neuralib.imglib.labeller
SequenceLabeller
Simple CV2-based viewer/labeller GUI for image sequences
Use Cases:
viewing the image sequences
label each image and save as csv dataframe (human-eval for population neurons activity profile)
Load sequences from a directory
Use CLI mode
See help:
python -m neuralib.imglib.labeller -h
Example:
python neuralib.imglib.labeller -D <DIR>
Use API call
from neuralib.imglib.labeller import SequenceLabeller
directory = ...
labeller = SequenceLabeller.load_from_dir(directory)
labeller.main()
Load sequences from sequences array
from neuralib.imglib.labeller import SequenceLabeller
arr = ... # numpy array with (F, H, W, <3>)
labeller = SequenceLabeller.load_sequences(arr)
labeller.main()
- class neuralib.imglib.labeller.SequenceLabeller[source]
- window_title: ClassVar[str] = 'SeqLabeller'
- __init__(seqs_info, output=None)[source]
- Parameters:
seqs_info (list[FrameInfo])
output (str | Path | bytes | BinaryIO | BufferedIOBase | BufferedReader | None)
- classmethod load_sequences(seqs, filenames=None, output=None)[source]
- Parameters:
seqs (ndarray | list[ndarray])
filenames (list[str] | None)
output (str | Path | bytes | BinaryIO | BufferedIOBase | BufferedReader | None)
- Returns:
- Return type:
Self
- classmethod load_from_dir(directory, file_suffix='.tif', sort_func=None, single_frame_per_file=True, output=None)[source]
- Parameters:
directory (str | Path | bytes | BinaryIO | BufferedIOBase | BufferedReader) – directory contain image sequences
file_suffix (str) – sequence file suffix
sort_func (Callable[[Path], Any] | None) – sorted function with signature (filename:Path) -> Comparable
single_frame_per_file (bool)
output (str | Path | bytes | BinaryIO | BufferedIOBase | BufferedReader | None)
- Returns:
- Return type:
Self
- property n_frames: int
aka. number of images
- property current_frame_index: int
- property text_color: float | tuple[int, int, int]