nopenpilot/selfdrive/modeld/thneed
George Hotz 5c5a56c5e6
thneed: a more sane way of doing record/debug (#23938)
Co-authored-by: Comma Device <device@comma.ai>
2022-03-10 16:33:35 -08:00
..
include thneed saves 45% of a core (#1512) 2020-05-15 13:53:01 -07:00
kernels minor cleanups, fix non binary compile (#23882) 2022-03-01 16:05:44 -08:00
README thneed saves 45% of a core (#1512) 2020-05-15 13:53:01 -07:00
__init__.py model: mse err from 0.02-> 0.000056 (#23891) 2022-03-02 20:52:17 -08:00
compile.cc thneed: a more sane way of doing record/debug (#23938) 2022-03-10 16:33:35 -08:00
lib.py model: mse err from 0.02-> 0.000056 (#23891) 2022-03-02 20:52:17 -08:00
optimizer.cc minor cleanups, fix non binary compile (#23882) 2022-03-01 16:05:44 -08:00
serialize.cc thneed: a more sane way of doing record/debug (#23938) 2022-03-10 16:33:35 -08:00
thneed.cc thneed: a more sane way of doing record/debug (#23938) 2022-03-10 16:33:35 -08:00
thneed.h thneed: a more sane way of doing record/debug (#23938) 2022-03-10 16:33:35 -08:00
weights_fixup.py model: mse err from 0.02-> 0.000056 (#23891) 2022-03-02 20:52:17 -08:00

README

thneed is an SNPE accelerator. I know SNPE is already an accelerator, but sometimes things need to go even faster..

It runs on the local device, and caches a single model run. Then it replays it, but fast.

thneed slices through abstraction layers like a fish.

You need a thneed.