if __name__ == "__main__":
args = parse_args()
if args.cfg_file is not None:
cfg_from_file(args.cfg_file)
if args.gpu_id != -1:
cfg.GPU_ID = args.gpu_id
print('Using config:')
pprint.pprint(cfg)
now = datetime.datetime.now(dateutil.tz.tzlocal())
timestamp = now.strftime('%Y_%m_%d_%H_%M_%S')
datadir = 'Data/%s' % cfg.DATASET_NAME
dataset = TextDataset(datadir, cfg.EMBEDDING_TYPE, 1)
filename_test = '%s/test' % (datadir)
dataset.test = dataset.get_data(filename_test)
if cfg.TRAIN.FLAG:
filename_train = '%s/train' % (datadir)
dataset.train = dataset.get_data(filename_train)
ckt_logs_dir = "ckt_logs/%s/%s_%s" % (cfg.DATASET_NAME,
cfg.CONFIG_NAME, timestamp)
mkdir_p(ckt_logs_dir)
else:
s_tmp = cfg.TRAIN.PRETRAINED_MODEL
ckt_logs_dir = s_tmp[:s_tmp.find('.ckpt')]
model = CondGAN(image_shape=dataset.image_shape)
algo = CondGANTrainer(model=model,
dataset=dataset,
if __name__ == "__main__":
args = parse_args()
if args.cfg_file is not None:
cfg_from_file(args.cfg_file)
if args.gpu_id != -1:
cfg.GPU_ID = args.gpu_id
print('Using config:')
pprint.pprint(cfg)
now = datetime.datetime.now(dateutil.tz.tzlocal())
timestamp = now.strftime('%Y_%m_%d_%H_%M_%S')
# datadir = 'Data/%s' % cfg.DATASET_NAME
datadir = cfg.DATASET_NAME
dataset = TextDataset(datadir, cfg.EMBEDDING_TYPE, 4)
filename_test = datadir
# dataset.test = dataset.get_data(filename_test)
dataset.test = dataset.get_data(cfg.DATASET_NAME)
if cfg.TRAIN.FLAG:
filename_train = datadir
# dataset.train = dataset.get_data(filename_train)
dataset.train = dataset.get_data(cfg.DATASET_NAME)
ckt_logs_dir = "ckt_logs/%s/%s_%s" % \
(cfg.DATASET_NAME, cfg.CONFIG_NAME, timestamp)
mkdir_p(ckt_logs_dir)
else:
s_tmp = cfg.TRAIN.PRETRAINED_MODEL
ckt_logs_dir = s_tmp[:s_tmp.find('.ckpt')]
model = CondGAN(lr_imsize=int(dataset.image_shape[0] /
return args
if __name__ == "__main__":
args = parse_args()
if args.cfg_file is not None:
cfg_from_file(args.cfg_file)
if args.gpu_id != -1:
cfg.GPU_ID = args.gpu_id
print('Using config:')
pprint.pprint(cfg)
now = datetime.datetime.now(dateutil.tz.tzlocal())
timestamp = now.strftime('%Y_%m_%d_%H_%M_%S')
datadir = 'Data/%s' % cfg.DATASET_NAME
dataset = TextDataset(datadir, cfg.EMBEDDING_TYPE, 1)
filename_test = '%s/test' % (datadir)
dataset.test = dataset.get_data(filename_test)
if cfg.TRAIN.FLAG:
filename_train = '%s/train' % (datadir)
dataset.train = dataset.get_data(filename_train)
ckt_logs_dir = "ckt_logs/%s/%s_%s" % \
(cfg.DATASET_NAME, cfg.CONFIG_NAME, timestamp)
mkdir_p(ckt_logs_dir)
else:
s_tmp = cfg.TRAIN.PRETRAINED_MODEL
ckt_logs_dir = s_tmp[:s_tmp.find('.ckpt')]
model = CondGAN(
image_shape=dataset.image_shape
cfg_from_file(args.cfg_file)
if args.gpu_id != -1:
cfg.GPU_ID = args.gpu_id
# Load text embeddings generated from the encoder
cap_path = cfg.TEST.CAPTION_PATH
t_file = torchfile.load(cap_path)
captions_list = t_file.raw_txt
print(t_file.fea_txt)
embeddings = np.concatenate(t_file.fea_txt, axis=0)
num_embeddings = len(captions_list)
print('Successfully load sentences from: ', cap_path)
print('Total number of sentences:', num_embeddings)
print('num_embeddings:', num_embeddings, embeddings.shape)
datadir = 'Data/%s' % cfg.DATASET_NAME
dataset = TextDataset(datadir, cfg.EMBEDDING_TYPE, 1)
# path to save generated samples
save_dir = cap_path[:cap_path.find('.t7')]
if num_embeddings > 0:
batch_size = np.minimum(num_embeddings, cfg.TEST.BATCH_SIZE)
# Build StackGAN and load the model
config = tf.ConfigProto(allow_soft_placement=True)
with tf.Session(config=config) as sess:
with tf.device("/gpu:%d" % cfg.GPU_ID):
embeddings_holder, fake_images_opt, fake_images_2_opt =\
build_model(sess, dataset.image_shape, embeddings.shape[-1], batch_size)
count = 0
while count < num_embeddings:
import argparse
import pprint
from misc.datasets import TextDataset
from model import CondGAN
from trainer import CondGANTrainer
from misc.get_configs import parse_args
from misc.utils import mkdir_p
if __name__ == "__main__":
args = parse_args()
print(args)
now = datetime.datetime.now()
timestamp = now.strftime('%Y_%m_%d_%H_%M_%S')
dataset = TextDataset(datadir='datasets/' + args.dataset + '/')
print("Dataset created!")
dataset.train = dataset.get_data()
model = CondGAN(args, image_shape=dataset.image_shape)
print("model created!")
# if args.for_training:
ckt_logs_dir = "ckt_logs/%s" % \
("{}_logs".format(args.dataset))
res_dir = "retrieved_res/%s" % \
("{}_res".format(args.dataset))
mkdir_p(ckt_logs_dir)
mkdir_p(res_dir)
with open(ckt_logs_dir + '/args.txt', 'w') as fid:
if __name__ == "__main__":
args = parse_args()
if args.cfg_file is not None:
cfg_from_file(args.cfg_file)
if args.gpu_id != -1:
cfg.GPU_ID = args.gpu_id
print('Using config:')
pprint.pprint(cfg)
now = datetime.datetime.now(dateutil.tz.tzlocal())
timestamp = now.strftime('%Y_%m_%d_%H_%M_%S')
# datadir = 'Data/%s' % cfg.DATASET_NAME
datadir = cfg.DATASET_NAME
dataset = TextDataset(datadir, cfg.EMBEDDING_TYPE, 1)
filename_test = datadir
# dataset.test = dataset.get_data(filename_test,aug_flag=False)
if cfg.TRAIN.FLAG:
filename_train = datadir
dataset.train = dataset.get_data(filename_train, aug_flag=False)
ckt_logs_dir = "ckt_logs/%s/%s_%s" % \
(cfg.DATASET_NAME, cfg.CONFIG_NAME, timestamp)
mkdir_p(ckt_logs_dir)
else:
s_tmp = cfg.TRAIN.PRETRAINED_MODEL
ckt_logs_dir = s_tmp[:s_tmp.find('.ckpt')]
model = CondGAN(image_shape=dataset.image_shape)
