def __init__(self):
# setting output file
self._OUTPUT = filesystem.mkdir('../_outputs/')
self._DATASET = '../_datasets'
# logger config
self._LOG_DATE = True
self._LOG_SYS = False
self._LOG_TRAIN = True
self._LOG_TEST = True
self._LOG_VAL = True
self._LOG_NET = True
self._LOG_WARN = True
self._LOG_INFO = True
self._LOG_ERR = True
# compile config - processing *.py files
self._COMPILE_DIR_BIN = '../_bin' # output dir of binary file
self._COMPILE_DIR_SRC = '../_src' # output dir of code source
self._COMPILE_EXCLUDE_ROOT = ['_', '.git', '.vscode'] # skip folders
self._COMPILE_EXCLUDE_FILE = ['compile.py'] # skip files
# SUMMARY SETTING
self._SUMMARY_GRAD_STAT = False
self._SUMMARY_GRAD_HIST = False
self._SUMMARY_WEIGHT_STAT = False
self._SUMMARY_WEIGHT_HIST = False
def test(self):
"""
"""
# save current context
self._enter_('test')
# create a folder to save
test_dir = filesystem.mkdir(self.config.output_dir + '/test/')
# get data pipeline
data, label, path = loads(self.config)
# get network
logit, net = self._net(data)
loss, mae, rmse = self._loss(logit, label)
# prepare
total_num = self.data.total_num
batchsize = self.data.batchsize
num_iter = int(total_num / batchsize)
info = string.concat(batchsize, [path, label, logit * self.data.range])
mean_loss, mean_mae, mean_rmse = 0, 0, 0
# get saver
saver = tf.train.Saver()
with tf.Session() as sess:
# get latest checkpoint
global_step = self.snapshot.restore(sess, saver)
with open(test_dir + '%s.txt' % global_step, 'wb') as fw:
with context.QueueContext(sess):
for _ in range(num_iter):
# running session to acuqire value
_loss, _mae, _rmse, _info = sess.run(
[loss, mae, rmse, info])
mean_loss += _loss
mean_mae += _mae
mean_rmse += _rmse
# save tensor info to text file
[fw.write(_line + b'\r\n') for _line in _info]
# statistic
mean_loss = 1.0 * mean_loss / num_iter
mean_mae = 1.0 * mean_mae / num_iter
mean_rmse = 1.0 * mean_rmse / num_iter
# display results on screen
keys = ['total sample', 'num batch', 'loss', 'mae', 'rmse']
vals = [total_num, num_iter, mean_loss, mean_mae, mean_rmse]
logger.test(logger.iters(int(global_step), keys, vals))
# write to summary
self.summary.adds(global_step=global_step,
tags=['test/loss', 'test/mae', 'test/rmse'],
values=[mean_loss, mean_mae, mean_rmse])
self._exit_()
return mean_mae
def test(self):
""" we need acquire threshold from validation first """
with tf.Graph().as_default():
self._enter_('val')
val_dir = filesystem.mkdir(self.config.output_dir + '/val/')
self._val_or_test(val_dir)
self._exit_()
with tf.Graph().as_default():
self._enter_('test')
test_dir = filesystem.mkdir(self.config.output_dir + '/test/')
step = self._val_or_test(test_dir)
val_err, val_thed, test_err = similarity.get_all_result(
self.val_x, self.val_y, self.val_l, self.test_x, self.test_y,
self.test_l, False)
keys = ['val_error', 'thred', 'test_error']
vals = [val_err, val_thed, test_err]
logger.test(logger.iters(int(step) - 1, keys, vals))
self._exit_()
def _initialize(self):
pid = datetime.strftime(datetime.now(), '%y%m%d%H%M%S')
# 1. setting output dir
if self.config.output_dir is None:
self.config.output_dir = filesystem.mkdir(
env._OUTPUT + self.config.name + '.' +
self.config.target + '.' + pid)
# 2. setting logger location
logger.init(self.config.name + '.' + pid, self.config.output_dir)
logger.info('Initilized logger successful.')
