###############
model_valid = vae('valid', **C)
if A.profile:
from util_tf import profile
with tf.Session() as sess:
tf.global_variables_initializer().run()
with tf.summary.FileWriter(pform(P.log, A.trial), sess.graph) as wtr:
profile(sess, wtr, model_valid.loss, {
model_valid.src: valid[:32],
model_valid.tgt: valid[:32]
})
if not A.rounds: sys.exit("profiling done")
src, tgt = pipe(batch, (tf.int32, tf.int32), prefetch=A.prefetch)
model_train = vae('train', src=src, tgt=tgt, **C)
############
# training #
############
sess = tf.InteractiveSession()
saver = tf.train.Saver()
if A.ckpt:
saver.restore(sess, pform(P.ckpt, A.ckpt))
else:
tf.global_variables_initializer().run()
wtr = tf.summary.FileWriter(pform(P.log, A.trial))
summary = tf.summary.merge(
# valid_da, train_da = np.load(pform(P.data, "valid_da.npy")), np.load(pform(P.data, "train_da.npy"))
valid_sv, train_sv = np.load(pform(P.data, "valid_sv.npy")), np.load(pform(P.data, "train_sv.npy"))
data_index = 0, 2, 4
data_valid = valid_en, valid_de, valid_sv
data_train = train_en, train_de, train_sv
def batch(arrs, size= C.batch_train, seed= C.seed):
size //= len(arrs) * (len(arrs) - 1)
for i in batch_sample(len(arrs[0]), size, seed):
yield tuple(arr[i] for arr in arrs)
perm = comp(tuple, partial(permutations, r= 2))
data_index = perm(data_index)
data_valid = perm(data_valid)
data_train = perm(pipe(partial(batch, data_train), (tf.int32,)*len(data_train), prefetch= 16))
###############
# build model #
###############
model = Model.new(**select(C, *Model._new))
valid = tuple(model.data(i, j).valid() for i, j in data_index)
train = tuple(model.data(i, j, s, t).train(**T) for (i, j), (s, t) in zip(data_index, data_train))
model.lr = train[0].lr
model.step = train[0].step
model.errt = train[0].errt
model.loss = tf.add_n([t.loss for t in train])
model.down = tf.train.AdamOptimizer(model.lr, T.beta1, T.beta2, T.epsilon).minimize(model.loss, model.step)
def train(anomaly_class=8):
#set gpu
os.environ["CUDA_VISIBLE_DEVICES"] = "0"
#load data
(train_images,
train_labels), (test_images,
test_labels) = tf.keras.datasets.mnist.load_data()
inlier = train_images[train_labels != anomaly_class]
x_train = np.reshape(inlier, (len(inlier), 28 * 28)) / 255
#y_train = train_labels[train_labels!=anomaly_class]
y_train = np.zeros(len(x_train), dtype=np.int8) # dummy
outlier = train_images[train_labels == anomaly_class]
x_test = np.reshape(np.concatenate([outlier, test_images]),
(len(outlier) + len(test_images), 28 * 28)) / 255
y_test = np.concatenate(
[train_labels[train_labels == anomaly_class], test_labels])
y_test = [0 if y != anomaly_class else 1 for y in y_test]
x_test, y_test = unison_shfl(x_test, np.array(y_test))
path_log = "/cache/tensorboard-logdir/ae"
path_ckpt = "/project/outlier_detection/ckpt"
epochs = 400
batch_size = 700
dim_btlnk = 32
mult = 20
lr_max = 1e-4
trial = f"dae{anomaly_class}_b{batch_size}_btlnk{dim_btlnk}_lr_{lr_max}m{mult}"
#trial="test1"
dim_x = len(x_train[0])
#reset graphs and fix seeds
tf.reset_default_graph()
if 'sess' in globals(): sess.close()
rand = RandomState(0)
tf.set_random_seed(0)
# data pipeline
batch_fn = lambda: batch2(x_train, y_train, batch_size)
x, y = pipe(batch_fn, (tf.float32, tf.float32), prefetch=4)
#z = tf.random_normal((batch_size, z_dim))
# load graph
dae = DAE.new(dim_x, dim_btlnk)
model = DAE.build(dae, x, y, lr_max, mult)
