def test():
args = cmd.args()
args.images_dir_test = args.images_dir_train
args.pairs_file_test = 'data/market-re-id-pairs.csv'
pairs_for_each = 2
train_file_name = 'train.txt'
store_train_images = True
generated_as_separate = False
df_keypoints = pd.read_csv(args.annotations_file_train, sep=':')
df = filter_not_valid(df_keypoints)
print('Compute pair for train re-id...')
pairs_df_train = make_pairs(df, pairs_for_each)
print('Number of pairs: %s' % len(pairs_df_train))
pairs_df_train.to_csv('data/market-re-id-pairs.csv', index=False)
dataset = PoseHMDataset(test_phase=True, **vars(args))
generator = make_generator(args.image_size, args.use_input_pose,
args.warp_skip, args.disc_type, args.warp_agg,
args.use_bg, args.pose_rep_type)
assert (args.generator_checkpoint is not None)
generator.load_weights(args.generator_checkpoint)
print("Generate images...")
generate_images(dataset,
generator,
args.use_input_pose,
args.generated_images_dir,
store_train_images=store_train_images)
print("Creating train file...")
create_train_file(args.generated_images_dir, train_file_name,
generated_as_separate)
def main():
args = cmd.args()
date_str = '{}'.format(
datetime.datetime.today().strftime('%Y-%m-%d_%H-%M-%S'))
sys.stdout = Logger(
osp.join(args.output_dir, 'log_{}.txt'.format(date_str)))
# save opts
with open(osp.join(args.output_dir, 'args_{}.json'.format(date_str)),
'w') as fp:
json.dump(vars(args), fp, indent=1)
generator = make_generator(args.image_size, args.use_input_pose,
args.warp_skip, args.disc_type, args.warp_agg,
args.debug)
if args.generator_checkpoint is not None:
generator.load_weights(args.generator_checkpoint)
discriminator = make_discriminator(args.image_size, args.use_input_pose,
args.warp_skip, args.disc_type,
args.warp_agg)
if args.discriminator_checkpoint is not None:
discriminator.load_weights(args.discriminator_checkpoint)
dataset = PoseHMDataset(test_phase=False, **vars(args))
gan = CGAN(generator, discriminator, **vars(args))
trainer = Trainer(dataset, gan, **vars(args))
trainer.train()
def test():
args = cmd.args()
print("Loading images...")
generated_images = load_generated_images(args.generated_images_dir)
print("Compute inception score...")
inception_score = get_inception_score(generated_images)
print("Inception score %s" % inception_score[0])
return inception_score
def test():
args = cmd.args()
args.images_dir_test = args.images_dir_train
args.pairs_file_test = 'data/market-re-id-pairs.csv'
dataset = PoseHMDataset(test_phase=True, **vars(args))
generator = make_generator(args.image_size, args.use_input_pose,
args.warp_skip, args.disc_type, args.warp_agg)
assert (args.generator_checkpoint is not None)
generator.load_weights(args.generator_checkpoint)
print("Generate images...")
generate_images(dataset, generator, args.use_input_pose,
args.generated_images_dir)
def main():
args = cmd.args()
generator = make_generator(args.image_size, args.use_input_pose, args.warp_skip, args.disc_type, args.warp_agg)
if args.generator_checkpoint is not None:
generator.load_weights(args.generator_checkpoint)
discriminator = make_discriminator(args.image_size, args.use_input_pose, args.warp_skip, args.disc_type, args.warp_agg)
if args.discriminator_checkpoint is not None:
discriminator.load_weights(args.discriminator_checkpoint)
dataset = PoseHMDataset(test_phase=False, **vars(args))
gan = CGAN(generator, discriminator, **vars(args))
trainer = Trainer(dataset, gan, **vars(args))
trainer.train()
def test():
args = cmd.args()
if args.load_generated_images:
print ("Loading images...")
input_images, target_images, generated_images, names = load_generated_images(args.generated_images_dir)
else:
print ("Generate images...")