logger.info('Current model in %s' % self.config.output_dir)
def test(self):
"""
"""
# save current context
self._enter_('test')
# create a folder to save
test_dir = filesystem.mkdir(self.config.output_dir + '/test/')
# get data pipeline
data, label, path = loads(self.config)
# total_num
total_num = self.data.total_num
batchsize = self.data.batchsize
# network
logit, net = self._net(data)
loss, error, pred = self._loss(logit, label)
# prepare
info = string.concat(batchsize, [path, label, pred])
num_iter = int(total_num / batchsize)
mean_err, mean_loss = 0, 0
# get saver
saver = tf.train.Saver()
with context.DefaultSession() as sess:
global_step = self.snapshot.restore(sess, saver)
with open(test_dir + '%s.txt' % global_step, 'wb') as fw:
with context.QueueContext(sess):
for _ in range(num_iter):
_loss, _err, _info = sess.run([loss, error, info])
mean_loss += _loss
mean_err += _err
[fw.write(_line + b'\r\n') for _line in _info]
# statistic
mean_loss = 1.0 * mean_loss / num_iter
mean_err = 1.0 * mean_err / num_iter
# display results on screen
keys = ['total sample', 'num batch', 'loss', 'error']
vals = [total_num, num_iter, mean_loss, mean_err]
logger.test(logger.iters(int(global_step), keys, vals))
# write to summary
self.summary.adds(global_step=global_step,
tags=['test/error', 'test/loss'],
values=[mean_err, mean_loss])
self._exit_()
return mean_err
def test(self):
""" random test a group of image
"""
self._enter_('test')
test_dir = filesystem.mkdir(self.config['output_dir'] + '/test/')
# add conditional gan
y = [[i for i in range(10)] for i in range(10)]
logit_G, net_G = self._generator(y, 'test')
saver = tf.train.Saver(name='restore_all')
with tf.Session() as sess:
step = self.snapshot.restore(sess, saver)
imgs = sess.run(logit_G)
image.save_multi_to_one(imgs, [10, 10],
path.join_step(test_dir, step, 'png'))
self._exit_()
def _val_or_test(self, dstdir):
""" COMMON FOR TRAIN AND VAL """
# considering output train image
data, info, path = loads(self.config)
c1_real, p1_real, c2_real, p2_real = tf.unstack(data, axis=1)
c1_path, p1_path, c2_path, p2_path = tf.unstack(path, axis=1)
label, cond = tf.unstack(info, axis=1)
# encode image to a vector
c1_mu, c1_sigma, feat_c1 = self._encoder(c1_real)
p2_mu, p2_sigma, feat_p2 = self._encoder(p2_real, True)
c1_z = c1_mu + c1_sigma * tf.random_normal(tf.shape(c1_mu))
c1_z = self._generator(c1_z, cond)
c1_fake = tf.clip_by_value(c1_z, 1e-8, 1 - 1e-8)
p2_z = p2_mu + p2_sigma * tf.random_normal(tf.shape(p2_mu))
p2_z = self._generator(p2_z, cond, True)
p2_fake = tf.clip_by_value(p2_z, 1e-8, 1 - 1e-8)
R_loss, loss = self._loss_metric(feat_c1, feat_p2, None)
saver = tf.train.Saver()
c1_zs, p2_zs = 0, 0
with context.DefaultSession() as sess:
step = self.snapshot.restore(sess, saver)
filesystem.mkdir(dstdir + '/' + step + '_c1')
filesystem.mkdir(dstdir + '/' + step + '_p2')
info = string.concat(
self.data.batchsize,
[c1_path, p1_path, c2_path, p2_path, label, loss])
output = [
c1_fake, p2_fake, c1_path, p2_path, c1_real, c2_real, p1_real,
p2_real, info, feat_c1, feat_p2, label
]
fw = open(dstdir + '%s.txt' % step, 'wb')
with context.QueueContext(sess):
for i in range(self.epoch_iter):
_c1, _p2, _c1p, _p2p, _c1r, _c2r, _p1r, _p2r, _info, _x, _y, _label = sess.run(
output)
self._write_feat_to_npy(i, _x, _y, _label)
[fw.write(_line + b'\r\n') for _line in _info]
if self.is_save_all_images:
image.save_multi(dstdir + '/' + step + '_c1', _c1,
_c1p)
image.save_multi(dstdir + '/' + step + '_p2', _p2,
_p2p)
if self.is_save_batch_images:
image.save_batchs_to_one(
imgs_list=[_c1, _p2, _c1r, _c2r, _p1r, _p2r],
batchsize=self.data.batchsize,
dst=dstdir,
step=step,
name_list=[
'_c1', '_p2', '_c1r', '_c2r', '_p1r', '_p2r'
])
if self.is_save_feats:
c1_zs = _x if type(c1_zs) == int else np.row_stack(
(c1_zs, _x))
p2_zs = _y if type(p2_zs) == int else np.row_stack(
(p2_zs, _y))
fw.close()
if self.is_save_feats:
np.save(dstdir + '/' + step + '_c1.npy', c1_zs)
np.save(dstdir + '/' + step + '_p2.npy', p2_zs)
return step