def recognize_from_video():
# net initialize
env_id = ailia.get_gpu_environment_id()
print(f'env_id: {env_id}')
net = ailia.Net(MODEL_PATH, WEIGHT_PATH, env_id=env_id)
net.set_input_shape((1, IMAGE_HEIGHT, IMAGE_WIDTH, 3))
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)
fig = create_figure()
tight_layout = True
while(True):
ret, frame = capture.read()
if cv2.waitKey(1) & 0xFF == ord('q'):
break
if not ret:
continue
input_image, resized_img = adjust_frame_size(
frame, IMAGE_HEIGHT, IMAGE_WIDTH
)
resized_img = cv2.cvtColor(resized_img, cv2.COLOR_BGR2RGB)
if args.apply_rotate:
rotation_angle = np.random.randint(360)
rotated_img = generate_rotated_image(
resized_img,
rotation_angle,
size=(IMAGE_HEIGHT, IMAGE_WIDTH),
crop_center=True,
crop_largest_rect=True
)
input_data = rotated_img.reshape((1, IMAGE_HEIGHT, IMAGE_WIDTH, 3))
else:
rotation_angle = 0
rotated_img = resized_img
input_data = rotated_img.reshape((1, IMAGE_HEIGHT, IMAGE_WIDTH, 3))
# inference
preds_ailia = net.predict(input_data)
# visualize
predicted_angle = np.argmax(preds_ailia, axis=1)[0]
plt = visualize(fig, rotated_img, rotation_angle, predicted_angle, tight_layout)
plt.pause(.01)
tight_layout = False
capture.release()
cv2.destroyAllWindows()
print('Script finished successfully.')
def recognize_from_image():
# net initialize
net = 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 = cv2.cvtColor(cv2.imread(image_path), cv2.COLOR_BGR2RGB)
if args.apply_rotate:
rotation_angle = np.random.randint(360)
rotated_img = generate_rotated_image(org_img,
rotation_angle,
size=(IMAGE_HEIGHT,
IMAGE_WIDTH),
crop_center=True,
crop_largest_rect=True)
input_data = rotated_img.reshape((1, IMAGE_HEIGHT, IMAGE_WIDTH, 3))
else:
rotation_angle = 0
rotated_img = cv2.resize(org_img, (IMAGE_HEIGHT, IMAGE_WIDTH))
input_data = rotated_img.reshape((1, IMAGE_HEIGHT, IMAGE_WIDTH, 3))
net.set_input_shape(input_data.shape)
# inference
logger.info('Start inference...')
if args.benchmark:
logger.info('BENCHMARK mode')
for i in range(5):
start = int(round(time.time() * 1000))
preds_ailia = net.predict(input_data)
end = int(round(time.time() * 1000))
logger.info(f'\tailia processing time {end - start} ms')
else:
preds_ailia = net.predict(input_data)
# visualize
predicted_angle = np.argmax(preds_ailia, axis=1)[0]
fig = create_figure()
plt = visualize(fig, rotated_img, rotation_angle, predicted_angle)
savepath = get_savepath(args.savepath, image_path)
logger.info(f'saved at : {savepath}')
plt.savefig(savepath)
logger.info('Script finished successfully.')
def recognize_from_image():
# prepare input data
org_img = cv2.cvtColor(cv2.imread(args.input), cv2.COLOR_BGR2RGB)
if args.apply_rotate:
rotation_angle = np.random.randint(360)
rotated_img = generate_rotated_image(org_img,
rotation_angle,
size=(IMAGE_HEIGHT, IMAGE_WIDTH),
crop_center=True,
crop_largest_rect=True)
input_data = rotated_img.reshape((1, IMAGE_HEIGHT, IMAGE_WIDTH, 3))
else:
rotation_angle = 0
rotated_img = cv2.resize(org_img, (IMAGE_HEIGHT, IMAGE_WIDTH))
input_data = rotated_img.reshape((1, IMAGE_HEIGHT, IMAGE_WIDTH, 3))
# net initialize
env_id = ailia.get_gpu_environment_id()
print(f'env_id: {env_id}')
net = ailia.Net(MODEL_PATH, WEIGHT_PATH, env_id=env_id)
net.set_input_shape(input_data.shape)
# inference
print('Start inference...')
if args.benchmark:
print('BENCHMARK mode')
for i in range(5):
start = int(round(time.time() * 1000))
preds_ailia = net.predict(input_data)
end = int(round(time.time() * 1000))
print(f'\tailia processing time {end - start} ms')
else:
preds_ailia = net.predict(input_data)
# visualize
predicted_angle = np.argmax(preds_ailia, axis=1)[0]
plt = visualize(rotated_img, rotation_angle, predicted_angle)
plt.savefig(args.savepath)
print('Script finished successfully.')
def recognize_from_video():
# net initialize
net = ailia.Net(MODEL_PATH, WEIGHT_PATH, env_id=args.env_id)
net.set_input_shape((1, IMAGE_HEIGHT, IMAGE_WIDTH, 3))
capture = webcamera_utils.get_capture(args.video)
# create video writer if savepath is specified as video format
if args.savepath != SAVE_IMAGE_PATH:
logger.warning(
'currently, video results cannot be output correctly...')
# TODO: DEBUG: shape
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
fig = create_figure()
tight_layout = True
while (True):
ret, frame = capture.read()
if (cv2.waitKey(1) & 0xFF == ord('q')) or not ret:
break
input_image, resized_img = webcamera_utils.adjust_frame_size(
frame, IMAGE_HEIGHT, IMAGE_WIDTH)
resized_img = cv2.cvtColor(resized_img, cv2.COLOR_BGR2RGB)
if args.apply_rotate:
rotation_angle = np.random.randint(360)
rotated_img = generate_rotated_image(resized_img,
rotation_angle,
size=(IMAGE_HEIGHT,
IMAGE_WIDTH),
crop_center=True,
crop_largest_rect=True)
input_data = rotated_img.reshape((1, IMAGE_HEIGHT, IMAGE_WIDTH, 3))
else:
rotation_angle = 0
rotated_img = resized_img
input_data = rotated_img.reshape((1, IMAGE_HEIGHT, IMAGE_WIDTH, 3))
# inference
preds_ailia = net.predict(input_data)
# visualize
predicted_angle = np.argmax(preds_ailia, axis=1)[0]
plt = visualize(fig, rotated_img, rotation_angle, predicted_angle,
tight_layout)
plt.pause(.01)
if not plt.get_fignums():
break
tight_layout = False
# # 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.')
