DeepLabCut data conversion

Install NeuroConv with the additional dependencies necessary for reading DeepLabCut data.

pip install "neuroconv[deeplabcut]"

Convert DeepLabCut pose estimation data to NWB using DeepLabCutInterface. This interface supports both .h5 and .csv output files from DeepLabCut.

>>> from datetime import datetime
>>> from zoneinfo import ZoneInfo
>>> from pathlib import Path
>>> from neuroconv.datainterfaces import DeepLabCutInterface

>>> file_path = BEHAVIOR_DATA_PATH / "DLC" / "open_field_without_video" / "m3v1mp4DLC_resnet50_openfieldAug20shuffle1_30000.h5"
>>> config_file_path = BEHAVIOR_DATA_PATH / "DLC" / "open_field_without_video" / "config.yaml"

>>> interface = DeepLabCutInterface(file_path=file_path, config_file_path=config_file_path, subject_name="ind1", verbose=False)

>>> metadata = interface.get_metadata()
>>> # For data provenance we add the time zone information to the conversion
>>> session_start_time = datetime(2020, 1, 1, 12, 30, 0, tzinfo=ZoneInfo("US/Pacific"))
>>> metadata["NWBFile"].update(session_start_time=session_start_time)
>>> # Choose a path for saving the nwb file and run the conversion
>>> interface.run_conversion(nwbfile_path=path_to_save_nwbfile, metadata=metadata)