def recognize_from_video():
# net initialize
detector = ailia.Detector(MODEL_PATH,
WEIGHT_PATH,
len(FACE_CATEGORY),
format=ailia.NETWORK_IMAGE_FORMAT_RGB,
channel=ailia.NETWORK_IMAGE_CHANNEL_FIRST,
range=RANGE,
algorithm=ALGORITHM,
env_id=args.env_id)
capture = webcamera_utils.get_capture(args.video)
if args.savepath != SAVE_IMAGE_PATH:
writer = webcamera_utils.get_writer(
args.savepath,
IMAGE_HEIGHT,
IMAGE_WIDTH,
fps=capture.get(cv2.CAP_PROP_FPS),
)
else:
writer = None
while (True):
ret, frame = capture.read()
if (cv2.waitKey(1) & 0xFF == ord('q')) or not ret:
break
_, resized_img = webcamera_utils.adjust_frame_size(
frame, IMAGE_HEIGHT, IMAGE_WIDTH)
img = cv2.cvtColor(resized_img, cv2.COLOR_BGR2BGRA)
detector.compute(img, THRESHOLD, IOU)
detections = []
for idx in range(detector.get_object_count()):
obj = detector.get_object(idx)
detections.append(obj)
detections = nms_between_categories(detections,
frame.shape[1],
frame.shape[0],
categories=[0, 1],
iou_threshold=IOU)
res_img = plot_results(detections, resized_img, FACE_CATEGORY, False)
cv2.imshow('frame', res_img)
# save results
if writer is not None:
writer.write(res_img)
capture.release()
cv2.destroyAllWindows()
if writer is not None:
writer.release()
logger.info('Script finished successfully.')
def get_faces(detector, frame, w, h):
# detect face
org_detections = []
if args.face == "blazeface":
org_detections = compute_blazeface(detector, frame)
else:
img = cv2.cvtColor(frame, cv2.COLOR_BGR2BGRA)
detector.compute(img, args.face_threshold, FACE_IOU)
count = detector.get_object_count()
for idx in range(count):
obj = detector.get_object(idx)
org_detections.append(obj)
# remove overwrapped detection
org_detections = nms_between_categories(org_detections,
w,
h,
categories=[0, 1],
iou_threshold=FACE_IOU)
detections = []
for idx in range(len(org_detections)):
# get detected face
obj = org_detections[idx]
margin = FACE_MARGIN
cx = (obj.x + obj.w / 2) * w
cy = (obj.y + obj.h / 2) * h
cw = max(obj.w * w * margin, obj.h * h * margin)
fx = max(cx - cw / 2, 0)
fy = max(cy - cw / 2, 0)
fw = min(cw, w - fx)
fh = min(cw, h - fy)
top_left = (int(fx), int(fy))
bottom_right = (int((fx + fw)), int(fy + fh))
# get detected face
crop_img = frame[top_left[1]:bottom_right[1],
top_left[0]:bottom_right[0], 0:3]
if crop_img.shape[0] <= 0 or crop_img.shape[1] <= 0:
continue
crop_img, resized_frame = adjust_frame_size(crop_img, IMAGE_HEIGHT,
IMAGE_WIDTH)
detections.append({
"resized_frame": resized_frame,
"top_left": top_left,
"bottom_right": bottom_right,
"id_sim": 0,
"score_sim": 0,
"fe": None
})
return detections
def recognize_from_image():
# net initialize
detector = ailia.Detector(MODEL_PATH,
WEIGHT_PATH,
len(FACE_CATEGORY),
format=ailia.NETWORK_IMAGE_FORMAT_RGB,
channel=ailia.NETWORK_IMAGE_CHANNEL_FIRST,
range=RANGE,
algorithm=ALGORITHM,
env_id=args.env_id)
# input image loop
for image_path in args.input:
# prepare input data
logger.info(image_path)
img = load_image(image_path)
logger.debug(f'input image shape: {img.shape}')
# inference
logger.info('Start inference...')
