def recognize_from_video():
# net initialize
detector = None
detector = ailia.Net(MODEL_PATH, WEIGHT_PATH, env_id=args.env_id)
if int(args.detection_width) != DETECTION_WIDTH:
detector.set_input_shape(
(1, 3, int(args.detection_width), int(args.detection_width)))
capture = webcamera_utils.get_capture(args.video)
# create video writer if savepath is specified as video format
if args.savepath != SAVE_IMAGE_PATH:
f_h = int(capture.get(cv2.CAP_PROP_FRAME_HEIGHT))
f_w = int(capture.get(cv2.CAP_PROP_FRAME_WIDTH))
writer = webcamera_utils.get_writer(args.savepath, f_h, f_w)
else:
writer = None
while (True):
ret, frame = capture.read()
if (cv2.waitKey(1) & 0xFF == ord('q')) or not ret:
break
img = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
img = cv2.resize(img, (IMAGE_WIDTH, IMAGE_HEIGHT))
img = np.transpose(img, [2, 0, 1])
img = img.astype(np.float32) / 255
img = np.expand_dims(img, 0)
output = detector.predict([img])
detect_object = yolov4_utils.post_processing(img, THRESHOLD, IOU,
output)
res_img = plot_results(detect_object[0], frame, COCO_CATEGORY)
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()
print('Script finished successfully.')
def recognize_from_image():
# net initialize
detector = ailia.Net(MODEL_PATH, WEIGHT_PATH, env_id=args.env_id)
# input image loop
for image_path in args.input:
# prepare input data
logger.info(image_path)
org_img = load_image(image_path)
org_img = cv2.cvtColor(org_img, cv2.COLOR_BGRA2BGR)
logger.debug(f'input image shape: {org_img.shape}')
img = letterbox_convert(org_img, (IMAGE_HEIGHT, IMAGE_WIDTH))
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
img = np.transpose(img, [2, 0, 1])
img = img.astype(np.float32) / 255
img = np.expand_dims(img, 0)
# inference
logger.info('Start inference...')
if args.benchmark:
logger.info('BENCHMARK mode')
for i in range(5):
start = int(round(time.time() * 1000))
output = detector.predict([img])
end = int(round(time.time() * 1000))
logger.info(f'\tailia processing time {end - start} ms')
else:
output = detector.predict([img])
detect_object = yolov4_utils.post_processing(img, args.threshold,
args.iou, output)
detect_object = reverse_letterbox(detect_object[0], org_img,
(IMAGE_HEIGHT, IMAGE_WIDTH))
# plot result
res_img = plot_results(detect_object, org_img, COCO_CATEGORY)
# plot result
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
detector = None
env_id = ailia.get_gpu_environment_id()
print(f'env_id: {env_id}')
detector = ailia.Net(MODEL_PATH, WEIGHT_PATH, env_id=env_id)
if int(args.detection_width) != DETECTION_WIDTH:
detector.set_input_shape(
(1, 3, int(args.detection_width), int(args.detection_width)))
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
img = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
img = cv2.resize(img, (IMAGE_WIDTH, IMAGE_HEIGHT))
img = np.transpose(img, [2, 0, 1])
img = img.astype(np.float32) / 255
img = np.expand_dims(img, 0)
output = detector.predict([img])
detect_object = yolov4_utils.post_processing(img, THRESHOLD, IOU,
output)
res_img = plot_results(detect_object[0], frame, COCO_CATEGORY)
cv2.imshow('frame', res_img)
capture.release()
cv2.destroyAllWindows()
print('Script finished successfully.')
def recognize_from_image():
# prepare input data
org_img = load_image(args.input)
print(f'input image shape: {org_img.shape}')
img = cv2.cvtColor(org_img, cv2.COLOR_BGRA2RGB)
img = cv2.resize(img, (IMAGE_WIDTH, IMAGE_HEIGHT))
img = np.transpose(img, [2, 0, 1])
img = img.astype(np.float32) / 255
img = np.expand_dims(img, 0)
# net initialize
env_id = ailia.get_gpu_environment_id()
print(f'env_id: {env_id}')
detector = ailia.Net(MODEL_PATH, WEIGHT_PATH, env_id=env_id)
if int(args.detection_width) != DETECTION_WIDTH:
detector.set_input_shape(
(1, 3, int(args.detection_width), int(args.detection_width)))
# inferece
print('Start inference...')
