Export trained PyTorch detection model to TorchScript model

This Python script allows you to export a trained PyTorch detection model to a TorchScript model that can be easily deployed in various runtime environment, with an optimized latency and throughput.

The source code of this sample can be found in <install-prefix>/share/metavision/sdk/ml/python_samples/export_detector when installing Metavision SDK from installer or packages. For other deployment methods, check the page Path of Samples.

Expected Output

Compiled TorchScript Model that can be easily deployed during runtime.

Specifically, it will output:

  1. model.ptjit (the model)

  2. info_ssd_jit.json (the hyperparameters used during training)

Setup & requirements

You will need to provide the following input:

  • path to the checkpoint. You can use red_event_cube_all_classes.ckpt from our pre-trained models

  • path to the output directory

How to start

To run the script with red_event_cube_all_classes.ckpt:

python export_detector.py red_event_cube_all_classes.ckpt /path/to/output

You can also verify the performance of the trained checkpoint directly by testing it on an event-based recording. For example, to use driving_sample.raw as a verification sequence:

python export_detector.py red_event_cube_all_classes.ckpt /path/to/output --verification_sequence driving_sample.raw

To find the full list of options, run:

python export_detector.py -h