def load_data(group_id, face_num=1000, max_user=None, method='vgg'):
X_train = []
y_train = []
X_test = []
y_test = []
# 按用户分组从db装入特征数据, 装入所有数据
start = 0
max_length = 1000
total = 0
while 1:
user_list = dbport.user_list_by_group(group_id,
start=start,
length=max_length)
for i in tqdm(range(len(user_list))):
if max_user and total >= max_user:
break
X = []
y = []
faces = dbport.user_face_list(group_id, user_list[i])
for f in faces[:face_num]: # 训练集
r = dbport.face_info(f)
if r:
e_list = get_encodings(r['encodings'], method)
X_train.extend(e_list)
y_train.extend([user_list[i]] * len(e_list))
for f in faces[face_num:]: # 验证集
r = dbport.face_info(f)
if r:
e_list = get_encodings(r['encodings'], method)
X_test.extend(e_list)
y_test.extend([user_list[i]] * len(e_list))
total += 1
if max_user and total >= max_user:
break
if len(user_list) < max_length:
break
else: # 未完，继续
start += max_length
# y标签规范化
label_y = preprocessing.LabelEncoder()
label_y.fit(y_train)
y_train = label_y.transform(y_train)
y_train = to_one_hot(y_train, total)
y_test = label_y.transform(y_test)
y_test = to_one_hot(y_test, total)
return np.array(X_train), np.array(y_train), np.array(X_test), np.array(
y_test), label_y
def face_verify_db(request_id, b64_data, group_id, user_id):
# 获取已知用户的特征数据
face_list = user_face_list(group_id, user_id)
if face_list==-1: # user_id 不存在
return None, -1
face_encodings = [face_info(i)['encodings'] for i in face_list]
# 进行比较验证
is_match, score, face_array = verify.verify_vgg.is_match_b64_2(face_encodings, b64_data)
if type(score)!=type([]):
score = score.tolist() # np.array
# 只记录结果正确的人脸数据，用于后面数据增强
if is_match>0:
face_save_to_temp(group_id, request_id, 'face_verify_db', [user_id], face_array[0])
return is_match, score
def face_search_mobile_tail(request_id, b64_data, mobile_tail, group_id='DEFAULT', max_user_num=5):
# 获取手机尾号的用户列表
user_list = user_list_by_mobile_tail(mobile_tail, group_id)
# 获取已知用户的特征数据
face_X = []
face_y = []
user_dict = {}
for user in user_list:
user_dict[user['user_id']] = user
face_list = user_face_list(group_id, user['user_id'])
if face_list==-1: # user_id 不存在
continue
for x in face_list:
ec = face_info(x)['encodings']['vgg'].values()
face_X.extend(ec)
face_y.extend([user['user_id']]*len(ec))
# 进行识别: 与给定的用户人脸进行比较
r, face_boxes, face_array = verify.verify_vgg.is_match_b64_3((face_X, face_y), b64_data)
user_list = []
for i in r[:max_user_num]:
user_id = i[0]
user_list.append({
'user_id' : user_id,
'mobile_tail' : mobile_tail, # 手机后4位
'name' : user_dict[user_id]['name'], # 用户姓名
'location' : face_boxes,
'score' : i[1], # 距离
})
# 只记录有结果的人脸数据，用于后面数据增强
if len(user_list)>0:
face_save_to_temp(group_id, request_id, 'face_search_mobile_tail', user_list, face_array[0])
return user_list
method = sys.argv[1]
Xy_file = group_id = sys.argv[2]
if method=='file':
with open(Xy_file, 'rb') as f:
X, y = pickle.load(f)
print('Calculating...')
score_acc_f1(X, y)
elif method in ('db_vgg', 'db_evo', 'db_rec'):
X = []
y = []
user_list = dbport.user_list_by_group(group_id, length=1000)
for i in range(len(user_list)):
faces_list = dbport.user_face_list(group_id, user_list[i])
for face in faces_list:
r = dbport.face_info(face)
e_list = r['encodings'][method[-3:]].values()
X.extend(e_list)
y.extend([user_list[i]]*len(e_list))
print('Calculating...')
score_acc_f1(X, y, title=method[-3:])
else:
print('Unknown method.')
sys.exit(1)
def train(group_id,
model_save_path=None,
n_neighbors=None,
knn_algo='ball_tree',
verbose=False,
face_algorithm='rec',
face_num=1000,
max_user=None,
need_train=None):
"""
Trains a k-nearest neighbors classifier for face recognition.