if args.benchmark:
print('BENCHMARK mode')
for i in range(5):
start = int(round(time.time() * 1000))
output = detector.predict([img])
end = int(round(time.time() * 1000))
print(f'\tailia processing time {end - start} ms')
else:
output = detector.predict([img])
detect_object = yolov4_utils.post_processing(img, THRESHOLD, IOU, output)
# plot result
res_img = plot_results(detect_object[0], org_img, COCO_CATEGORY)
# plot result
cv2.imwrite(args.savepath, res_img)
print('Script finished successfully.')
def recognize_from_video(detector):
capture = webcamera_utils.get_capture(args.video)
# create video writer if savepath is specified as video format
if args.savepath != SAVE_IMAGE_PATH:
f_h = int(capture.get(cv2.CAP_PROP_FRAME_HEIGHT))
f_w = int(capture.get(cv2.CAP_PROP_FRAME_WIDTH))
writer = webcamera_utils.get_writer(args.savepath, f_h, f_w)
else:
writer = None
if args.write_prediction:
frame_count = 0
frame_digit = int(
math.log10(capture.get(cv2.CAP_PROP_FRAME_COUNT)) + 1)
video_name = os.path.splitext(os.path.basename(args.video))[0]
while (True):
ret, frame = capture.read()
if (cv2.waitKey(1) & 0xFF == ord('q')) or not ret:
break
if args.detector:
img = cv2.cvtColor(frame, cv2.COLOR_BGR2BGRA)
detector.compute(img, args.threshold, args.iou)
res_img = plot_results(detector, frame, COCO_CATEGORY)
else:
img = letterbox_convert(frame, (IMAGE_HEIGHT, IMAGE_WIDTH))
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
img = np.transpose(img, [2, 0, 1])
img = img.astype(np.float32) / 255
img = np.expand_dims(img, 0)
output = detector.predict([img])
detect_object = yolov4_utils.post_processing(
img, args.threshold, args.iou, output)
detect_object = reverse_letterbox(detect_object[0], frame,
(IMAGE_HEIGHT, IMAGE_WIDTH))
res_img = plot_results(detect_object, frame, COCO_CATEGORY)
cv2.imshow('frame', res_img)
# save results
if writer is not None:
writer.write(res_img)
# write prediction
if args.write_prediction:
savepath = get_savepath(
args.savepath,
video_name,
post_fix='_%s' %
(str(frame_count).zfill(frame_digit) + '_res'),
ext='.png')
pred_file = '%s.txt' % savepath.rsplit('.', 1)[0]
write_predictions(pred_file, detect_object, frame, COCO_CATEGORY)
frame_count += 1
capture.release()
cv2.destroyAllWindows()
if writer is not None:
writer.release()
logger.info('Script finished successfully.')
def recognize_from_image(detector):
if args.profile:
detector.set_profile_mode(True)
# input image loop
for image_path in args.input:
# prepare input data
logger.info(image_path)
org_img = load_image(image_path)
if not args.detector:
org_img = cv2.cvtColor(org_img, cv2.COLOR_BGRA2BGR)
logger.debug(f'input image shape: {org_img.shape}')
img = letterbox_convert(org_img, (IMAGE_HEIGHT, IMAGE_WIDTH))
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
img = np.transpose(img, [2, 0, 1])
img = img.astype(np.float32) / 255
img = np.expand_dims(img, 0)
# inference
logger.info('Start inference...')
if args.benchmark:
logger.info('BENCHMARK mode')
total_time = 0
for i in range(args.benchmark_count):
start = int(round(time.time() * 1000))
if args.detector:
detector.compute(org_img, args.threshold, args.iou)
else:
output = detector.predict([img])
end = int(round(time.time() * 1000))
if i != 0:
total_time = total_time + (end - start)
logger.info(f'\tailia processing time {end - start} ms')
logger.info(
f'\taverage time {total_time / (args.benchmark_count-1)} ms')
else:
if args.detector:
detector.compute(org_img, args.threshold, args.iou)
else:
output = detector.predict([img])
if not args.detector:
detect_object = yolov4_utils.post_processing(
img, args.threshold, args.iou, output)
detect_object = reverse_letterbox(detect_object[0], org_img,
(IMAGE_HEIGHT, IMAGE_WIDTH))
res_img = plot_results(detect_object, org_img, COCO_CATEGORY)
else:
res_img = plot_results(detector, org_img, COCO_CATEGORY)
# plot result
savepath = get_savepath(args.savepath, image_path)
logger.info(f'saved at : {savepath}')
cv2.imwrite(savepath, res_img)
# write prediction
if args.write_prediction:
pred_file = '%s.txt' % savepath.rsplit('.', 1)[0]
write_predictions(pred_file, detect_object, org_img, COCO_CATEGORY)
if args.profile:
print(detector.get_summary())
logger.info('Script finished successfully.')