# start session, initialize variables
sess = tf.InteractiveSession()
saver = tf.train.Saver()
wrtr = tf.summary.FileWriter(pform(path_log, trial))
#wrtr.add_graph(sess.graph)
### if load pretrained model
# pretrain = "modelname"
#saver.restore(sess, pform(path_ckpt, pretrain))
### else:
auc_vars = tf.get_collection(tf.GraphKeys.LOCAL_VARIABLES, scope='AUC')
init = tf.group(tf.global_variables_initializer(),
tf.variables_initializer(var_list=auc_vars))
sess.run(init)
def log(step,
wrtr=wrtr,
log=tf.summary.merge([
tf.summary.scalar('g_loss', model.g_loss),
tf.summary.scalar('d_loss', model.d_loss),
tf.summary.image('gx400',
spread_image(model.gx[:400], 20, 20, 28, 28)),
tf.summary.image('dgx400',
spread_image(model.dgx[:400], 20, 20, 28,
28)),
tf.summary.image('dx400',
spread_image(model.dx[:400], 20, 20, 28, 28)),
tf.summary.scalar("AUC_dgx", model.auc_dgx),
tf.summary.scalar("AUC_dx", model.auc_dx),
tf.summary.scalar("AUC_gx", model.auc_gx)
]),
y=y_test,
x=x_test):
wrtr.add_summary(sess.run(log, {model.x: x, model.y: y}), step)
wrtr.flush()
steps_per_epoch = len(x_train) // batch_size
for epoch in tqdm(range(epochs)):
for i in range(steps_per_epoch):
sess.run(model.d_step)
sess.run(model.g_step)
# tensorboard writer
log(sess.run(model["step"]) // steps_per_epoch)
saver.save(sess, pform(path_ckpt, trial), write_meta_graph=False)
def train(anomaly_class, loss_type):
#set gpu
os.environ["CUDA_VISIBLE_DEVICES"] = "1"
#load data
(train_images,
train_labels), (test_images,
test_labels) = tf.keras.datasets.mnist.load_data()
inlier = train_images[train_labels != anomaly_class]
x_train = np.reshape(inlier, (len(inlier), 28 * 28)) / 255
#y_train = train_labels[train_labels!=anomaly_class]
y_train = np.zeros(len(x_train), dtype=np.int8) # dummy
outlier = train_images[train_labels == anomaly_class]
x_test = np.reshape(np.concatenate([outlier, test_images]),
(len(outlier) + len(test_images), 28 * 28)) / 255
y_test = np.concatenate(
[train_labels[train_labels == anomaly_class], test_labels])
y_test = [0 if y != anomaly_class else 1 for y in y_test]
x_test, y_test = unison_shfl(x_test, np.array(y_test))
path_log = "/cache/tensorboard-logdir/ae"
path_ckpt = "/project/outlier_detection/ckpt"
epochs = 400
batch_size = 700
dim_btlnk = 32
dim_z = dim_btlnk
dim_dense = 32
accelerate = 1e-5
context_weight = 1
trial = f"vaegan_{loss_type}_{anomaly_class}_b{batch_size}_btlnk{dim_btlnk}_d{dim_dense}_n{dim_z}_a{accelerate}"
dim_x = len(x_train[0])
#reset graphs and fix seeds
tf.reset_default_graph()
if 'sess' in globals(): sess.close()
rand = RandomState(0)
tf.set_random_seed(0)
# data pipeline
batch_fn = lambda: batch2(x_train, y_train, batch_size, dim_z)
x, y, z = pipe(batch_fn, (tf.float32, tf.float32, tf.float32), prefetch=4)
# load graph
aegan = VAEGAN.new(dim_x, dim_btlnk, dim_dense, dim_z, accelerate)
model = VAEGAN.build(aegan, x, y, z, loss_type)
# start session, initialize variables
sess = tf.InteractiveSession()
saver = tf.train.Saver()
wrtr = tf.summary.FileWriter(pform(path_log, trial))
#wrtr.add_graph(sess.graph)
### if load pretrained model
# pretrain = "modelname"
#saver.restore(sess, pform(path_ckpt, pretrain))
### else:
auc_vars = tf.get_collection(tf.GraphKeys.LOCAL_VARIABLES, scope='AUC')
init = tf.group(tf.global_variables_initializer(),
tf.variables_initializer(var_list=auc_vars))
sess.run(init)
def log(
step,
wrtr=wrtr,
log=tf.summary.
