema = tf.train.ExponentialMovingAverage(decay=ema_decay)
maintain_averages_op_gen = gen_ema.apply(gvars)
with tf.control_dependencies([gen_op]):
train_gen_op = tf.group(maintain_averages_op_gen)
enc_ema = tf.train.ExponentialMovingAverage(decay=ema_decay)
maintain_averages_op_enc = enc_ema.apply(evars)
with tf.control_dependencies([enc_op]):
train_enc_op = tf.group(maintain_averages_op_enc)
with tf.name_scope('summary'):
with tf.name_scope('dis_summary'):
tf.summary.scalar('loss_discriminator', loss_discriminator,
['dis'])
tf.summary.scalar('loss_dis_encoder', loss_dis_enc, ['dis'])
tf.summary.scalar('loss_dis_gen', loss_dis_gen, ['dis'])
with tf.name_scope('gen_summary'):
tf.summary.scalar('loss_generator', loss_generator, ['gen'])
tf.summary.scalar('loss_encoder', loss_encoder, ['gen'])
sum_op_dis = tf.summary.merge_all('dis')
sum_op_gen = tf.summary.merge_all('gen')
logger.info('Building testing graph...')
with tf.variable_scope('encoder_model'):
z_gen_ema = enc(input_pl,
is_training=is_training_pl,
getter=get_getter(enc_ema),
reuse=True)
with tf.variable_scope('generator_model'):
reconstruct_ema = gen(z_gen_ema,
is_training=is_training_pl,
getter=get_getter(gen_ema),
reuse=True)
with tf.variable_scope('discriminator_model'):
l_encoder_ema, inter_layer_inp_ema = dis(z_gen_ema,
input_pl,
is_training=is_training_pl,
getter=get_getter(dis_ema),
reuse=True)
l_generator_ema, inter_layer_rct_ema = dis(z_gen_ema,
reconstruct_ema,
is_training=is_training_pl,
getter=get_getter(dis_ema),
reuse=True)
with tf.name_scope('Testing'):
with tf.variable_scope('Reconstruction_loss'):
delta = input_pl - reconstruct_ema
delta_flat = tf.contrib.layers.flatten(delta)
gen_score = tf.norm(delta_flat,
ord=degree,
axis=1,
keep_dims=False,
name='epsilon')
with tf.variable_scope('Discriminator_loss'):
if method == "cross-e":
dis_score = tf.nn.sigmoid_cross_entropy_with_logits(
labels=tf.ones_like(l_generator_ema),
logits=l_generator_ema)
elif method == "fm":
fm = inter_layer_inp_ema - inter_layer_rct_ema
fm = tf.contrib.layers.flatten(fm)
dis_score = tf.norm(fm,
ord=degree,
axis=1,
keep_dims=False,
name='d_loss')
dis_score = tf.squeeze(dis_score)
with tf.variable_scope('Score'):
list_scores = (1 - weight) * gen_score + weight * dis_score
logdir = create_logdir(weight, method, random_seed)
sv = tf.train.Supervisor(logdir=logdir,
save_summaries_secs=None,
save_model_secs=120)
logger.info('Start training...')
with sv.managed_session() as sess:
logger.info('Initialization done')
writer = tf.summary.FileWriter(logdir, sess.graph)
train_batch = 0
epoch = 0
while not sv.should_stop() and epoch < nb_epochs:
lr = starting_lr
begin = time.time()
# construct randomly permuted minibatches
trainx = trainx[rng.permutation(
trainx.shape[0])] # shuffling dataset
trainx_copy = trainx_copy[rng.permutation(trainx.shape[0])]
train_loss_dis, train_loss_gen, train_loss_enc = [0, 0, 0]
# training
for t in range(nr_batches_train):
display_progression_epoch(t, nr_batches_train)
ran_from = t * batch_size
ran_to = (t + 1) * batch_size
# train discriminator
feed_dict = {
input_pl: trainx[ran_from:ran_to],
is_training_pl: True,
learning_rate: lr
}
_, ld, sm = sess.run(
[train_dis_op, loss_discriminator, sum_op_dis],
feed_dict=feed_dict)
train_loss_dis += ld
writer.add_summary(sm, train_batch)
# train generator and encoder
feed_dict = {
input_pl: trainx_copy[ran_from:ran_to],
is_training_pl: True,
learning_rate: lr
}
_, _, le, lg, sm = sess.run([
train_gen_op, train_enc_op, loss_encoder, loss_generator,
sum_op_gen
],
feed_dict=feed_dict)
train_loss_gen += lg
train_loss_enc += le
writer.add_summary(sm, train_batch)
train_batch += 1
train_loss_gen /= nr_batches_train
train_loss_enc /= nr_batches_train
train_loss_dis /= nr_batches_train
logger.info('Epoch terminated')
print(
"Epoch %d | time = %ds | loss gen = %.4f | loss enc = %.4f | loss dis = %.4f "
% (epoch, time.time() - begin, train_loss_gen, train_loss_enc,
train_loss_dis))
epoch += 1
logger.warn('Training evaluation...')
