motile_tracker.example_data
Attributes
Functions
|
Loads the Mouse Embryo Membrane raw data and segmentation data from |
|
Loads the Fluo-N2DL-HeLa 01 training raw data and silver truth from |
|
Loads the Fluo-N2DL-HeLa 01 training raw data and silver truth from |
|
Read a zenodo dataset (assumes pre-downloaded) |
|
Read a CTC dataset from a zarr (assumes pre-downloaded and converted) |
|
Download a sample dataset from zenodo doi and unzip it, then delete the zip. Then convert the tiffs to |
|
Download a dataset from the Cell Tracking Challenge |
|
Convert 4D tiff file image data to zarr. Also deletes the tiffs! |
|
Convert tiff file image data to zarr. Also deletes the tiffs! |
Module Contents
- motile_tracker.example_data.logger
- motile_tracker.example_data.Mouse_Embryo_Membrane() list[napari.types.LayerData]
Loads the Mouse Embryo Membrane raw data and segmentation data from the appdir “user data dir”. Will download it from the Zenodo DOI if it is not present already. Returns:
- list[LayerData]: An image layer of raw data and a segmentation labels
layer
- motile_tracker.example_data.Fluo_N2DL_HeLa() list[napari.types.LayerData]
Loads the Fluo-N2DL-HeLa 01 training raw data and silver truth from the appdir “user data dir”. Will download it from the CTC and convert it to zarr if it is not present already. Returns:
- list[LayerData]: An image layer of 01 training raw data and a labels
layer of 01 training silver truth labels
- motile_tracker.example_data.Fluo_N2DL_HeLa_crop() list[napari.types.LayerData]
Loads the Fluo-N2DL-HeLa 01 training raw data and silver truth from the appdir “user data dir”. Will download it from the CTC and convert it to zarr if it is not present already. Returns:
- list[LayerData]: An image layer of 01 training raw data and a labels
layer of 01 training silver truth labels
- motile_tracker.example_data.read_zenodo_dataset(ds_name: str, raw_name: str, label_name: str, data_dir: pathlib.Path) list[napari.types.LayerData]
Read a zenodo dataset (assumes pre-downloaded) and returns a list of layer data for making napari layers
- Args:
ds_name (str): name to give to the dataset raw_name (str): name of the file that points to the intensity data label_name (str): name of the file that points to the segmentation data data_dir (Path): Path to the directory containing the images
- Returns:
- list[LayerData]: An image layer of raw data and a segmentation labels
layer
- motile_tracker.example_data.read_ctc_dataset(ds_name: str, data_dir: pathlib.Path, crop_region=False) list[napari.types.LayerData]
Read a CTC dataset from a zarr (assumes pre-downloaded and converted) and returns a list of layer data for making napari layers
- Args:
ds_name (str): Dataset name data_dir (Path): Path to the directory containing the zarr
- Returns:
- list[LayerData]: An image layer of 01 training raw data and a labels
layer of 01 training silver truth labels
- motile_tracker.example_data.download_zenodo_dataset(ds_name: str, raw_name: str, label_name: str, data_dir: pathlib.Path) None
Download a sample dataset from zenodo doi and unzip it, then delete the zip. Then convert the tiffs to zarrs for the first training set consisting of 3D membrane intensity images and segmentation.
- Args:
ds_name (str): Name to give to the dataset raw_name (str): Name of the file that contains the intensity data label_name (str): Name of the file that contains the label data data_dir (Path): The directory in which to store the data.
- motile_tracker.example_data.download_ctc_dataset(ds_name: str, data_dir: pathlib.Path) None
Download a dataset from the Cell Tracking Challenge and unzip it, then delete the zip. Then convert the tiffs to zarrs for the first training set images and silver truth.
- Args:
ds_name (str): Dataset name, according to the CTC data_dir (Path): The directory in which to store the data.
- motile_tracker.example_data.convert_4d_arr_to_zarr(tiff_file: str, zarr_path: str, zarr_group: str, relabel=False)
Convert 4D tiff file image data to zarr. Also deletes the tiffs! Args:
tiff_file (str): string representing path to tif file to be converted zarr_path (str): path to the zarr file to write the output to zarr_group (str): group within the zarr store to write the data to relabel (bool): if true, relabels the segmentations to be unique over time
- motile_tracker.example_data.convert_to_zarr(tiff_path: pathlib.Path, zarr_path: pathlib.Path, zarr_group: str, relabel=False)
Convert tiff file image data to zarr. Also deletes the tiffs! Args:
tif_path (Path): Path to the directory containing the tiff files zarr_path (Path): path to the zarr file to write the output to zarr_group (Path): group within the zarr store to write the data to