def predict_img():
global mtcnn_detector, facenet, face_db
if request.method == 'POST':
files = request.files.getlist('file')
# print(request.files['file'].filename)
# thresh = request.form['thresh']
if request.files['file'].filename == '':
return jsonify(message='No file selected for predict'), 400
else:
result = {}
for file in files:
if file and allowed_file(file.filename):
filename = secure_filename(file.filename)
path_to_file = os.path.join(predict_path, filename)
print(path_to_file)
if os.path.isfile(path_to_file):
os.remove(path_to_file)
file.save(path_to_file)
img = cv2.imread(path_to_file)
faces, _ = mtcnn_detector.detect(img)
names, sims = [], []
for face in faces:
x1, y1, x2, y2 = int(face[0]), int(face[1]), int(
face[2]), int(face[3])
face_image = img[y1:y2, x1:x2]
names, sims = predict(face_image,
facenet,
face_db,
VERIFICATION_THRESHOLD=0.5)
result[filename] = len(names), names, sims
return jsonify(str(result)), 200
def test_with_cam(facenet, facedb):
cam = cv2.VideoCapture(0)
mtcnn_detector = load_mtcnn(scale_factor=0.709)
while True:
ret, frame = cam.read()
if ret:
faces, _ = mtcnn_detector.detect(frame)
for face in faces:
x1, y1, x2, y2 = int(face[0]), int(face[1]), int(face[2]), int(
face[3])
face_image = frame[y1:y2, x1:x2]
names, sims = predict(face_image,
facenet,
facedb,
VERIFICATION_THRESHOLD=0.5)
print(names)
cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 0, 255),
thickness=2)
cv2.imshow("frame", frame)
key = cv2.waitKey(1)
if key == ord('q'):
break
if key == 32:
cv2.waitKey(0)
else:
break
def predict_image(image):
names, sims = predict(image, facenet, face_db, VERIFICATION_THRESHOLD=0.5)
print(names)