inds = rng.permutation(trainx_org.shape[0])
trainx_org = trainx_org[inds] # shuffling dataset
trainy_org = trainy_org[inds] # shuffling dataset
scores = []
inference_time = []
# Create scores
for t in range(nr_batches_train_org):
# construct randomly permuted minibatches
ran_from = t * batch_size
ran_to = (t + 1) * batch_size
begin_val_batch = time.time()
feed_dict = {
input_pl: trainx_org[ran_from:ran_to],
is_training_pl: False
}
scores += sess.run(list_scores, feed_dict=feed_dict).tolist()
inference_time.append(time.time() - begin_val_batch)
logger.info('Testing : mean inference time is %.4f' %
(np.mean(inference_time)))
ran_from = nr_batches_train_org * batch_size
ran_to = (nr_batches_train_org + 1) * batch_size
size = trainx_org[ran_from:ran_to].shape[0]
fill = np.ones([batch_size - size, 70])
batch = np.concatenate([trainx_org[ran_from:ran_to], fill], axis=0)
feed_dict = {input_pl: batch, is_training_pl: False}
batch_score = sess.run(list_scores, feed_dict=feed_dict).tolist()
scores += batch_score[:size]
# Highest 80% are anomalous
per = np.percentile(scores, 80)
y_pred_org = scores.copy()
y_pred_org = np.array(y_pred_org)
inds = (y_pred_org < per)
inds_comp = (y_pred_org >= per)
y_pred_org[inds] = 0
y_pred_org[inds_comp] = 1
roc_auc = do_roc(scores, trainy_org, "train_", "Results/", True)
prc_auc = do_prc(scores, trainy_org, "train_", "Results/", True)
#prg_auc = do_prg(scores, trainy_org, "train_", "Results/", True)
precision, recall, f1, _ = precision_recall_fscore_support(
trainy_org, y_pred_org, average='binary')
print("Testing : Prec = %.4f | Rec = %.4f | F1 = %.4f " %
(precision, recall, f1))
save_results(scores,
trainy_org,
'bigan',
'sia_train_air_4',
'fm',
'0.5',
'1',
2018,
'outlier',
0.1,
step=-1)
logger.warn('Testing evaluation...')