merge([
tf.summary.scalar('g_loss', model.g_loss),
tf.summary.scalar('d_loss', model.d_loss),
tf.summary.scalar('mu', model.m),
tf.summary.scalar('lv', model.l),
tf.summary.image('gzx400',
spread_image(model.gzx[:400], 20, 20, 28, 28))
#, tf.summary.image('gz400', spread_image(model.gz[:400], 20,20,28,28))
,
tf.summary.scalar("AUC_gzx", model.auc_gzx),
tf.summary.scalar("AUC_dgzx", model.auc_dgzx),
tf.summary.scalar("AUC_dx", model.auc_dx)
#, tf.summary.scalar("gz_loss",model.gz_loss)
,
tf.summary.scalar("gzx_loss", model.gzx_loss),
tf.summary.scalar("ftr_loss", model.ftr_loss),
tf.summary.scalar("kl_loss", model.kl_loss),
tf.summary.scalar("dx_loss", model.dx_loss)
#, tf.summary.scalar("dgz_loss",model.dgz_loss)
,
tf.summary.scalar("dgzx_loss", model.dgzx_loss)
]),
y=y_test,
x=x_test):
mu = sess.run(model.mu, {model.x: x})
wrtr.add_summary(sess.run(log, {
model.zx: mu,
model.x: x,
model.y: y
}), step)
wrtr.flush()
steps_per_epoch = len(x_train) // batch_size
for epoch in tqdm(range(epochs)):
for i in range(steps_per_epoch):
sess.run(model.g_step)
sess.run(model.d_step)
# tensorboard writer
#log(sess.run(model["step"])//steps_per_epoch)
log(sess.run(model["step"] // steps_per_epoch))
saver.save(sess, pform(path_ckpt, trial), write_meta_graph=False)
val = np.array(
sorted(range(len(tgt_valid)),
key=lambda i: max(len(src_valid[i]), len(tgt_valid[i]))))
src_valid = src_valid[val]
tgt_valid = tgt_valid[val]
def feed(src, tgt, cws=cws, cwt=cwt):
src_idx, len_src = cws(src, ret_img=False, ret_idx=True)
tgt_img, tgt_idx, len_tgt = cwt(tgt, ret_img=True, ret_idx=True)
return src_idx, len_src, tgt_img, tgt_idx, len_tgt
def batch(src=src_train, tgt=tgt_train, size=128, seed=0):
for bat in batch_sample(len(tgt), size, seed):
yield feed(src[bat], tgt[bat])
src_idx, len_src, tgt_img, tgt_idx, len_tgt = pipe(
batch, (tf.int32, tf.int32, tf.uint8, tf.int32, tf.int32))
train = model('train', cws.dwh(), cwt.dwh(), src_idx, len_src, tgt_img,
tgt_idx, len_tgt)
valid = model('valid', cws.dwh(), cwt.dwh())
dummy = tuple(placeholder(tf.float32, ()) for _ in range(3))
def log(step,
wtr=tf.summary.FileWriter("../log/{}".format(trial)),
log=tf.summary.merge((tf.summary.scalar('step_mae', dummy[0]),
tf.summary.scalar('step_xid', dummy[1]),
tf.summary.scalar('step_err', dummy[2]))),
fet=(valid.mae, valid.xid, valid.err),
inp=(valid.src_idx, valid.len_src, valid.tgt_img, valid.tgt_idx,
valid.len_tgt),
src=src_valid,
tgt=tgt_valid,
def train(anomaly_class=8,
dataset="cifar",
n_dis=1,
epochs=25,
dim_btlnk=32,
batch_size=64,
loss="mean",
context_weight=1,
dim_d=64,
dim_g=64,
extra_layers=0,
gpu="0"):
#set gpu
os.environ["CUDA_VISIBLE_DEVICES"] = gpu
path_log = f"/cache/tensorboard-logdir/{dataset}"
path_ckpt = "/project/multi-discriminator-gan/ckpt"
path_data = "/project/multi-discriminator-gan/data"
#reset graphs and fix seeds
tf.reset_default_graph()
if 'sess' in globals(): sess.close()
rand = RandomState(0)
tf.set_random_seed(0)
#load data
if dataset == "ucsd1":
