def train_arcface_model(face_detector, config, dataset_folder,
embedding_folder):
objs = []
register_image_bbox_objs = []
registered_ids = []
for folder in os.listdir(dataset_folder):
if not folder.endswith('.txt'):
for face in os.listdir(f"{dataset_folder}/{folder}"):
raw_image_path = f"{dataset_folder}/{folder}/{face}"
train_image_id = ImageId(channel='train_img',
timestamp=arrow.now().timestamp,
file_format=os.path.splitext(face)[1])
train_image_obj = Image(train_image_id,
raw_image_path=raw_image_path)
try:
face_detection_result = face_detector.detect(
train_image_obj, label=folder)
if len(face_detection_result.detected_objects) == 1:
register_image_bbox_objs.append(
face_detection_result.detected_objects[0])
registered_ids.append(
face_detection_result.detected_objects[0].label)
objs += train_image_obj.fetch_bbox_pil_objs(
register_image_bbox_objs)
except:
print(
f"[ERROR] An error occured with the face detector model. Can't open the photo {dataset_folder}/{folder}/{face}"
)
register_image_bbox_objs = []
objects_frame = resize_and_stack_image_objs((112, 112), objs)
print("Object_frame shape:", objects_frame.shape)
objects_frame = np.transpose(objects_frame, (0, 3, 1, 2))
with SimpleTimer("[INFO] Extracting embedding for our dataset"):
arcface_classifier = ArcFaceClassifier(config,
registered_ids,
objects_frame=objects_frame)
embedding_path = f"{embedding_folder}/faces.pkl"
print(f"[INFO] Store face embedding to {embedding_path}")
arcface_classifier.store_embedding_info(embedding_path)
ids_path = f"{embedding_folder}/registered_ids.txt"
print(f"[INFO] Store registered ids to {ids_path}")
with open(ids_path, 'w') as filehandle:
for registered_id in registered_ids:
filehandle.write('%s\n' % registered_id)
return arcface_classifier
def recognize_person(self, img, face_detection_result):
image_id = ImageId(channel='stream', timestamp=arrow.now().timestamp)
image_obj = Image(image_id, pil_image_obj=img)
detection_result = self.detect(image_obj,
face_detection_result.detected_objects)
persons = [(elt.label, elt.x1, elt.y1, elt.x2, elt.y2, elt.score)
for elt in detection_result.detected_objects]
return (persons, detection_result.detected_objects)
# if args.gpu >= 0:
# ctx = mx.gpu(args.gpu)
# else:
# ctx = mx.cpu(0)
model_name = 'MTCNN'
with SimpleTimer("Loading model %s" % model_name):
face_detector = MtcnnFaceDetector(args.mtcnn_path, ctx=mx.gpu(0))
# Préprocess de l'image
raw_image_path = 'demo/183club/test_imag1.jpg'
#ImageId is used to standardize the image_id format
train_image_id = ImageId(channel='demo',
timestamp=arrow.now().timestamp,
file_format='jpg')
train_image_obj = Image(train_image_id, raw_image_path=raw_image_path)
register_image_bbox_objs = [
BoundedBoxObject(x1=1526,
y1=755,
x2=1730,
y2=1007,
label='Zoe',
score=1,
meta=''),
#BoundedBoxObject(x1=946, y1=551, x2=1149, y2=784, label='Amine', score=1, meta=''),
BoundedBoxObject(x1=1364,
y1=564,
x2=1492,
y2=720,
label='Lu',
url=FLAGS.url, verbose=FLAGS.verbose)
except Exception as e:
print("channel creation failed: " + str(e))
sys.exit()
model_name = "yolov4"
# Infer
inputs = []
outputs = []
# the built engine with input NCHW
inputs.append(tritongrpcclient.InferInput("data", [1, 3, 608, 608],
"FP32"))
# Initialize the data
image_obj = Image("image_id", raw_image_path=FLAGS.img)
ori_w, ori_h = image_obj.pil_image_obj.size
image_frame, scale_ratio = preprocess(image_obj.pil_image_obj,
input_image_shape=(608, 608))
inputs[0].set_data_from_numpy(image_frame)
outputs.append(tritongrpcclient.InferRequestedOutput("prob"))
# Test with outputs
results = triton_client.infer(model_name=model_name,
inputs=inputs,
outputs=outputs,
headers={"test": "1"})
statistics = triton_client.get_inference_statistics(model_name=model_name)
print(statistics)
from eyewitness.image_utils import ImageHandler, Image
from bistiming import SimpleTimer
from cv2_detector import CascadeClassifierPersonWrapper, HogPersonDetectorWrapper, MobileNetWrapper
def get_person_detector(model):
if model == 'Cascade':
detector = CascadeClassifierPersonWrapper()
elif model == 'Hog':
detector = HogPersonDetectorWrapper()
elif model == 'MobileNet':
detector = MobileNetWrapper()
else:
raise Exception('not implement error')
return detector
if __name__ == '__main__':
model_name = 'MobileNet'
with SimpleTimer("Loading model %s" % model_name):
object_detector = get_person_detector(model_name)
raw_image_path = 'demo/test_image.jpg'
image_id = ImageId(channel='demo', timestamp=arrow.now().timestamp, file_format='jpg')
image_obj = Image(image_id, raw_image_path=raw_image_path)
with SimpleTimer("Predicting image with classifier"):
detection_result = object_detector.detect(image_obj)
print("detected %s objects" % len(detection_result.detected_objects))
ImageHandler.draw_bbox(image_obj.pil_image_obj, detection_result.detected_objects)
ImageHandler.save(image_obj.pil_image_obj, "detected_image/drawn_image.jpg")