Files
dragonpilot/selfdrive/modeld/thneed
George Hotz 2c7542d34e Refactor convolutions (#23807)
* one conv with defines

* add conv

* building works on C3

* this is num_outputs too, process replay is so useful

Co-authored-by: Comma Device <device@comma.ai>
2022-02-20 11:55:23 -08:00
..
2022-02-20 11:55:23 -08:00
2022-02-19 16:06:31 -08:00
2022-02-20 11:55:23 -08:00
2020-05-15 13:53:01 -07:00
2022-02-15 15:32:00 -08:00
2022-02-15 15:32:00 -08:00

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.