x_train = np.load("./data/ucsd1_train_x.npz")["arr_0"] / 255
y_train = np.load("./data/ucsd1_train_y.npz")["arr_0"]
x_test = np.load("./data/ucsd1_test_x.npz")["arr_0"] / 255
y_test = np.load("./data/ucsd1_test_y.npz")["arr_0"]
elif dataset == "uscd2":
x_train = np.load("./data/ucsd2_train_x.npz")["arr_0"]
y_train = np.load("./data/ucsd2_train_y.npz")["arr_0"]
x_test = np.load("./data/ucsd2_test_x.npz")["arr_0"]
y_test = np.load("./data/ucsd2_test_y.npz")["arr_0"]
else:
if dataset == "mnist":
(train_images, train_labels), (
test_images,
test_labels) = tf.keras.datasets.mnist.load_data()
train_images = resize_images(train_images)
test_images = resize_images(test_images)
else:
(train_images, train_labels), (
test_images,
test_labels) = tf.keras.datasets.cifar10.load_data()
train_labels = np.reshape(train_labels, len(train_labels))
test_labels = np.reshape(test_labels, len(test_labels))
inlier = train_images[train_labels != anomaly_class]
#data_size = prod(inlier[0].sha
x_train = inlier / 255
#x_train = np.reshape(inlier, (len(inlier), data_size))/255
#y_train = train_labels[train_labels!=anomaly_class]
y_train = np.zeros(len(x_train), dtype=np.int8) # dummy
outlier = train_images[train_labels == anomaly_class]
x_test = np.concatenate([outlier, test_images]) / 255
#x_test = np.reshape(np.concatenate([outlier, test_images])
# ,(len(outlier)+len(test_images), data_size))/255
y_test = np.concatenate(
[train_labels[train_labels == anomaly_class], test_labels])
y_test = [0 if y != anomaly_class else 1 for y in y_test]
x_test, y_test = unison_shfl(x_test, np.array(y_test))
img_size_x = x_train[0].shape[0]
img_size_y = x_train[0].shape[1]
channel = x_train[0].shape[-1]
trial = f"{dataset}_{loss}_dis{n_dis}_{anomaly_class}_w{context_weight}_btlnk{dim_btlnk}_d{dim_d}_g{dim_g}e{extra_layers}"
# data pipeline
batch_fn = lambda: batch2(x_train, y_train, batch_size)
x, y = pipe(batch_fn, (tf.float32, tf.float32), prefetch=4)
#z = tf.random_normal((batch_size, z_dim))
# load graph
mg_gan = MG_GAN.new(img_size_x,
channel,
dim_btlnk,
dim_d,
dim_g,
n_dis,
extra_layers=0)
model = MG_GAN.build(mg_gan, x, y, context_weight, loss)
# start session, initialize variables
sess = tf.InteractiveSession()
saver = tf.train.Saver()
wrtr = tf.summary.FileWriter(pform(path_log, trial))
wrtr.add_graph(sess.graph)
### if load pretrained model
# pretrain = "modelname"
#saver.restore(sess, pform(path_ckpt, pretrain))
### else:
auc_vars = tf.get_collection(tf.GraphKeys.LOCAL_VARIABLES, scope='AUC')
init = tf.group(tf.global_variables_initializer(),
tf.variables_initializer(var_list=auc_vars))
sess.run(init)
#if "ucsd" in dataset:
summary_test = tf.summary.merge([
tf.summary.scalar('g_loss', model.g_loss),
tf.summary.scalar("lambda", model.lam),
tf.summary.scalar("gl_rec", model.gl_rec),
tf.summary.scalar("gl_adv", model.gl_adv),
tf.summary.scalar("gl_lam", model.gl_lam),
tf.summary.scalar('d_loss_mean', model.d_loss_mean),
tf.summary.scalar('d_max', model.d_max)
#, tf.summary.scalar('d_loss', model.d_loss)
,
