airpack_scripts.pytorch.run_benchmarks
¶
Utility script to benchmark the data rate that a neural network will support.
Module Contents¶
-
airpack_scripts.pytorch.run_benchmarks.
benchmark
(onnx_file)¶ Convert an onnx file to an optimized plan file and benchmark the maximum data rate throughput.
See also
This is a wrapper for
airpack.deploy.trt.onnx2plan()
andairpack.deploy.trt.plan_bench()
that is setup with default values for theairpack.pytorch.model.Network()
. If non-default parameters are needed for your customization, it is better practice to call directly theairpack.deploy.trt.onnx2plan()
andairpack.pytorch.model.Network()
instead of this demonstration wrapper.- Parameters
onnx_file (Union[str, os.PathLike]) – Trained neural network saved as an onnx file
- Returns
- Return type
None