objectscope.utils
=================

.. py:module:: objectscope.utils


Functions
---------

.. autoapisummary::

   objectscope.utils.launch_tensorboard
   objectscope.utils.run_optimize_model
   objectscope.utils.compute_statistics
   objectscope.utils.predict_bbox
   objectscope.utils.draw_bbox_and_polygons
   objectscope.utils.save_class_metadata


Module Contents
---------------

.. py:function:: launch_tensorboard(logdir, port_num=None)

.. py:function:: run_optimize_model(model_name_or_path, output_dir, device='cpu', provider='CPUExecutionProvider', precision='int4')

.. py:function:: compute_statistics(img_paths: list)

.. py:function:: predict_bbox(image, model_path)

.. py:function:: draw_bbox_and_polygons(image, bboxes, scores, class_names=None, score_thresh=0.3, polygons=None) -> PIL.Image

   Visualize the bbox(es) and segmentation mask(s) of objects in image(s)

   :param image: PIL Image to draw bbox and segmentation on.
   :type image: Image
   :param bboxes: List of boundary boxes.
   :type bboxes: List
   :param scores: Confidence score to use for filtering and drawing on image.
   :type scores: List
   :param class_names: Name(s) of objects for each bbox and polygon.
   :type class_names: List
   :param score_thresh: Threshold to filter out low-confidence detections. Defaults to 0.3.
   :type score_thresh: float, optional
   :param polygons: List of segmentation masks. Defaults to None.
   :type polygons: List, optional

   Returns: PIL Image with drawn bbox and segmentation mask.


.. py:function:: save_class_metadata(train_data_name, save_metadata_as)