def __init__(self, overall_iters, cfg, mode):
"""
overall_iters (int): the overall number of iterations of one epoch.
cfg (CfgNode): configs.
mode (str): `train`, `val`, or `test` mode.
"""
self.cfg = cfg
self.lr = None
self.loss = ScalarMeter(cfg.LOG_PERIOD)
self.full_ava_test = cfg.AVA.FULL_TEST_ON_VAL
self.mode = mode
self.iter_timer = Timer()
self.data_timer = Timer()
self.net_timer = Timer()
self.all_preds_train = []
self.all_ori_boxes_train = []
self.all_metadata_train = []
self.all_preds = []
self.all_ori_boxes = []
self.all_metadata = []
self.overall_iters = overall_iters
self.categories, self.class_whitelist = read_labelmap(
os.path.join(cfg.AVA.ANNOTATION_DIR, cfg.AVA.LABEL_MAP_FILE))
gt_filename = os.path.join(cfg.AVA.ANNOTATION_DIR,
cfg.AVA.GROUNDTRUTH_FILE)
self.full_groundtruth = read_csv(gt_filename, self.class_whitelist)
self.mini_groundtruth = get_ava_mini_groundtruth(self.full_groundtruth)
_, self.video_idx_to_name = ava_helper.load_image_lists(
cfg, mode == "train")
self.output_dir = cfg.OUTPUT_DIR
def __init__(self, overall_iters, cfg, mode):
"""
overall_iters (int): the overall number of iterations of one epoch.
cfg (CfgNode): configs.
mode (str): `train`, `val`, or `test` mode.
"""
is_custom_dataset = cfg.TRAIN.DATASET == "custom" and cfg.TEST.DATASET == "custom"
if is_custom_dataset:
logger.info("Creating AVA Meter for custom dataset in %s mode" %
mode)
else:
logger.info("Creating AVA Meter for AVA dataset in %s mode" % mode)
self.cfg = cfg
self.lr = None
self.loss = ScalarMeter(cfg.LOG_PERIOD)
self.full_ava_test = cfg.AVA.FULL_TEST_ON_VAL if not is_custom_dataset else cfg.CUSTOM_DATASET.FULL_TEST_ON_VAL
self.mode = mode
self.iter_timer = Timer()
self.all_preds = []
self.all_ori_boxes = []
self.all_metadata = []
self.overall_iters = overall_iters
self.excluded_keys = read_exclusions(
os.path.join(cfg.AVA.ANNOTATION_DIR, cfg.AVA.EXCLUSION_FILE)
) if not is_custom_dataset else read_exclusions(
os.path.join(cfg.CUSTOM_DATASET.ANNOTATION_DIR,
cfg.CUSTOM_DATASET.EXCLUSION_FILE))
self.categories, self.class_whitelist = read_labelmap(
os.path.join(cfg.AVA.ANNOTATION_DIR, cfg.AVA.LABEL_MAP_FILE)
) if not is_custom_dataset else read_labelmap(
os.path.join(cfg.CUSTOM_DATASET.ANNOTATION_DIR,
cfg.CUSTOM_DATASET.LABEL_MAP_FILE))
gt_filename = os.path.join(
cfg.AVA.ANNOTATION_DIR, cfg.AVA.GROUNDTRUTH_FILE
) if not is_custom_dataset else os.path.join(
cfg.CUSTOM_DATASET.ANNOTATION_DIR,
cfg.CUSTOM_DATASET.GROUNDTRUTH_FILE)
self.full_groundtruth = read_csv(gt_filename, self.class_whitelist)
self.mini_groundtruth = get_ava_mini_groundtruth(self.full_groundtruth)
_, self.video_idx_to_name = ava_helper.load_image_lists(
cfg, mode == "train"
) if not is_custom_dataset else custom_helper.load_image_lists(
cfg, mode == "train")
def __init__(self,
cfg,
img_height,
first_middle_frame_index,
frames_per_second,
input_detection_queue=None,
output_detection_queue=None,
output_tracker_queue_visualization=None,
output_tracker_queue_action_recognition=None,
input_action_recognition_queue=None,
output_action_recognition_queue_visualization=None,
output_action_recognition_queue_result_export=None):
"""
Initialize the object
:param cfg: our demo config
:param img_height: (int) the height of the image
:param first_middle_frame_index: (int) the index of the first middle_frame index
:param frames_per_second: (float) the fps of the video -> required for determining middle frames
:param input_detection_queue: please refer to class MultiProcessDemo
:param output_detection_queue: please refer to class MultiProcessDemo
:param output_tracker_queue_visualization: please refer to class MultiProcessDemo
:param output_tracker_queue_action_recognition: please refer to class MultiProcessDemo
:param input_action_recognition_queue: please refer to class MultiProcessDemo
:param output_action_recognition_queue_visualization: please refer to class MultiProcessDemo
:param output_action_recognition_queue_result_export: please refer to class MultiProcessDemo
"""
setup_environment()
# Setup logging format
logging.setup_logging(cfg.OUTPUT_DIR)
self.cfg = cfg
# The name of the input video
self.demo_video_name = Path(self.cfg.DEMO.VIDEO_SOURCE_PATH).stem
# Whether we will export an image
self.export_video = self.cfg.DEMO.VIDEO_EXPORT_VIDEO_ENABLE
if self.export_video:
# number of digits for exporting the images (determines how many images can be stored)
self.number_of_digits_for_image_export = 10
# The path of the to be created video
self.export_video_path = os.path.join(
self.cfg.DEMO.OUTPUT_FOLDER,
self.demo_video_name + "_annotated.mp4")
# Whether we will display an image
self.display_video = self.cfg.DEMO.VIDEO_SHOW_VIDEO_ENABLE
self.cv2_display_name = "Demo: " + self.demo_video_name
# Whether we will display the meta information (Queues Sizes and img idx)
self.display_meta_info = cfg.DEMO.VIDEO_SHOW_VIDEO_DEBUGGING_INFO
# Used for finding the position of meta info
self.img_height = img_height
