deepdisc.data_format.conversions

Attributes

logger

Functions

fitsim_to_numpy(img_files, outdir[, start_index])

Converts a list of single-band FITS images to multi-band numpy arrays

fitsim_to_hdf5(img_files, outname[, dset])

Converts a list of single-band FITS images to flattened multi-band images in an hdf5 file

ddict_to_hdf5(dataset_dicts, outname)

Converts a list of dataset dictionaries to an hdf5 file (for RAIL usage)

numpyim_to_hdf5(img_files, outname)

Converts a list of single-band FITS images to flattened multi-band images in an hdf5 file

convert_to_json(dict_list, output_file[, allow_cached])

Converts dataset into COCO format and saves it to a json file.

Module Contents

logger[source]
fitsim_to_numpy(img_files, outdir, start_index=0)[source]

Converts a list of single-band FITS images to multi-band numpy arrays

Parameters:

  • img_files (list[str]) – A nested list of the FITS image files. The first index is the image and the second index is the filter

  • outdir (str) – The directory to output the numpy arrays

  • start_index (int) – Index in the first img filename string used to chunk a unique identifier

  • end_index (int) – Index in the first img filename string used to chunk a unique identifier

fitsim_to_hdf5(img_files, outname, dset='train')[source]

Converts a list of single-band FITS images to flattened multi-band images in an hdf5 file

Parameters:

  • img_files (list[str]) – A nested list of the FITS image files. The first index is the image and the second index is the filter

  • outname (str) – The name of the output file

ddict_to_hdf5(dataset_dicts, outname)[source]

Converts a list of dataset dictionaries to an hdf5 file (for RAIL usage)

Parameters:

  • dataset_dicts (list[dict]) – The dataset dicts

  • outname (str) – The name of the output file

numpyim_to_hdf5(img_files, outname)[source]

Converts a list of single-band FITS images to flattened multi-band images in an hdf5 file

Parameters:

  • img_files (list[str]) – A nested list of the FITS image files. The first index is the image and the second index is the filter

  • outname (str) – The name of the output file

convert_to_json(dict_list, output_file, allow_cached=True)[source]

Converts dataset into COCO format and saves it to a json file. dataset_name must be registered in DatasetCatalog and in detectron2’s standard format.

Parameters:

  • dataset_name – reference from the config file to the catalogs must be registered in DatasetCatalog and in detectron2’s standard format

  • output_file – path of json file that will be saved to

  • allow_cached – if json file is already present then skip conversion