path_ckpt = "../trial/ckpt/kudo396"
path_emb = "../data/stance_emb.npy"
path_emb_sp = "../data/stance_emb_sample.npy"
path_vocab = "../trial/data/vocab.model"
path_data = "../data/stance.npz"
from model import tf, vAe
from util import partial
from util_io import load_txt
from util_np import np, partition, vpack
import util_sp as sp
from util_np import vpack
# load test sentences
text = np.load(path_data)['text']
# load sentencepiece model
vocab = sp.load_spm(path_vocab)
# Load the model
model = vAe('infer')
# Restore the session
sess = tf.InteractiveSession()
tf.train.Saver().restore(sess, path_ckpt)
################################
# deterministic representation #
################################
# encode text with sentence piece model
from util_sp import load_spm, encode_capped, encode_capped_sample_pair
from util_tf import tf, pipe
config = load_json(A.config)
P = Record(config['paths'])
C = Record(config['model'])
T = Record(config['train'])
tf.set_random_seed(A.seed)
#############
# load data #
#############
vocab = load_spm(P.vocab)
valid = np.load(P.valid)
def batch(size=T.batch_train,
path=P.train,
vocab=vocab,
seed=A.seed,
kudo=A.sample,
max_len=T.max_len):
pac = lambda arrs: vpack(arrs, (size, max(map(len, arrs))), eos, np.int32)
enc = encode_capped_sample_pair if kudo else encode_capped
raw = tuple(load_txt(path))
eos = vocab.eos_id()
bat = []
for i in sample(len(raw), seed):
if size == len(bat):
from trial import config as C, paths as P, train as T
from util import partial, comp, select
from util_io import pform, load_txt, save_txt
from util_np import np, partition, batch_sample
from util_sp import load_spm, encode, decode
from util_tf import tf, pipe
tf.set_random_seed(C.seed)
C.trial = 'm4_'
#############
# load data #
#############
# valid_en, train_en = np.load(pform(P.data, "valid_en.npy")), np.load(pform(P.data, "train_en.npy"))
valid_nl, train_nl = np.load(pform(P.data, "valid_nl.npy")), np.load(pform(P.data, "train_nl.npy"))
# valid_de, train_de = np.load(pform(P.data, "valid_de.npy")), np.load(pform(P.data, "train_de.npy"))
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"))
train_nl = train_nl[:2**17].copy()
train_da = train_da[:2**17].copy()
data_index = 1, 3
data_valid = valid_nl, valid_da
data_train = train_nl, train_da
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)
from tqdm import tqdm
from trial import config as C, paths as P, train as T
from util import partial, comp, select
from util_io import pform, load_txt, save_txt
from util_np import np, partition, batch_sample
from util_sp import load_spm, encode, decode
from util_tf import tf, pipe
tf.set_random_seed(C.seed)
C.trial = 'm1_'
#############
# load data #
#############
valid_en, train_en = np.load(pform(P.data, "valid_en.npy")), np.load(pform(P.data, "train_en.npy"))
# valid_nl, train_nl = np.load(pform(P.data, "valid_nl.npy")), np.load(pform(P.data, "train_nl.npy"))
valid_de, train_de = np.load(pform(P.data, "valid_de.npy")), np.load(pform(P.data, "train_de.npy"))
# 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))
path_ckpt = "../trial/ckpt/kudo396"
path_emb = "../data/test_data_emb.npy"
path_emb_sp = "../data/test_data_emb_sample.npy"
path_vocab = "../trial/data/vocab.model"
path_data = "../data/test_data.npz"
from model import tf, vAe, encode, decode
from util import partial
from util_io import load_txt
from util_np import np, partition, vpack
import util_sp as sp
from util_np import vpack
# load test sentences
text = np.load(path_data)["posts"]
# load sentencepiece model
vocab = sp.load_spm(path_vocab)
# Load the model
model = vAe('infer')
# Restore the session
sess = tf.InteractiveSession()
tf.train.Saver().restore(sess, path_ckpt)
################################
# deterministic representation #
################################
# encode text with sentence piece model
path_csv = "../docs/results_iac/clustering.csv"
path_emb = "../data/test_data_emb.npy"
path_emb_sp = "../data/test_data_emb_sample.npy"
from model import tf, vAe, encode, decode
from util import partial
from util_io import load_txt, save_txt
from util_np import np, partition, vpack
from util_np import vpack
import pandas as pd
import util_sp as sp
# load data
df = pd.read_csv(path_csv)
emb = np.load(path_emb)
emb_sp = np.load(path_emb_sp)
# load sentencepiece model
vocab = sp.load_spm(path_vocab)
# Load the model
model = vAe('infer')
# Restore the session
sess = tf.InteractiveSession()
tf.train.Saver().restore(sess, path_ckpt)
###########################
# generate from centroids #
###########################
from model import Transformer
from os.path import expanduser, join
from tqdm import tqdm
from util import PointedIndex
from util_io import decode
from util_np import np, permute
from util_tf import tf, batch
logdir = expanduser("~/cache/tensorboard-logdir/explicharr")
tf.set_random_seed(0)
###############
# preparation #
###############
src_train = np.load("trial/data/train_src.npy")
tgt_train = np.load("trial/data/train_tgt.npy")
src_valid = np.load("trial/data/valid_src.npy")
tgt_valid = np.load("trial/data/valid_tgt.npy")
assert src_train.shape[1] <= len_cap
assert tgt_train.shape[1] <= len_cap
assert src_valid.shape[1] <= len_cap
assert tgt_valid.shape[1] <= len_cap
epoch = len(src_train) // batch_size
# # for profiling
# from util_tf import profile
# m = Transformer.new().data()
# forcing = m.forcing(trainable= False)
# autoreg = m.autoreg(trainable= False)
# feed = {m.src_: src_train[:batch_size], m.tgt_: tgt_train[:batch_size]}
from model import Transformer
from os.path import expanduser, join
from tqdm import tqdm
from util import comp
from util_io import path, save
from util_np import np, vpack, c2r
from util_tf import tf, batch
logdir = expanduser("~/cache/tensorboard-logdir/i-synth")
tf.set_random_seed(0)
###############
# preparation #
###############
index = np.load("trial/data/index.npy").item()
texts = np.load("trial/data/texts.npy")
names = np.load("trial/data/names.npy")
epoch, split = divmod(len(texts), batch_size)
print("{} batches of {} training instances, {} validation".format(
epoch, batch_size, split))
def load_batch(names, load=comp(np.load, "trial/data/grams/{}.npy".format)):
names = names.astype(np.str)
x = vpack(map(load, names), complex('(nan+nanj)'), 1, 1)
# x = vpack(map(comp(load, path), names), complex('(nan+nanj)'), 1, 1)
x[:, 0] = 0j
x = c2r(x)
_, t, d = x.shape
assert t <= len_cap
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)