from keras import backend as K
if args.use_dropout_test:
K.set_learning_phase(1)
dataset = PoseHMDataset(test_phase=True, **vars(args))
generator = make_generator(args.image_size, args.use_input_pose, args.warp_skip, args.disc_type, args.warp_agg,
args.use_bg, args.pose_rep_type)
assert (args.generator_checkpoint is not None)
generator.load_weights(args.generator_checkpoint)
input_images, target_images, generated_images, names = generate_images(dataset, generator, args.use_input_pose)
print ("Save images to %s..." % (args.generated_images_dir, ))
save_images(input_images, target_images, generated_images, names,
args.generated_images_dir)
print ("Compute inception score...")
inception_score = get_inception_score(generated_images)
print ("Inception score %s" % inception_score[0])
print ("Compute structured similarity score (SSIM)...")
structured_score = ssim_score(generated_images, target_images)
print ("SSIM score %s" % structured_score)
print ("Compute l1 score...")
norm_score = l1_score(generated_images, target_images)
print ("L1 score %s" % norm_score)
print ("Compute masked inception score...")
generated_images_masked = create_masked_image(names, generated_images, args.annotations_file_test)
reference_images_masked = create_masked_image(names, target_images, args.annotations_file_test)
inception_score_masked = get_inception_score(generated_images_masked)
print ("Inception score masked %s" % inception_score_masked[0])
print ("Compute masked SSIM...")
structured_score_masked = ssim_score(generated_images_masked, reference_images_masked)
print ("SSIM score masked %s" % structured_score_masked)
print ("Inception score = %s, masked = %s; SSIM score = %s, masked = %s; l1 score = %s" %
(inception_score, inception_score_masked, structured_score, structured_score_masked, norm_score))
def test():
args = cmd.args()
if args.load_generated_images:
print("Loading images...")
input_images, target_images, generated_images, names = load_generated_images(
args.generated_images_dir)
else:
print("Generate images...")
from keras import backend as K
if args.use_dropout_test:
K.set_learning_phase(1)
dataset = PoseHMDataset(test_phase=True, **vars(args))
generator = make_generator(args.image_size, args.use_input_pose,
args.warp_skip, args.disc_type,
args.warp_agg)
assert (args.generator_checkpoint is not None)
generator.load_weights(args.generator_checkpoint)
input_images, target_images, generated_images, names = generate_images(
dataset, generator, args.use_input_pose)
print("Save images to %s..." % (args.generated_images_dir, ))
save_images(input_images, target_images, generated_images, names,
args.generated_images_dir)
if args.is_test_real_data:
generated_images = target_images
print('Compute FID score')
fid = FID_score()
fid_score = fid.calculate_fid_images(generated_images, target_images)
print("FID score %s" % fid_score)
print("Compute inception score...")
inception_score = get_inception_score(generated_images)
print("Inception score %s" % inception_score[0])
print("Compute structured similarity score (SSIM)...")
structured_score = ssim_score(generated_images, target_images)
print("SSIM score %s" % structured_score)
print("Compute l1 score...")
norm_score = l1_score(generated_images, target_images)
print("L1 score %s" % norm_score)
def main():
args = cmd.args()
generator = make_generator(args.image_size, args.use_input_pose,
args.warp_agg, args.num_landmarks,
args.num_mask)
generator.summary()
if args.generator_checkpoint is not None:
generator.load_weights(args.generator_checkpoint, by_name=True)
discriminator = make_discriminator(args.image_size, args.use_input_pose,
args.num_landmarks, args.num_mask)
if args.discriminator_checkpoint is not None:
discriminator.load_weights(args.discriminator_checkpoint)
dataset = PoseHMDataset(test_phase=False, **vars(args))
gan = CGAN(generator, discriminator, **vars(args))
trainer = Trainer(dataset, gan, **vars(args))
trainer.train()
import pandas as pd
from cmd import args
import pose_transform
import pose_utils
from itertools import permutations
args = args()
def filter_not_valid(df_keypoints):
def check_valid(x):
kp_array = pose_utils.load_pose_cords_from_strings(
x['keypoints_y'], x['keypoints_x'])
distractor = x['name'].startswith('-1') or x['name'].startswith('0000')
return pose_transform.check_valid(kp_array) and not distractor
return df_keypoints[df_keypoints.apply(check_valid, axis=1)].copy()
def make_pairs(df):
persons = df.apply(lambda x: '_'.join(x['name'].split('_')[0:1]), axis=1)
df['person'] = persons
fr, to = [], []
for person in pd.unique(persons):
pairs = zip(*list(permutations(df[df['person'] == person]['name'], 2)))
if len(pairs) != 0:
fr += list(pairs[0])
to += list(pairs[1])
pair_df = pd.DataFrame(index=range(len(fr)))
pair_df['from'] = fr
pair_df['to'] = to
def test():
args = cmd.args()
if args.load_generated_images:
print("Loading images...")
