def unpack_bz2(src_path):
data = bz2.BZ2File(src_path).read()
dst_path = src_path[:-4]
with open(dst_path, 'wb') as fp:
fp.write(data)
return dst_path
if __name__ == "__main__":
"""
Extracts and aligns all faces from images using DLib and a function from original FFHQ dataset preparation step
python align_images.py /raw_images /aligned_images
"""
landmarks_model_path = unpack_bz2(
tf.keras.utils.get_file('shape_predictor_68_face_landmarks.dat.bz2',
LANDMARKS_MODEL_URL,
cache_subdir='temp'))
RAW_IMAGES_DIR = sys.argv[1]
ALIGNED_IMAGES_DIR = sys.argv[2]
landmarks_detector = LandmarksDetector(landmarks_model_path)
for img_name in os.listdir(RAW_IMAGES_DIR):
raw_img_path = os.path.join(RAW_IMAGES_DIR, img_name)
for i, face_landmarks in enumerate(
landmarks_detector.get_landmarks(raw_img_path), start=1):
face_img_name = '%s_%02d.png' % (os.path.splitext(img_name)[0], i)
aligned_face_path = os.path.join(ALIGNED_IMAGES_DIR, face_img_name)
image_align(raw_img_path, aligned_face_path, face_landmarks)
for img_name in os.listdir(RAW_IMAGES_DIR):
print('Aligning %s ...' % img_name)
try:
raw_img_path = os.path.join(RAW_IMAGES_DIR, img_name)
fn = face_img_name = '%s_%02d.png' % (
os.path.splitext(img_name)[0], 1)
if os.path.isfile(fn):
continue
print('Getting landmarks...')
for i, face_landmarks in enumerate(
landmarks_detector.get_landmarks(raw_img_path), start=1):
try:
print('Starting face alignment...')
face_img_name = '%s_%02d.png' % (
os.path.splitext(img_name)[0], i)
aligned_face_path = os.path.join(ALIGNED_IMAGES_DIR,
face_img_name)
image_align(raw_img_path,
aligned_face_path,
face_landmarks,
output_size=args.output_size,
x_scale=args.x_scale,
y_scale=args.y_scale,
em_scale=args.em_scale,
alpha=args.use_alpha)
print('Wrote result %s' % aligned_face_path)
except:
print("Exception in face alignment!")
except:
print("Exception in landmark detection!")
def align_image(input_path, output_path):
landmarks_model_path = unpack_bz2(get_file('shape_predictor_68_face_landmarks.dat.bz2',
LANDMARKS_MODEL_URL, cache_subdir='temp'))
landmarks_detector = LandmarksDetector(landmarks_model_path)
for i, face_landmarks in enumerate(landmarks_detector.get_landmarks(input_path), start=1):
image_align(input_path, output_path, face_landmarks)
id_list = [x.split(' ')[1].rstrip("\n") for x in id_lines]
# top n-most frequent id
ctr = collections.Counter(id_list)
top_id_list = [x[0] for x in ctr.most_common(3300)]
# data list
data_list = [(fn, ld, id) for fn, ld, id in zip(fn_list, ld_list, id_list)
if id in top_id_list]
for i, (fn, ld, id) in enumerate(data_list):
# 4-point landmarks (left eye, right eye, left mouth, right mouth)
face_landmarks = [[ld[0], ld[1]], [ld[2], ld[3]], [ld[6], ld[7]],
[ld[8], ld[9]]]
# FFHQ align
image = cv2.imread(os.path.join(img_dir, fn))
aligned_image = image_align(image,
face_landmarks,
output_size=img_size,
transform_size=img_size * 4,
enable_padding=True)
# save
save_dir = os.path.join(save_base_dir, 'sort_by_id_aligned', id)
if not os.path.exists(save_dir):
os.makedirs(save_dir)
cv2.imwrite(os.path.join(save_dir, '{}.png'.format(i)), aligned_image)
print('[{}/{}] save {} for id: {}'.format(i + 1, len(data_list), fn, id))
print('done')