if args.benchmark:
logger.info('BENCHMARK mode')
for i in range(5):
start = int(round(time.time() * 1000))
detector.compute(img, THRESHOLD, IOU)
end = int(round(time.time() * 1000))
logger.info(f'\tailia processing time {end - start} ms')
else:
detector.compute(img, THRESHOLD, IOU)
# nms
detections = []
for idx in range(detector.get_object_count()):
obj = detector.get_object(idx)
detections.append(obj)
detections = nms_between_categories(
detections,
img.shape[1],
img.shape[0],
categories=[0, 1],
iou_threshold=IOU,
)
# plot result
res_img = plot_results(detections, img, FACE_CATEGORY)
savepath = get_savepath(args.savepath, image_path)
logger.info(f'saved at : {savepath}')
cv2.imwrite(savepath, res_img)
logger.info('Script finished successfully.')
def recognize_from_video():
# net initialize
env_id = ailia.get_gpu_environment_id()
print(f'env_id: {env_id}')
detector = ailia.Detector(
MODEL_PATH,
WEIGHT_PATH,
len(FACE_CATEGORY),
format=ailia.NETWORK_IMAGE_FORMAT_RGB,
channel=ailia.NETWORK_IMAGE_CHANNEL_FIRST,
range=RANGE,
algorithm=ALGORITHM,
env_id=env_id
)
if args.video == '0':
print('[INFO] Webcam mode is activated')
capture = cv2.VideoCapture(0)
if not capture.isOpened():
print("[ERROR] webcamera not found")
sys.exit(1)
else:
if check_file_existance(args.video):
capture = cv2.VideoCapture(args.video)
while(True):
ret, frame = capture.read()
if cv2.waitKey(1) & 0xFF == ord('q'):
break
if not ret:
continue
_, resized_img = adjust_frame_size(frame, IMAGE_HEIGHT, IMAGE_WIDTH)
img = cv2.cvtColor(resized_img, cv2.COLOR_BGR2BGRA)
detector.compute(img, THRESHOLD, IOU)
detections = []
for idx in range(detector.get_object_count()):
obj = detector.get_object(idx)
detections.append(obj)
detections=nms_between_categories(detections,frame.shape[1],frame.shape[0],categories=[0,1],iou_threshold=IOU)
res_img = plot_results(detections, resized_img, FACE_CATEGORY, False)
cv2.imshow('frame', res_img)
capture.release()
cv2.destroyAllWindows()
print('Script finished successfully.')
def recognize_from_frame(net, detector, frame):
# object detection
detector.compute(frame, args.threshold, args.iou)
frame = cv2.cvtColor(frame, cv2.COLOR_BGRA2BGR)
# nms
detections = []
for idx in range(detector.get_object_count()):
obj = detector.get_object(idx)
detections.append(obj)
detections = nms_between_categories(
detections,
frame.shape[1],
frame.shape[0],
categories=DETECT_CLASSES,
iou_threshold=IOU,
)
for idx in range(len(detections)):
obj = detections[idx]
if obj.category not in DETECT_CLASSES:
continue
# cropping image
margin = 1.0
crop_img, top_left, bottom_right = crop(obj, margin, frame)
# inference
img = cv2.resize(crop_img, (IMAGE_SIZE, IMAGE_SIZE))
img = np.expand_dims(img, axis=0) # 次元合せ
output = net.predict([img])
out_typ, out_clr = output
typ = TYPE_LIST[np.argmax(out_typ)]
clr = COLOR_LIST[np.argmax(out_clr)]
clr_table = COLOR_TABLE_LIST[np.argmax(out_clr)]
# draw label
LABEL_WIDTH = bottom_right[1] - top_left[1]
LABEL_HEIGHT = 20
color = clr_table #(255, 128, 128)
cv2.rectangle(frame, top_left, bottom_right, color, thickness=2)
cv2.rectangle(
frame,
top_left,
(top_left[0] + LABEL_WIDTH, top_left[1] + LABEL_HEIGHT),
color,
thickness=-1,
)
text_position = (top_left[0], top_left[1] + LABEL_HEIGHT * 3 // 4)
color = (0, 0, 0)
fontScale = 0.7
cv2.putText(
frame,
"{} {}".format(typ, clr),
text_position,
cv2.FONT_HERSHEY_SIMPLEX,
fontScale,
color,
1,
)
return frame
