def __init__(self,
config,
registered_ids,
objects_frame=None,
registered_images_embedding=None,
batch_size=20):
params = {
'model': config["arcface_model"]["path"],
'image_size': '112,112',
'gpu': 0,
}
self.model = face_model.FaceModel(params)
self.image_size = [int(i) for i in params['image_size'].split(',')]
if registered_images_embedding is not None:
self.registered_images_embedding = registered_images_embedding
else:
n_images = objects_frame.shape[0]
registered_images_embedding_list = []
for row_idx, batch_start, batch_end in chunk_with_index(
range(n_images), batch_size):
objects_embedding = self.model.get_faces_feature(
objects_frame[batch_start:batch_end])
registered_images_embedding_list.append(objects_embedding)
self.registered_images_embedding = np.concatenate(
registered_images_embedding_list)
self.registered_ids = registered_ids
self.threshold = config["arcface_model"]["confidence_threshold"]
self.unknown = 'Unknown'
def __init__(self, gpu_id=0):
# 初始化模型的一些参数
ModelParam.gpu = gpu_id
self.model = face_model.FaceModel(ModelParam)
self.database = None
self.index2name = []
self.feature_matrix = None
def main(args):
args.det = 0
args.model = "C:\\Users\\Paul\\insightface\\models\\model-r50-am-lfw\\,0"
model = face_model.FaceModel(args)
img = cv2.imread(args.image)
img = cv2.resize(img, (112, 112))
img = model.get_input(img)
f1 = model.get_feature(img)
print(f1)
def test_all():
im_path = '/Users/wangyiran/Documents/face_data_set'
file = open('/Users/wangyiran/Documents/bad_case.txt', 'a')
# 人脸检测
folders = os.listdir(im_path)
cnt = 0
name_list = []
for folder in folders:
# 跳过mac隐藏文件
if folder.startswith('.'):
continue
random.seed(time.time() * 100000 % 10000)
sublist = []
imgs = os.listdir(os.path.join(im_path, folder))
random.shuffle(imgs)
for i in range(0, len(imgs), 2):
# 跳过mac隐藏文件
if imgs[i].startswith("."):
continue
try:
model = face_model.FaceModel(args)
pic_path1 = os.path.join(im_path, folder, imgs[i])
img1 = cv2.imread(pic_path1)
img1 = model.get_input(img1)
f1 = model.get_feature(img1)
pic_path2 = os.path.join(im_path, folder, imgs[i+1])
img2 = cv2.imread(pic_path2)
img2 = model.get_input(img2)
f2 = model.get_feature(img2)
dist = np.sum(np.square(f1-f2))
if dist < args.threshold:
print('they are the same one')
else:
# pdb.set_trace()
bad_case_folder = '/Users/wangyiran/Documents/face_data_set_result/' + str(cnt)
os.mkdir(bad_case_folder)
shutil.copy(pic_path1, bad_case_folder)
shutil.copy(pic_path2, bad_case_folder)
cnt += 1
file.writelines(pic_path1 + ',' + pic_path2+ ',' + str(dist) + ',' + str(args.threshold) + '\n')
print('they are the different one')
print(dist)
except:
continue
file.close()
def test():
model = face_model.FaceModel(args)
for i in range(1):
cnt = 0
out_txt = open('/media/dhao/系统/05-weiwei/FR/dataset/test_result/combine_test/1.38/result' +str(i+1) + '.txt', 'a')
file = open('/media/dhao/系统/05-weiwei/FR/politician_code/same_pairs.txt', 'r')
lines = file.readlines()
for j in range(len(lines)):
name1 = lines[j].strip().split(',')[0]
name2 = lines[j].strip().split(',')[1]
try:
img1 = cv2.imread(name1)
img1 = model.get_input(img1)
f1 = model.get_feature(img1)
img2 = cv2.imread(name2)
img2 = model.get_input(img2)
f2 = model.get_feature(img2)
dist = np.sqrt(np.sum(np.square(f1 - f2)))
if dist < args.threshold:
# print('they are the same one')
out_txt.writelines(name1 + ',' + name2 + ',' + str(dist) + ',' + str(args.threshold) + '*' *3 + str(1) + '\n')
else:
out_txt.writelines(name1 + ',' + name2 + ',' + str(dist) + ',' + str(args.threshold) + '*' * 3 + str(0) + '\n')
bad_case_folder = '/media/dhao/系统/05-weiwei/FR/dataset/test_result/combine_test/1.38/all' + str(i) + '/' + str(cnt) + '/'
if not os.path.exists(bad_case_folder):
os.mkdirs(bad_case_folder)
