pytorch nightly build should be installed, see Start Locally.
git clone https://github.com/sdpython/experimental-experiment.git pip install onnxruntime-gpu pynvml pip install -r requirements-dev.txt export PYTHONPATH=$PYTHONPATH:<this folder>
The script evaluates the memory peak, the computation time of the exporters. It also compares the exported models when run through onnxruntime. The full script takes around 20 minutes to complete. It stores on disk all the graphs, the data used to draw them, and the models.
python _doc/examples/plot_torch_export.py -s large