Visualization of Preprocessed HDF5 Files

This Python script allows you to visualize HDF5 files, containing preprocessed event tensors. If bounding boxes are provided, they will be visualized altogether in the detection mode.

Another implementation of this script is available in viz_cd_process_data sample.

Expected Output

A video showing the preprocessed event data in HDF5 format (h5).

Setup & requirements

To run the script, you need:

a path containing one or multiple h5 files under the subfolders named train, val or test.

Note:

with --detection enabled, it is set to visualize object detection data with ground-truth (GT) labels. In this case, a label_map_dictionary.json file and NPY Bbox labels are required to be included in the input path.
with --video-output defined, a video will be saved locally.

How to start

To run the script:

Linux

python3 viz_data.py /path/to/folder_with_hdf5_files

Windows

python viz_data.py /path/to/folder_with_hdf5_files

To find the full list of options, run:

Linux

python3 viz_data.py -h

Windows

python viz_data.py -h