# Used for determining middle_frame_indices (they have the action prediction)
self.first_middle_frame_index = first_middle_frame_index
self.frames_per_second = frames_per_second
# Additional options for displaying the video
self.video_display_scaling_factor = cfg.DEMO.VIDEO_DISPLAY_SCALING_FACTOR
self.video_action_display_duration_milliseconds = cfg.DEMO.VIDEO_ACTION_DISPLAY_DURATION_MILLISECONDS
# The queues containing relevant information
self.input_detection_queue = input_detection_queue
self.output_detection_queue = output_detection_queue,
self.output_tracker_queue_visualization = output_tracker_queue_visualization
self.output_tracker_queue_action_recognition = output_tracker_queue_action_recognition,
self.input_action_recognition_queue = input_action_recognition_queue
self.output_action_recognition_queue_visualization = output_action_recognition_queue_visualization
self.output_action_recognition_queue_result_export = output_action_recognition_queue_result_export
# The queue sizes as specified in the config files
self.queue_size = self.cfg.DEMO.QSIZE_SECONDS * self.cfg.CUSTOM_DATASET.FRAME_RATE
# Used for terminating the process successfully
self.action_recognition_input_finished = False
# The information for displaying actions
# Load the categories:
self.path_to_label_map_file = os.path.join(cfg.CUSTOM_DATASET.ANNOTATION_DIR, cfg.CUSTOM_DATASET.LABEL_MAP_FILE) \
if not os.path.isfile(cfg.ACTIONRECOGNIZER.LABEL_MAP_FILE) \
else cfg.ACTIONRECOGNIZER.LABEL_MAP_FILE
# List of dicts (id, name)
self.action_categories, _ = read_labelmap(self.path_to_label_map_file)
# A color value for every category
self.palette_actions = np.random.randint(
64, 128, (len(self.action_categories), 3)).tolist()
# The information required for displaying person_tracking info
self.palette_person_ids = (2**11 - 1, 2**15 - 1, 2**20 - 1)
# The process for person detection
self.display_next_frame_process = mp.Process(
target=self.display_and_or_export_next_frame, args=())
# Used to test the correct order of images
self.display_img_idx = -1
# The information for action info display
self.current_action_output_img_idx = ""
self.current_pred_action_category_scores = ""
def __init__(self, cfg, img_height, img_width):
"""
Initialize the DemoMeter with the relevant paramters
:param cfg:
:param img_height: (int) the height of the input images
:param img_width: (int) the width of input images
"""
# Set up environment.
setup_environment()
# Setup logging format
logging.setup_logging(cfg.OUTPUT_DIR)
self.cfg = cfg
# In the case of an AVA-like predictor it is necessary to specify a
# cfg.ACTIONRECOGNIZER.LABEL_MAP_FILE, because it comprises all 80 categories.
# during the ava challenge only 60 categories were evaluated, an we
# want alle categories
path_to_label_map_file = os.path.join(cfg.CUSTOM_DATASET.ANNOTATION_DIR, cfg.CUSTOM_DATASET.LABEL_MAP_FILE) \
if not os.path.isfile(cfg.ACTIONRECOGNIZER.LABEL_MAP_FILE) \
else cfg.ACTIONRECOGNIZER.LABEL_MAP_FILE
# Export properties
datetime_for_filenames = datetime.datetime.now().strftime(
"%Y-%m-%d_%H_%M_%S")
self.delimiter = ","
assert cfg.DEMO.OUTPUT_FOLDER != "", "Please specify cfg.DEMO.OUTPUT_FOLDER to be able to export the output"
self.output_dir_path = self.cfg.DEMO.OUTPUT_FOLDER
self.file_name_demo_log = datetime_for_filenames + "_" + "demo_log"
self.file_name_demo_gt_like_file = datetime_for_filenames + "_" + "demo_gt_format"
self.results_gt_like_csv_path = os.path.join(
self.output_dir_path, self.file_name_demo_gt_like_file + ".csv")
self.results_log_path_prefix = os.path.join(self.output_dir_path,
self.file_name_demo_log)
self.results_log_csv_path = ""
self.results_xes_path = ""
# The minimum score for a predicted category to be exported
self.min_category_export_score = cfg.DEMO.EXPORT_MIN_CATEGORY_EXPORT_SCORE
# Whether a person can do multiple actions at the same time or not
# This influences the export options, since only the option with max value is chosen
self.multiple_action_possible = cfg.CUSTOM_DATASET.MULTIPLE_ACTION_POSSIBLE
# Resolution used for export
self.img_height = img_height
self.img_width = img_width
# List of dict with items "id" and "name"
self.categories, _ = read_labelmap(path_to_label_map_file)
# Replace delimiter out of category_name to guarantee good csv export
for idx in range(0, len(self.categories)):
self.categories[idx]["name"] = self.categories[idx][
"name"].replace(self.delimiter, "")
# The list-variables we use to store the demo prediction results.
# They will be used to export the information into csv or xes
self.res_person_tracking_outputs = []
self.res_pred_action_category_scores = []
self.res_all_metadata = []
self.res_case_ids = []
# This df is used to assign correct case_concept_name and concept_instance values
self.case_and_instance_df = self.create_empty_case_and_instance_df()
# Used to indicate that the activity instance has not yet completed
self.video_second_not_complete = -1
# Used as test for correct functionality of lifecycle_transition
self.not_closed_list = []