if os.path.isdir(bad_case_folder):
shutil.copy(name1, bad_case_folder)
shutil.copy(name2, bad_case_folder)
cnt += 1
else:
sys.exit(0)
except:
continue
file.close()
out_txt.close()
def face_refine():
im_path = '/Users/wangyiran/Documents/face_data_set'
result_path = '/Users/wangyiran/Documents/face_data_set_result'
# 人脸检测
folders = os.listdir(im_path)
cnt = 0
name_list = []
for folder in folders:
# 跳过mac隐藏文件
if folder.startswith('.'):
continue
random.seed(time.time() * 100000 % 10000)
# 在结果集中建立文件夹
result_dir = os.path.join(result_path, folder)
if not os.path.exists(result_dir):
os.mkdir(result_dir)
sublist = []
imgs = os.listdir(os.path.join(im_path, folder))
random.shuffle(imgs)
for i in range(0, len(imgs), 1):
# 跳过mac隐藏文件
if imgs[i].startswith("."):
continue
try:
model = face_model.FaceModel(args)
pic_path1 = os.path.join(im_path, folder, imgs[i])
img1 = cv2.imread(pic_path1)
img1 = model.get_input(img1)
# f1 = model.get_feature(img1)
if type(img1) == np.ndarray:
if not os.path.exists(os.path.join(result_path, folder)):
os.mkdir(os.path.join(result_path, folder))
cv2.imwrite(os.path.join(result_path, folder, imgs[i]), np.transpose(img1, (1, 2, 0))[:, :, ::-1])
except:
print('错误：文件名:' + folder + '/' + str(imgs[i]))
continue
def test_Faces(args):
model = face_model.FaceModel(args)
imgs = os.listdir(args.image_path)
flag = False
# 设置阈值，这两个阈值用来判定该人是否是库里的人
a = zip([args.threshold1], [args.threshold2])
for k, v in a:
for img in imgs:
if img.startswith('.'):
continue
pic = cv2.imread(os.path.join(args.image_path, img))
pic = model.get_input(pic)
if pic is None:
continue
else:
f1 = model.get_feature(pic)
for i in range(faces.shape[0]):
cnt = 0
for j in range(faces.shape[1]):
dist = np.sqrt(np.sum(np.square(f1 - faces[i][j])))
# 如果与库中某人距离小于阈值1
if dist < k:
cnt += 1
# 如果与库中某个人的相似度大于阈值2，则证明是该人
if cnt >= v:
name = labels[i]
testresult.writelines(
os.path.join(args.image_path, img) + ' is ' +
name + '\n')
print(
os.path.join(args.image_path, img) + ' is ' + name)
flag = True
if flag is False:
print("image:" + os.path.join(args.image_path, img) +
' is not in the gallery, refused!' + '\n')
testresult.close()
def compute_sim():
model = face_model.FaceModel(args)
out_txt = open('/media/dhao/系统/05-weiwei/FR/politician_code/result_dist.txt', 'a')
file = open('/media/dhao/系统/05-weiwei/FR/politician_code/same_pairs.txt', 'r')
lines = file.readlines()
for j in range(len(lines)):
name1 = lines[j].strip().split(',')[0]
name2 = lines[j].strip().split(',')[1]
try:
img1 = cv2.imread(name1)
img1 = model.get_input(img1)
f1 = model.get_feature(img1)
img2 = cv2.imread(name2)
img2 = model.get_input(img2)
f2 = model.get_feature(img2)
dist = np.sqrt(np.sum(np.square(f1 - f2)))
out_txt.writelines(name1 + ',' + name2 + ',' + ',' + str(dist) + '\n')
except:
continue
file.close()
out_txt.close()
image_set = get_dataset(args.data_dir)
image_list, label_list = get_image_paths_and_labels(image_set)
path_exp = os.path.expanduser(args.data_dir)
classes = [
path for path in os.listdir(path_exp)
if os.path.isdir(os.path.join(path_exp, path))
]
label_strings = [
name for name in classes if os.path.isdir(os.path.join(path_exp, name))
]
# pdb.set_trace()
# 初始化人脸检测模型
model = face_model.FaceModel(args)
# embedding_array 是一个 类别数*每个类别的图片数*每张图片特征向量长度 的numpy，这里每个类别有50张，可以更改。
embedding_array = np.zeros((len(classes), args.num_per_class, 512))
for i in range(0, len(classes)):
for j in range(args.num_per_class):
try:
pic = cv2.imread(image_list[i * args.num_per_class + j])
print(image_list[i * args.num_per_class + j])
if pic is None:
print(image_list[j])
else:
pic = model.get_input(pic)
feature = model.get_feature(pic)
embedding_array[i, j, :] = feature
except:
def __init__(self):
self.model = face_model.FaceModel(args)