input_images, target_images, generated_images, names = load_generated_images(
args.generated_images_dir)
else:
print("Generate images...")
from keras import backend as K
if args.use_dropout_test:
K.set_learning_phase(1)
dataset = PoseHMDataset(test_phase=True, **vars(args))
generator = make_generator(args.image_size, args.use_input_pose,
args.warp_agg, args.num_landmarks,
args.num_mask)
assert (args.generator_checkpoint is not None)
generator.load_weights(args.generator_checkpoint)
input_images, pose_inp_array, out_pose, pose_out_array, inp_pose, target_images, generated_images, names = generate_images(
dataset, generator, args.use_input_pose)
print("Save images to %s..." % (args.generated_images_dir, ))
save_images(input_images, pose_inp_array, out_pose, pose_out_array,
inp_pose, target_images, generated_images, names,
args.generated_images_dir)
print("Compute inception score...")
inception_score = get_inception_score(generated_images)
print("Inception score %s" % inception_score[0])
# print ("Compute Frechet distance...")
# fid.create_inception_graph('/tmp/imagenet/classify_image_graph_def.pb') # load the graph into the current TF graph
# with tf.Session() as sess:
# sess.run(tf.global_variables_initializer())
# mu_gen, sigma_gen = fid.calculate_activation_statistics(generated_images, sess, batch_size=100)
# mu_real, sigma_real = fid.calculate_activation_statistics(target_images, sess, batch_size=100)
#
# fid_value = fid.calculate_frechet_distance(mu_gen, sigma_gen, mu_real, sigma_real)
# print ("Frechet distance %s" % fid_value)
print("Compute structured similarity score (SSIM)...")
structured_score = ssim_score(generated_images, target_images)
print("SSIM score %s" % structured_score)
print("Compute l1 score...")
norm_score = l1_score(generated_images, target_images)
print("L1 score %s" % norm_score)
print("Compute masked inception score...")
generated_images_masked = create_masked_image(names, generated_images,
args.annotations_file_test)
reference_images_masked = create_masked_image(names, target_images,
args.annotations_file_test)
inception_score_masked = get_inception_score(generated_images_masked)
print("Inception score masked %s" % inception_score_masked[0])
# print ("Compute masked Frechet distance...")
# fid.create_inception_graph('/tmp/imagenet/classify_image_graph_def.pb') # load the graph into the current TF graph
# with tf.Session() as sess:
# sess.run(tf.global_variables_initializer())
# mu_gen, sigma_gen = fid.calculate_activation_statistics(generated_images_masked, sess, batch_size=100)
# mu_real, sigma_real = fid.calculate_activation_statistics(reference_images_masked, sess, batch_size=100)
#
# fid_value = fid.calculate_frechet_distance(mu_gen, sigma_gen, mu_real, sigma_real)
# print("Frechet distance masked %s" % fid_value)
print("Compute masked SSIM...")
structured_score_masked = ssim_score(generated_images_masked,
reference_images_masked)
print("SSIM score masked %s" % structured_score_masked)
print(
"Inception score = %s, masked = %s; SSIM score = %s, masked = %s; l1 score = %s"
% (inception_score, inception_score_masked, structured_score,
structured_score_masked, norm_score))