inds = rng.permutation(testx.shape[0])
testx = testx[inds] # shuffling dataset
testy = testy[inds] # shuffling dataset
scores = []
inference_time = []
# Create scores
for t in range(nr_batches_test):
# construct randomly permuted minibatches
ran_from = t * batch_size
ran_to = (t + 1) * batch_size
begin_val_batch = time.time()
feed_dict = {
input_pl: testx[ran_from:ran_to],
is_training_pl: False
}
scores += sess.run(list_scores, feed_dict=feed_dict).tolist()
inference_time.append(time.time() - begin_val_batch)
logger.info('Testing : mean inference time is %.4f' %
(np.mean(inference_time)))
ran_from = nr_batches_test * batch_size
ran_to = (nr_batches_test + 1) * batch_size
size = testx[ran_from:ran_to].shape[0]
fill = np.ones([batch_size - size, 70])
batch = np.concatenate([testx[ran_from:ran_to], fill], axis=0)
feed_dict = {input_pl: batch, is_training_pl: False}
batch_score = sess.run(list_scores, feed_dict=feed_dict).tolist()
scores += batch_score[:size]
# Highest 80% are anomalous
per = np.percentile(scores, 80)
y_pred = scores.copy()
y_pred = np.array(y_pred)
inds = (y_pred < per)
inds_comp = (y_pred >= per)
y_pred[inds] = 0
y_pred[inds_comp] = 1
roc_auc = do_roc(scores, testy, "test_", "Results/", True)
prc_auc = do_prc(scores, testy, "test_", "Results/", True)
#prg_auc = do_prg(scores, testy, "test_", "Results/", True)
precision, recall, f1, _ = precision_recall_fscore_support(
testy, y_pred, average='binary')
print("Testing : Prec = %.4f | Rec = %.4f | F1 = %.4f " %
(precision, recall, f1))
# SIA metrics calculation
TN_train, FN_train, FP_train, TP_train = my_confusion_matrix(
trainy_org, y_pred_org)
TN_test, FN_test, FP_test, TP_test = my_confusion_matrix(testy, y_pred)
overall_train, average_train, sens_train, spec_train, ppr_train = derive_metric(
TN_train, FN_train, FP_train, TP_train)
overall_test, average_test, sens_test, spec_test, ppr_test = derive_metric(
TN_test, FN_test, FP_test, TP_test)
print('Train Metrics:', overall_train, average_train, sens_train,
spec_train, ppr_train)
print('Test Metrics:', overall_test, average_test, sens_test,
spec_test, ppr_test)
save_results(scores,
testy,
'bigan',
'sia_test_air_4',
'fm',
'0.5',
'1',
2018,
'outlier',
0.1,
step=-1)
def train_and_test(nb_epochs, weight, method, degree, random_seed, label):
""" Runs the Bigan on the KDD dataset
Note:
Saves summaries on tensorboard. To display them, please use cmd line
tensorboard --logdir=model.training_logdir() --port=number
Args:
nb_epochs (int): number of epochs
weight (float, optional): weight for the anomaly score composition
method (str, optional): 'fm' for ``Feature Matching`` or "cross-e"
for ``cross entropy``, "efm" etc.
anomalous_label (int): int in range 0 to 10, is the class/digit
which is considered outlier
"""
logger = logging.getLogger("GAN.train.mnist.{}.{}".format(method,label))
# Placeholders
input_pl = tf.placeholder(tf.float32, shape=data.get_shape_input(), name="input")
is_training_pl = tf.placeholder(tf.bool, [], name='is_training_pl')
learning_rate = tf.placeholder(tf.float32, shape=(), name="lr_pl")
# Data
trainx, trainy = data.get_train(label, True)
trainx_copy = trainx.copy()
testx, testy = data.get_test(label, True)
# Parameters
starting_lr = network.learning_rate
batch_size = network.batch_size
latent_dim = network.latent_dim
ema_decay = 0.999
rng = np.random.RandomState(RANDOM_SEED)
nr_batches_train = int(trainx.shape[0] / batch_size)
nr_batches_test = int(testx.shape[0] / batch_size)
logger.info('Building training graph...')
logger.warn("The GAN is training with the following parameters:")
display_parameters(batch_size, starting_lr, ema_decay, weight, method, degree, label)
gen = network.generator
dis = network.discriminator
# Sample noise from random normal distribution
random_z = tf.random_normal([batch_size, latent_dim], mean=0.0, stddev=1.0, name='random_z')
# Generate images with generator
generator = gen(random_z, is_training=is_training_pl)
# Pass real and fake images into discriminator separately
real_d, inter_layer_real = dis(input_pl, is_training=is_training_pl)
fake_d, inter_layer_fake = dis(generator, is_training=is_training_pl, reuse=True)
with tf.name_scope('loss_functions'):
# Calculate seperate losses for discriminator with real and fake images
real_discriminator_loss = tf.losses.sigmoid_cross_entropy(tf.constant(1, shape=[batch_size]), real_d, scope='real_discriminator_loss')
fake_discriminator_loss = tf.losses.sigmoid_cross_entropy(tf.constant(0, shape=[batch_size]), fake_d, scope='fake_discriminator_loss')
