def main(mode, face_id_model_root, id_features_dir, font_path):
print('Loading models...')
det_models = load_detect_faces_models()
face_id_model = load_face_id_model(model_root=face_id_model_root)
id_npy = load_id_files(id_features_dir)
crop_size = 112
max_size = 1024
reference = get_reference_facial_points(default_square=True)
font = ImageFont.FreeTypeFont(font=font_path, size=24)
print('Starting image processing...')
if mode == Mode.DEMO:
demo(det_models=det_models,
face_id_model=face_id_model,
reference=reference,
crop_size=crop_size,
id_npy=id_npy,
max_size=max_size,
font=font)
elif mode == Mode.FILE:
process_files(input_dir=STREAM_DIR,
output_dir=RESULT_DIR,
det_models=det_models,
face_id_model=face_id_model,
reference=reference,
crop_size=crop_size,
id_npy=id_npy,
max_size=max_size,
font=font)
else:
raise ValueError('Invalid mode: {}'.format(mode))
def detect_one_face_align(img):
crop_size = 112
scale = crop_size / 112.
reference = get_reference_facial_points(default_square=True) * scale
#img = Image.open(os.path.join(image_path))
landmarks = []
bounding_boxes = []
try:
bounding_boxes, landmarks = detect_faces(img)
except Exception as e:
print(e)
if len(
landmarks
) == 0: # If the landmarks cannot be detected, the img will be discarded
return None
#print(landmarks)
facial5point = [[landmarks[0][j], landmarks[0][j + 5]] for j in range(5)]
#print(facial5points[i])
warped_face = warp_and_crop_face(np.array(img),
facial5point,
reference,
crop_size=(crop_size, crop_size))
img_warped = Image.fromarray(warped_face)
# img_warped.save("test.jpg")
# img_warped.show()
return img_warped, bounding_boxes
def detect_face_align(img):
crop_size = 112 #因为backbone的input_size要[112,112]or[224,224]
scale = crop_size / 112.
reference = get_reference_facial_points(default_square=True) * scale
#img = Image.open(os.path.join(image_path))
bounding_boxes = []
warped_face = []
img_warped = []
facial5point = []
landmarks = []
try:
bounding_boxes, landmarks = detect_faces(img)
except Exception as e:
print(e)
if len(
landmarks
) == 0: # If the landmarks cannot be detected, the img will be discarded
return img_warped, bounding_boxes
#print(landmarks)
for i in range(len(landmarks)):
facial5point.append([[landmarks[i][j], landmarks[i][j + 5]]
for j in range(5)])
#print(facial5points[i])
warped_face.append(
warp_and_crop_face(np.array(img),
facial5point[i],
reference,
crop_size=(crop_size, crop_size)))
img_warped.append(Image.fromarray(warped_face[i]))
# img_warped.save("test.jpg")
# img_warped.show()
return img_warped, bounding_boxes
def align_68(img, crop_size, model):
# check if img is PIL
bbox = model.face_detector.detect_from_image(img)
if bbox is None:
return 4
landmarks = model.get_landmarks(img, bbox)
if landmarks is None:
return 4
landmarks = landmarks[0]
left_eye = np.mean(landmarks[36:42, :], axis=0).astype(np.int)
right_eye = np.mean(landmarks[42:48, :], axis=0).astype(np.int)
nose = np.mean(landmarks[28:35, :], axis=0).astype(np.int)
left_mouth = landmarks[48].astype(np.int)
right_mouth = landmarks[54].astype(np.int)
# settings
scale = crop_size / 112.
reference = get_reference_facial_points(default_square=True) * scale
facial5points = [left_eye, right_eye, nose, left_mouth, right_mouth]
warped_face = warp_and_crop_face(np.array(img),
facial5points,
reference,
crop_size=(crop_size, crop_size))
img_warped = Image.fromarray(warped_face)
return img_warped
def __init__(self, device, crop_size = 112):
#default format is N X H X W X D
super().__init__()
self.detection = Detection(device)
self.embedding = Embedding(device)
for parameter in self.embedding.parameters():
parameter.requires_grad = False
self.embedding = self.embedding.eval()
self.crop_size = crop_size
self.scale = crop_size / 112.
self.reference = get_reference_facial_points(default_square = True) * self.scale
def __init__(self, cpu=True, crop_size=112, weights_path="./weights/backbone_ir50_asia.pth"):
self.cpu = cpu
self.crop_size = crop_size
self.weights_path = weights_path
torch.set_grad_enabled(False)
self.device = torch.device('cpu' if self.cpu else 'cuda:0')
# Feature Extraction Model
self.arcface_r50_asian = IR_50([self.crop_size, self.crop_size])
self.arcface_r50_asian.load_state_dict(torch.load(weights_path, map_location='cpu' if self.cpu else 'cuda'))
self.arcface_r50_asian.eval()
self.arcface_r50_asian.to(self.device)
# Align
self.scale = self.crop_size / 112.
self.reference = get_reference_facial_points(default_square=True) * self.scale
# Facial Detection Model
self.face_detector = FaceDetector()
def align(img, crop_size, img_landmarks):
landmarks = img_landmarks[0]
left_eye = np.mean(landmarks[36:42, :], axis=0).astype(np.int)
right_eye = np.mean(landmarks[42:48, :], axis=0).astype(np.int)
nose = np.mean(landmarks[28:35, :], axis=0).astype(np.int)
left_mouth = landmarks[48].astype(np.int)
right_mouth = landmarks[54].astype(np.int)
# settings
scale = crop_size / 112.
