diplomat deeplabcut label_videos

Summary

Create labeled videos using results generated by DIPLOMAT’s DEEPLABCUT frontend.

Usage

diplomat deeplabcut label_videos [-h] --config FILE --videos
                                        [FILE, ...]|FILE [--body_parts_to_plot [STR, ...]]
                                        [--shuffle INT]
                                        [--training_set_index INT]
                                        [--tracker STR] [--video_type STR]
                                        [--skeleton_color TO_RGBA]
                                        [--pcutoff FLOAT] [--dotsize INT]
                                        [--alphavalue FLOAT]
                                        [--colormap TO_COLORMAP]
                                        [--shape_list [STR, ...]]
                                        [--line_thickness INT]
                                        [--antialiasing BOOL]
                                        [--draw_hidden_tracks BOOL]
                                        [--output_codec CV2_FOURCC_STRING]
                                        [--upscale_factor FLOAT]

Options

-h, --help            show this help message and exit
--config FILE, -c FILE
                      The path to the DLC config.yaml. The visual settings
                      from the DLC config are used.
--videos [FILE, ...]|FILE, -v [FILE, ...]|FILE
                      A single path or list of paths, to the location of the
                      video files to annotate. Can also be a directory.
--body_parts_to_plot [STR, ...], -bptp [STR, ...]
                      A list of strings, specifying which body parts to
                      plot. Defaults to None, which plots points for all
                      body parts.
--shuffle INT, -s INT
                      int, optional. An integer specifying the shuffle index
                      of the training dataset used for training the network.
                      The default is 1.
--training_set_index INT, -tsi INT
                      int, optional. Integer specifying which
                      TrainingsetFraction to use. By default, the first
                      (note that TrainingFraction is a list in config.yaml).
--tracker STR, -t STR
                      String, the extension of the deeplabcut tracker used,
                      used to find the h5 file. Doesn't need to be set for
                      DIPLOMAT files.
--video_type STR, -vt STR
                      Optional string, the video extension to search for if
                      the 'videos' argument is a directory to search inside
                      ('.avi', '.mp4', ...).
--skeleton_color TO_RGBA
                      Color of the skeleton.
--pcutoff FLOAT       The probability to cutoff results below.
--dotsize INT         The size of the dots.
--alphavalue FLOAT    The alpha value of the dots.
--colormap TO_COLORMAP
                      The colormap to use for tracked points in the video.
                      Can be a matplotlib colormap or a list of matplotlib
                      colors.
--shape_list [STR, ...]
                      A list of shape names, shapes to use for drawing each
                      individual's dots.
--line_thickness INT  Thickness of lines drawn.
--antialiasing BOOL   Use antialiasing when drawing points.
--draw_hidden_tracks BOOL
                      Whether or not to draw locations under the pcutoff
                      value.
--output_codec CV2_FOURCC_STRING
                      The codec to use for the labeled video...
--upscale_factor FLOAT
                      An optional float multiplier to use for increasing the
                      size of the output video.