:param model_save_path: (optional) path to save model on disk
:param n_neighbors: (optional) number of neighbors to weigh in classification. Chosen automatically if not specified
:param knn_algo: (optional) underlying data structure to support knn.default is ball_tree
:param verbose: verbosity of training
:return: returns knn classifier that was trained on the given data.
"""
X = []
y = []
# 按用户分组从db装入特征数据, 装入所有数据
start = 0
max_length = 1000
total = 0
while 1:
user_list = dbport.user_list_by_group(group_id,
start=start,
length=max_length,
need_train=need_train)
for i in tqdm(range(len(user_list))):
if max_user and total >= max_user:
break
faces = dbport.user_face_list(group_id, user_list[i])
for f in faces[:face_num]: # 同一个人，只训练指定数量的人脸，默认1000
r = dbport.face_info(f)
if r:
for angle in TRAINING_ANGLE: # 旋转不同角度训练 multi2
X.append(r['encodings'][face_algorithm][str(angle)])
y.append(user_list[i])
total += 1
if max_user and total >= max_user:
break
if len(user_list) < max_length:
break
else: # 未完，继续
start += max_length
print('Data loaded:', total, len(X))
# 没有可训练数据
if len(X) == 0:
return None
# Determine how many neighbors to use for weighting in the KNN classifier
if n_neighbors is None:
n_neighbors = int(round(math.sqrt(len(X))))
if verbose:
print("Chose n_neighbors automatically:", n_neighbors)
# Create and train the KNN classifier
start_time = datetime.now()
knn_clf = neighbors.KNeighborsClassifier(n_neighbors=n_neighbors,
algorithm=knn_algo,
weights='distance')
knn_clf.fit(X, y)
#print('[Time taken: {!s}]'.format(datetime.now() - start_time))
# Save the trained KNN classifier
if model_save_path is not None:
with open(model_save_path, 'wb') as f:
pickle.dump(knn_clf, f)
# 计算 threshold
#opt_tau, opt_acc = score_acc_f1(X, y, show=False)
#print('{}: Accuracy at threshold {:.4} = {:.4}'.format(face_algorithm, opt_tau, opt_acc))
return knn_clf
def train(group_id,
encodings_index=0,
model_save_path=None,
n_neighbors=None,
knn_algo='ball_tree',
verbose=False,
face_algorithm='rec'):
"""
Trains a k-nearest neighbors classifier for face recognition.
:param model_save_path: (optional) path to save model on disk
:param n_neighbors: (optional) number of neighbors to weigh in classification. Chosen automatically if not specified
:param knn_algo: (optional) underlying data structure to support knn.default is ball_tree
:param verbose: verbosity of training
:return: returns knn classifier that was trained on the given data.
"""
X = []
y = []
# 按用户分组从db装入特征数据, 装入所有数据
start = 0
max_length = 1000
total = 0
while 1:
user_list = dbport.user_list_by_group(group_id,
start=start,
length=max_length)
for i in tqdm(range(len(user_list))):
faces = dbport.user_face_list(group_id, user_list[i])
for f in faces:
r = dbport.face_info(f)
if r:
X.append(r['encodings'][encodings_index])
y.append(user_list[i])
total += len(user_list)
if len(user_list) < max_length:
break
else: # 未完，继续
start += max_length
print('Data loaded:', total)
# Determine how many neighbors to use for weighting in the KNN classifier
if n_neighbors is None:
n_neighbors = int(round(math.sqrt(len(X))))
if verbose:
print("Chose n_neighbors automatically:", n_neighbors)
# Create and train the KNN classifier
start_time = datetime.now()
svc_clf = svm.LinearSVC()
svc_clf.fit(X, y)
#print('[Time taken: {!s}]'.format(datetime.now() - start_time))
# Save the trained KNN classifier
if model_save_path is not None:
with open(model_save_path, 'wb') as f:
pickle.dump(svc_clf, f)
return svc_clf