neodroidvision.utilities.tf_utilities.tf_bb.draw_bounding_boxes_on_image_tensors

neodroidvision.utilities.tf_utilities.tf_bb.draw_bounding_boxes_on_image_tensors(images, boxes, classes, scores, category_index, instance_masks=None, keypoints=None, max_boxes_to_draw=20, min_score_thresh=0.2, line_thickness=2)[source]

Draws bounding boxes, masks, and keypoints on batch of image tensors.

Args: :param images: A 4D uint8 image tensor of shape [N, H, W, C]. :param boxes: [N, max_detections, 4] float32 tensor of detection boxes. :param classes: [N, max_detections] int tensor of detection classes. Note that classes are 1-indexed. :param scores: [N, max_detections] float32 tensor of detection scores. :param category_index: a dict that maps integer ids to category dicts. e.g. {1: {1: ‘dog’}, 2: {2: ‘cat’}, …} :param instance_masks: A 4D uint8 tensor of shape [N, max_detection, H, W] with instance masks. :param keypoints: A 4D float32 tensor of shape [N, max_detection, num_keypoints, 2] with keypoints. :param max_boxes_to_draw: Maximum number of boxes to draw on an image. Default 20. :param min_score_thresh: Minimum score threshold for visualization. Default 0.2. :param line_thickness:

Returns: 4D image tensor of type uint8, with boxes drawn on top.