reference = get_reference_facial_points(default_square=True) * scale
facial5points = [left_eye, right_eye, nose, left_mouth, right_mouth]
warped_face = warp_and_crop_face(np.array(img),
facial5points,
reference,
crop_size=(crop_size, crop_size))
img_warped = Image.fromarray(warped_face)
return img_warped
def align_(img, crop_size, model_root, filter=False):
# check if img is PIL
if type(img) == np.ndarray:
img = Image.fromarray(img)
# path to detector models
op = "{}/onet.npy".format(model_root)
pp = "{}/pnet.npy".format(model_root)
rp = "{}/rnet.npy".format(model_root)
# settings
scale = crop_size / 112.
reference = get_reference_facial_points(default_square=True) * scale
try: # Handle exception
_, landmarks = detect_faces(img, ppath=pp, opath=op, rpath=rp)
except Exception:
print("Image is discarded due to exception!")
return 4
if len(
landmarks
) == 0: # If the landmarks cannot be detected, the img will be discarded
print("Image is discarded due to non-detected landmarks!")
return 4
if filter:
return True
else:
facial5points = [[landmarks[0][j], landmarks[0][j + 5]]
for j in range(5)]
warped_face = warp_and_crop_face(np.array(img),
facial5points,
reference,
crop_size=(crop_size, crop_size))
img_warped = Image.fromarray(warped_face)
return img_warped
import argparse
from glob import glob
if __name__ == '__main__':
parser = argparse.ArgumentParser(description = "face alignment")
parser.add_argument("-source_root", "--source_root", help = "specify your source dir", default = "./data/test", type = str)
parser.add_argument("-dest_root", "--dest_root", help = "specify your destination dir", default = "./data/test_Aligned", type = str)
parser.add_argument("-crop_size", "--crop_size", help = "specify size of aligned faces, align and crop with padding", default = 112, type = int)
args = parser.parse_args()
source_root = args.source_root # specify your source dir
dest_root = args.dest_root # specify your destination dir
crop_size = args.crop_size # specify size of aligned faces, align and crop with padding
scale = crop_size / 112.
reference = get_reference_facial_points(default_square = True) * scale
cwd = os.getcwd() # delete '.DS_Store' existed in the source_root
os.chdir(source_root)
os.system("find . -name '*.DS_Store' -type f -delete")
os.chdir(cwd)
if not os.path.isdir(dest_root):
os.mkdir(dest_root)
for image_name in tqdm(glob("{}/*".format(source_root))):
print("Processing\t{}".format(image_name))
img = Image.open(image_name)
try: # Handle exception
_, landmarks = detect_faces(img)
except Exception:
default="/media/hyo/文档/VIS-NIR/colorferet/VIS_aligned/",
type=str)
parser.add_argument(
"-crop_size",
"--crop_size",
help="specify size of aligned faces, align and crop with padding",
default=112,
type=int)
args = parser.parse_args()
source_root = args.source_root # specify your source dir
dest_root = args.dest_root # specify your destination dir
crop_size = args.crop_size # specify size of aligned faces, align and crop with padding
scale = crop_size / 112.
# reference = get_reference_facial_points(default_square = True) * scale
original_5_points = get_reference_facial_points(default_square=True)
# original_5_points[:, 1] = original_5_points[:, 1] - 15
reference = (original_5_points) * scale
cwd = os.getcwd() # delete '.DS_Store' existed in the source_root
os.chdir(source_root)
os.system("find . -name '*.DS_Store' -type f -delete")
os.chdir(cwd)
if not os.path.isdir(dest_root):
os.mkdir(dest_root)
for image_name in tqdm(os.listdir(source_root)):
# if not os.path.isdir(os.path.join(dest_root, subfolder)):
# os.mkdir(os.path.join(dest_root, subfolder))
# for image_name in os.listdir(os.path.join(source_root, subfolder)):
print("Processing\t{}".format(os.path.join(source_root, image_name)))
from PIL import Image
import matplotlib.pyplot as plt
import torch
from torchvision import transforms
import scipy.misc as m
import os
import random
# img_path = '../00003.jpg'
# img = Image.open(img_path)
# img = img.convert('RGB')
# img = img.convert('YCbCr')
crop_size = 112
reference = get_reference_facial_points(
default_square=True) * crop_size / 112.0
TARGET_ROOT = '/media/hyo/文档/VIS-NIR/SKETCH/cropped_sketch'
SOURCE_ROOT_LIST = [
'/media/hyo/文档/VIS-NIR/SKETCH/CUFS/AR_sketch/sketch',
'/media/hyo/文档/VIS-NIR/SKETCH/CUFS/CUHK_testing_sketch/sketch',
'/media/hyo/文档/VIS-NIR/SKETCH/CUFS/CUHK_training_sketch/sketch',
'/media/hyo/文档/VIS-NIR/SKETCH/CUFS/XM2VTS_sketch/sketch',
'/media/hyo/文档/VIS-NIR/SKETCH/CUFSF/original_sketch'
]
count = 0
random.shuffle(SOURCE_ROOT_LIST)
for source_root in SOURCE_ROOT_LIST:
img_list = os.listdir(source_root)
for img_name in img_list:
img = Image.open(os.path.join(source_root, img_name))