# Add discriminator losses
discriminator_loss = real_discriminator_loss + fake_discriminator_loss
# Calculate loss for generator by flipping label on discriminator output
generator_loss = tf.losses.sigmoid_cross_entropy(tf.constant(1, shape=[batch_size]), fake_d, scope='generator_loss')
with tf.name_scope('optimizers'):
# control op dependencies for batch norm and trainable variables
dvars = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, scope='discriminator')
gvars = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, scope='generator')
update_ops_gen = tf.get_collection(tf.GraphKeys.UPDATE_OPS, scope='generator')
update_ops_dis = tf.get_collection(tf.GraphKeys.UPDATE_OPS, scope='discriminator')
optimizer_dis = tf.train.AdamOptimizer(learning_rate=learning_rate, beta1=0.5, name='dis_optimizer')
optimizer_gen = tf.train.AdamOptimizer(learning_rate=learning_rate, beta1=0.5, name='gen_optimizer')
with tf.control_dependencies(update_ops_gen): # attached op for moving average batch norm
gen_op = optimizer_gen.minimize(generator_loss, var_list=gvars)
with tf.control_dependencies(update_ops_dis):
dis_op = optimizer_dis.minimize(discriminator_loss, var_list=dvars)
dis_ema = tf.train.ExponentialMovingAverage(decay=ema_decay)
maintain_averages_op_dis = dis_ema.apply(dvars)
with tf.control_dependencies([dis_op]):
train_dis_op = tf.group(maintain_averages_op_dis)
gen_ema = tf.train.ExponentialMovingAverage(decay=ema_decay)
maintain_averages_op_gen = gen_ema.apply(gvars)
with tf.control_dependencies([gen_op]):
train_gen_op = tf.group(maintain_averages_op_gen)
with tf.name_scope('training_summary'):
with tf.name_scope('dis_summary'):
tf.summary.scalar('real_discriminator_loss', real_discriminator_loss, ['dis'])
tf.summary.scalar('fake_discriminator_loss', fake_discriminator_loss, ['dis'])
tf.summary.scalar('discriminator_loss', discriminator_loss, ['dis'])
with tf.name_scope('gen_summary'):
tf.summary.scalar('loss_generator', generator_loss, ['gen'])
with tf.name_scope('image_summary'):
tf.summary.image('reconstruct', generator, 8, ['image'])
tf.summary.image('input_images', input_pl, 8, ['image'])
sum_op_dis = tf.summary.merge_all('dis')
sum_op_gen = tf.summary.merge_all('gen')
sum_op_im = tf.summary.merge_all('image')
logger.info('Building testing graph...')
with tf.variable_scope("latent_variable"):
z_optim = tf.get_variable(name='z_optim', shape= [batch_size, latent_dim], initializer=tf.truncated_normal_initializer())
reinit_z = z_optim.initializer
# EMA
generator_ema = gen(z_optim, is_training=is_training_pl, getter=get_getter(gen_ema), reuse=True)
# Pass real and fake images into discriminator separately
real_d_ema, inter_layer_real_ema = dis(input_pl, is_training=is_training_pl, getter=get_getter(gen_ema), reuse=True)
fake_d_ema, inter_layer_fake_ema = dis(generator_ema, is_training=is_training_pl, getter=get_getter(gen_ema), reuse=True)
with tf.name_scope('error_loss'):
delta = input_pl - generator_ema
delta_flat = tf.contrib.layers.flatten(delta)
gen_score = tf.norm(delta_flat, ord=degree, axis=1, keep_dims=False, name='epsilon')
with tf.variable_scope('Discriminator_loss'):
if method == "cross-e":
dis_score = tf.nn.sigmoid_cross_entropy_with_logits(
labels=tf.ones_like(fake_d_ema), logits=fake_d_ema)
elif method == "fm":
fm = inter_layer_real_ema - inter_layer_fake_ema
fm = tf.contrib.layers.flatten(fm)
dis_score = tf.norm(fm, ord=degree, axis=1, keep_dims=False,
name='d_loss')
dis_score = tf.squeeze(dis_score)
with tf.variable_scope('Total_loss'):
loss = (1 - weight) * gen_score + weight * dis_score
with tf.variable_scope("Test_learning_rate"):
step = tf.Variable(0, trainable=False)
boundaries = [200, 300]
values = [0.01, 0.001, 0.0005]
learning_rate_invert = tf.train.piecewise_constant(step, boundaries, values)
reinit_lr = tf.variables_initializer(
tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES,
scope="Test_learning_rate"))
with tf.name_scope('Test_optimizer'):
optimizer = tf.train.AdamOptimizer(learning_rate_invert).minimize(loss, global_step=step, var_list=[z_optim], name='optimizer')
reinit_optim = tf.variables_initializer(
tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES,
scope='Test_optimizer'))
reinit_test_graph_op = [reinit_z, reinit_lr, reinit_optim]
with tf.name_scope("Scores"):
list_scores = loss
logdir = create_logdir(method, weight, label, random_seed)
sv = tf.train.Supervisor(logdir=logdir, save_summaries_secs=None,
save_model_secs=120)
logger.info('Start training...')
