Python utils.label_map_util.convert_label_map_to_categories() Examples

The following are 5 code examples of utils.label_map_util.convert_label_map_to_categories(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module utils.label_map_util , or try the search function .
Example #1
Source File: app.py    From tensorflow-object-detection-example with Apache License 2.0 6 votes vote down vote up 
def __init__(self):

    label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
    categories = label_map_util.convert_label_map_to_categories(
        label_map, max_num_classes=90, use_display_name=True)
    self.category_index = label_map_util.create_category_index(categories)

    model_url = MODEL_URL
    base_url = os.path.dirname(model_url)+"/"
    model_file = os.path.basename(model_url)
    model_name = os.path.splitext(os.path.splitext(model_file)[0])[0]
    model_dir = tf.keras.utils.get_file(
        fname=model_name, origin=base_url + model_file, untar=True)
    model_dir = pathlib.Path(model_dir)/"saved_model"

    model = tf.saved_model.load(str(model_dir))
    model = model.signatures['serving_default']
    self.model = model
Example #2
Source File: model.py    From MAX-Object-Detector with Apache License 2.0 6 votes vote down vote up 
def __init__(self, model_file=PATH_TO_CKPT, label_file=PATH_TO_LABELS):
        logger.info('Loading model from: {}...'.format(model_file))
        detection_graph = tf.Graph()
        graph = tf.Graph()
        with tf.Session(graph=detection_graph):
            # load the graph ===
            # loading a (frozen) TensorFlow model into memory

            with graph.as_default():
                od_graph_def = tf.GraphDef()
                with tf.gfile.GFile(model_file, 'rb') as fid:
                    serialized_graph = fid.read()
                    od_graph_def.ParseFromString(serialized_graph)
                    tf.import_graph_def(od_graph_def, name='')

                # loading a label map
                label_map = label_map_util.load_labelmap(label_file)
                categories = label_map_util.convert_label_map_to_categories(label_map, max_num_classes=NUM_CLASSES,
                                                                            use_display_name=True)
                category_index = label_map_util.create_category_index(categories)

        # set up instance variables
        self.graph = graph
        self.category_index = category_index
        self.categories = categories
Example #3
Source File: app.py    From easy-tensorflow-multimodel-server with MIT License 5 votes vote down vote up 
def load_model(model_dir, model_prefix):
    label_map = label_map_util.load_labelmap('{}/{}{}'.format(model_dir, model_prefix, LABEL_MAP_SUFFIX))
    categories = label_map_util.convert_label_map_to_categories(
        label_map, max_num_classes=90, use_display_name=True)
    category_index = label_map_util.create_category_index(categories)

    detection_graph = tf.Graph()
    with detection_graph.as_default():
        od_graph_def = tf.GraphDef()
        with tf.gfile.GFile('{}/{}{}'.format(model_dir, model_prefix, MODEL_SUFFIX), 'rb') as fid:
            serialized_graph = fid.read()
            od_graph_def.ParseFromString(serialized_graph)
            tf.import_graph_def(od_graph_def, name='')

            # Get handles to input and output tensors
            ops = tf.get_default_graph().get_operations()
            all_tensor_names = {
                output.name
                for op in ops for output in op.outputs
            }
            tensor_dict = {}
            for key in [
                    'num_detections', 'detection_boxes', 'detection_scores',
                    'detection_classes'
            ]:
                tensor_name = key + ':0'
                if tensor_name in all_tensor_names:
                    tensor_dict[key] = tf.get_default_graph(
                    ).get_tensor_by_name(tensor_name)
                image_tensor = tf.get_default_graph().get_tensor_by_name(
                    'image_tensor:0')
                sess = tf.Session(graph=detection_graph)
    return {
        'session': sess,
        'image_tensor': image_tensor, 
        'tensor_dict': tensor_dict,
        'category_index': category_index
    }
Example #4
Source File: app.py    From tensorflow-object-detection-example with Apache License 2.0 5 votes vote down vote up 
def __init__(self):
    self.detection_graph = self._build_graph()
    self.sess = tf.Session(graph=self.detection_graph)

    label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
    categories = label_map_util.convert_label_map_to_categories(
        label_map, max_num_classes=90, use_display_name=True)
    self.category_index = label_map_util.create_category_index(categories)
Example #5
Source File: 06_youtube_ssd_demo.py    From Practical-Computer-Vision with MIT License 5 votes vote down vote up 
def load_label_dict(PATH_TO_LABELS):
  label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
  categories = label_map_util.convert_label_map_to_categories(label_map, max_num_classes=NUM_CLASSES, use_display_name=True)
  category_index = label_map_util.create_category_index(categories)
  #print(category_index)
  return category_index