def _demo():
# Load checkpoint
if not tf.gfile.IsDirectory(FLAGS.checkpoint_dir):
raise FileNotFoundError("Could not find folder `%s'" % (FLAGS.checkpoint_dir,))
# Setup global tensorflow state
sess, summary_writer = setup_tensorflow()
# Prepare directories
filenames = prepare_dirs(delete_train_dir=False)
# Setup async input queues
features, labels = srez_input.setup_inputs(sess, filenames)
# Create and initialize model
[gene_minput, gene_moutput,
gene_output, gene_var_list,
disc_real_output, disc_fake_output, disc_var_list] = \
srez_model.create_model(sess, features, labels)
# Restore variables from checkpoint
saver = tf.train.Saver()
filename = 'checkpoint_new.txt'
filename = os.path.join(FLAGS.checkpoint_dir, filename)
saver.restore(sess, filename)
# Execute demo
srez_demo.demo1(sess)
def _demo():
# Load checkpoint
if not tf.gfile.IsDirectory(FLAGS.checkpoint_dir):
raise FileNotFoundError("Could not find folder `%s'" % (FLAGS.checkpoint_dir,))
# Setup global tensorflow state
sess, summary_writer = setup_tensorflow()
# Prepare directories
filenames = prepare_dirs(delete_train_dir=False)
# Setup async input queues
features, labels = srez_input.setup_inputs(sess, filenames)
# Create and initialize model
[gene_minput, gene_moutput,
gene_output, gene_var_list,
disc_real_output, disc_fake_output, disc_var_list] = \
srez_model.create_model(sess, features, labels)
# Restore variables from checkpoint
saver = tf.train.Saver()
filename = 'checkpoint_new.txt'
filename = os.path.join(FLAGS.checkpoint_dir, filename)
saver.restore(sess, filename)
# Execute demo
srez_demo.demo1(sess)
def main(argv=None):
# Training or showing off?
if tf.__version__ != '1.0.0':
print("please use tensorflow version 1.0.0")
exit(0)
if FLAGS.run == 'demo':
#_demo()
srez_demo.demo1()
elif FLAGS.run == 'train':
_train()
