​

module  pixeltable.functions.vision

import pixeltable as pxt
from pixeltable.functions import vision as pxtv

t = pxt.get_table(...)
t.select(pxtv.draw_bounding_boxes(t.img, boxes=t.boxes, label=t.labels)).collect()

​

udf  draw_bounding_boxes()

@pxt.udf
draw_bounding_boxes(
    img: pxt.Image,
    boxes: pxt.Json,
    *,
    labels: pxt.Json | None = None,
    color: pxt.String | None = None,
    box_colors: pxt.Json | None = None,
    alpha: pxt.Float | None = None,
    fill: pxt.Bool = False,
    fill_alpha: pxt.Float | None = None,
    width: pxt.Int = 1,
    font: pxt.String | None = None,
    font_size: pxt.Int | None = None
) -> pxt.Image

• img (pxt.Image): The image on which to draw the bounding boxes.
• boxes (pxt.Json): List of bounding boxes, each represented as [xmin, ymin, xmax, ymax].
• labels (pxt.Json | None): List of labels for each bounding box.
• color (pxt.String | None): Single color to be used for all bounding boxes and labels.
• box_colors (pxt.Json | None): List of colors, one per bounding box.
• alpha (pxt.Float | None): Opacity (0-1) of the bounding box borders and labels. If non-None, overrides any alpha in color/box_colors.
• fill (pxt.Bool): Whether to fill the bounding boxes with color.
• fill_alpha (pxt.Float | None): Opacity (0-1) of the bounding box fill. If non-None, overrides any alpha in color/box_colors.
• width (pxt.Int): Width of the bounding box borders.
• font (pxt.String | None): Name of a system font or path to a TrueType font file, as required by PIL.ImageFont.truetype(). If None, uses the default provided by PIL.ImageFont.load_default().
• font_size (pxt.Int | None): Size of the font used for labels in points. Only used in conjunction with non-None font argument.

• pxt.Image: The image with bounding boxes drawn on it.

​

udf  eval_detections()

@pxt.udf
eval_detections(
    pred_bboxes: pxt.Json,
    pred_labels: pxt.Json,
    pred_scores: pxt.Json,
    gt_bboxes: pxt.Json,
    gt_labels: pxt.Json,
    min_iou: pxt.Float = 0.5
) -> pxt.Json

• pred_bboxes (pxt.Json): List of predicted bounding boxes, each represented as [xmin, ymin, xmax, ymax].
• pred_labels (pxt.Json): List of predicted labels.
• pred_scores (pxt.Json): List of predicted scores.
• gt_bboxes (pxt.Json): List of ground truth bounding boxes, each represented as [xmin, ymin, xmax, ymax].
• gt_labels (pxt.Json): List of ground truth labels.
• min_iou (pxt.Float): Minimum intersection-over-union (IoU) threshold for a predicted bounding box to be considered a true positive.

• pxt.Json: A list of dictionaries, one per label class, with the following structure:
  Copy

  Ask AI

  {
      'min_iou': float,  # The value of `min_iou` used for the detections
      'class': int,  # The label class
      'tp': list[int],  # List of 1's and 0's indicating true positives for each
                        # predicted bounding box of this class
      'fp': list[int],  # List of 1's and 0's indicating false positives for each
                        # predicted bounding box of this class; `fp[n] == 1 - tp[n]`
      'scores': list[float],  # List of predicted scores for each bounding box of this class
      'num_gts': int,  # Number of ground truth bounding boxes of this class
  }