format ( len ( artists3 ) + 1, num_frames )) # Read the detections detections = detector. metadata ), 2 ) if show_class and show_score : draw. metadata score = round ( float ( detection. rectangle (, outline = ( 0, 255, 0 ), width = 1 ) class_ = detection. reshape ( 4 ) x1, y1 = ( x0 + w, y0 + h ) draw. Draw ( image ) for detection in detections : x0, y0, w, h = np.
Default is ``False`` Returns - : :class:`PIL.Image` Image with detections drawn """ draw = ImageDraw. Default is ``False`` show_score: bool Whether to draw the score of the object. Import numpy as np from PIL import ImageDraw def draw_detections ( image, detections, show_class = False, show_score = False ): """ Draw detections on an image Parameters - image: :class:`PIL.Image` Image on which to draw the detections detections: : set of :class:`~.Detection` A set of detections generated by :class:`~.TensorFlowBoxObjectDetector` show_class: bool Whether to draw the class of the object. Path ( label_dir ) return str ( label_dir ) LABEL_FILENAME = 'mscoco_label_map.pbtxt' PATH_TO_LABELS = download_labels ( LABEL_FILENAME ) get_file ( fname = filename, origin = base_url + filename, untar = False ) label_dir = pathlib. Path ( model_dir ) / "saved_model" return str ( model_dir ) MODEL_NAME = 'faster_rcnn_inception_resnet_v2_atrous_lowproposals_coco_2018_01_28' PATH_TO_MODEL = download_model ( MODEL_NAME ) # Download labels file def download_labels ( filename ): base_url = '' label_dir = tf. get_file ( fname = model_name, origin = base_url + model_file, untar = True ) model_dir = pathlib.
set_memory_growth ( gpu, True ) # Download and extract model def download_model ( model_name ): base_url = '' model_file = model_name + '.tar.gz' model_dir = tf. list_physical_devices ( 'GPU' ) for gpu in gpus : tf. setLevel ( 'ERROR' ) # Suppress TensorFlow logging (2) # Enable GPU dynamic memory allocation gpus = tf. environ = '2' # Suppress TensorFlow logging (1) import pathlib import tensorflow as tf tf.
0 kommentar(er)