with sv.managed_session() as sess:
logger.info('Initialization done')
writer = tf.summary.FileWriter(logdir, sess.graph)
train_batch = 0
epoch = 0
while not sv.should_stop() and epoch < nb_epochs:
lr = starting_lr
begin = time.time()
trainx = trainx[rng.permutation(trainx.shape[0])] # shuffling unl dataset
trainx_copy = trainx_copy[rng.permutation(trainx.shape[0])]
train_loss_dis, train_loss_gen = [0, 0]
# training
for t in range(nr_batches_train):
display_progression_epoch(t, nr_batches_train)
# construct randomly permuted minibatches
ran_from = t * batch_size
ran_to = (t + 1) * batch_size
# train discriminator
feed_dict = {input_pl: trainx[ran_from:ran_to],
is_training_pl:True,
learning_rate:lr}
_, ld, sm = sess.run([train_dis_op, discriminator_loss, sum_op_dis], feed_dict=feed_dict)
train_loss_dis += ld
writer.add_summary(sm, train_batch)
# train generator
feed_dict = {input_pl: trainx_copy[ran_from:ran_to],
is_training_pl:True,
learning_rate:lr}
_, lg, sm = sess.run([train_gen_op, generator_loss, sum_op_gen], feed_dict=feed_dict)
train_loss_gen += lg
writer.add_summary(sm, train_batch)
if t % FREQ_PRINT == 0: # inspect reconstruction
t= np.random.randint(0,4000)
ran_from = t
ran_to = t + batch_size
sm = sess.run(sum_op_im, feed_dict={input_pl: trainx[ran_from:ran_to],is_training_pl: False})
writer.add_summary(sm, train_batch)
train_batch += 1
train_loss_gen /= nr_batches_train
train_loss_dis /= nr_batches_train
logger.info('Epoch terminated')
print("Epoch %d | time = %ds | loss gen = %.4f | loss dis = %.4f "
% (epoch, time.time() - begin, train_loss_gen, train_loss_dis))
epoch += 1
logger.warn('Testing evaluation...')
inds = rng.permutation(testx.shape[0])
testx = testx[inds] # shuffling unl dataset
testy = testy[inds]
scores = []
inference_time = []
# testing
for t in range(nr_batches_test):
# construct randomly permuted minibatches
ran_from = t * batch_size
ran_to = (t + 1) * batch_size
begin_val_batch = time.time()
# invert the gan
feed_dict = {input_pl: testx[ran_from:ran_to],
is_training_pl:False}
for step in range(STEPS_NUMBER):
_ = sess.run(optimizer, feed_dict=feed_dict)
scores += sess.run(list_scores, feed_dict=feed_dict).tolist()
inference_time.append(time.time() - begin_val_batch)
sess.run(reinit_test_graph_op)
logger.info('Testing : mean inference time is %.4f' % (
np.mean(inference_time)))
ran_from = nr_batches_test * batch_size
ran_to = (nr_batches_test + 1) * batch_size
size = testx[ran_from:ran_to].shape[0]
fill = np.ones([batch_size - size, 28, 28, 1])
batch = np.concatenate([testx[ran_from:ran_to], fill], axis=0)
feed_dict = {input_pl: batch,
is_training_pl: False}
for step in range(STEPS_NUMBER):
_ = sess.run(optimizer, feed_dict=feed_dict)
batch_score = sess.run(list_scores,
feed_dict=feed_dict).tolist()
scores += batch_score[:size]
prc_auc = do_prc(scores, testy,
file_name=r'gan/mnist/{}/{}/{}'.format(method, weight,
label),
directory=r'results/gan/mnist/{}/{}/'.format(method,
weight))
print("Testing | PRC AUC = {:.4f}".format(prc_auc))