tf.summary.scalar("AUC_gx", model.auc_gx)
])
if dataset == "ucsd1":
summary_images = tf.summary.merge(
(tf.summary.image("gx", model.gx, max_outputs=8),
tf.summary.image("x", model.x, max_outputs=8),
tf.summary.image(
'gx400',
spread_image(tf.concat([model.gx, model.x], axis=1), 8, 2,
img_size_x, img_size_y, channel))))
else:
summary_images = tf.summary.merge(
(tf.summary.image("gx", model.gx, max_outputs=8),
tf.summary.image(
'gx400',
spread_image(model.gx[:400], 20, 20, img_size_x, img_size_y,
channel)),
tf.summary.image("x", model.x, max_outputs=8)))
if n_dis > 1:
d_wrtr = {
i: tf.summary.FileWriter(pform(path_log, trial + f"d{i}"))
for i in range(n_dis)
}
summary_discr = {
i: tf.summary.scalar('d_loss_multi', model.d_loss[i])
for i in range(n_dis)
}
def summ(step):
fetches = model.g_loss, model.lam, model.d_loss_mean, model.auc_gx
results = map(
np.mean,
zip(*(sess.run(fetches, {
model['x']: x_test[i:j],
model['y']: y_test[i:j]
}) for i, j in partition(len(x_test), batch_size, discard=False))))
results = list(results)
wrtr.add_summary(sess.run(summary_test, dict(zip(fetches, results))),
step)
if dataset == "ucsd1":
# bike, skateboard, grasswalk, shopping cart, car, normal, normal, grass
wrtr.add_summary(
sess.run(
summary_images, {
model.x:
x_test[[990, 1851, 2140, 2500, 2780, 2880, 3380, 3580]]
}), step)
else:
wrtr.add_summary(sess.run(summary_images, {model.x: x_test}), step)
wrtr.flush()
def summ_discr(step):
fetches = model.d_loss
results = map(
np.mean,
zip(*(sess.run(fetches, {
model['x']: x_test[i:j],
model['y']: y_test[i:j]
}) for i, j in partition(len(x_test), batch_size, discard=False))))
results = list(results)
if n_dis > 1: # put all losses of the discriminators in one plot
for i in range(n_dis):
d_wrtr[i].add_summary(
sess.run(summary_discr[i], dict(zip(fetches, results))),
step)
#d_wrtr[i].add_summary(sess.run(summary_discr[i], dict([(fetches[i], results[i])])), step)
d_wrtr[i].flush()
#def log(step
# , wrtr= wrtr
# , log = tf.summary.merge([tf.summary.scalar('g_loss', model.g_loss)
# , tf.summary.scalar('d_loss', tf.reduce_mean(model.d_loss))
# , tf.summary.scalar("lambda", model.lam)
# , tf.summary.image("gx", model.gx, max_outputs=5)
# , tf.summary.image('gx400', spread_image(model.gx[:400], 20,20, img_size, img_size, channel))
# #, tf.summary.scalar("AUC_dgx", model.auc_dgx)
# #, tf.summary.scalar("AUC_dx", model.auc_dx)
# , tf.summary.scalar("AUC_gx", model.auc_gx)])
# , y= y_test
# , x= x_test):
# wrtr.add_summary(sess.run(log, {model["x"]:x
# , model["y"]:y})
# , step)
# wrtr.flush()
steps_per_epoch = len(x_train) // batch_size - 1
for epoch in tqdm(range(epochs)):
for i in range(steps_per_epoch):
#sess.run(model["train_step"])
sess.run(model['d_step'])
sess.run(model['g_step'])
# tensorboard writer
#if "ucsd" in dataset:
summ(sess.run(model["step"]) // steps_per_epoch)
#else:
# log(sess.run(model["step"])//steps_per_epoch)
if n_dis > 1:
summ_discr(sess.run(model["step"]) // steps_per_epoch)
saver.save(sess, pform(path_ckpt, trial), write_meta_graph=False)